An independent, community-friendly plugin index for DeepSeek Harness (dsh). Curated by automation + human review. Topic:
dsh-plugin.
| Plugin | Description | Install | Status | Security | Trial | Checked at | Commit |
|---|---|---|---|---|---|---|---|
| dsh-netdoctor | Network diagnostics toolbox: DNS lookup (10 record types incl. SOA/CAA), multi-resolver DNS propagation check (one record across 6 public resolvers, answer sets grouped by record content, failed/slow resolvers reported as failed), ICMP ping, TCP port check, TLS cert check, traceroute, public IP, WHOIS registry lookup (TCP 43, IANA referral chain + TLD fallback map, ARIN for IPs, structured summary) — eight read-only probes, zero runtime dependencies | dsh plugin --profile web add github:TYEclipse/dsh-netdoctor#v0.3.0 |
✅ active | ✅ | ✅ e2e (isolated install v0.3.0, mirror friction=none; installed-copy execution 8/8 anchors incl. timeout + failure paths; LLM-driven headless run: dns_propagation → 6/6 resolvers answered, consistent) | 2026-10-07 | 63f31ba |
| dsh-webfetch | Web page reader: fetch any URL as clean Markdown / plain text, inventory links, read RSS/Atom feeds, inspect HTTP status/headers/redirect chain without the body (web_headers: HEAD with automatic GET fallback), extract HTML tables as structured rows (web_table: header detection, colspan/rowspan grid expansion, row/table caps), read a page's own metadata (web_meta: canonical, Open Graph/article/Twitter properties, hreflang alternates, feed autodiscovery, icons, JSON-LD @type summaries — invalid blocks reported, not dropped), zero-dependency http proxy support — zero runtime dependencies, read-only | dsh plugin --profile web add github:TYEclipse/dsh-webfetch#v0.5.0 |
✅ active | ✅ | ✅ e2e (R65: isolated install v0.5.0 friction=none, resolved 0.5.0; installed-copy execution of the published dist — web_meta returned canonical/lang/charset plus resolved hrefs, JSON-LD 2 blocks with 1 invalid reported with the parser message, web_table still registered; 145 tests green, coverage 90.56%, oracle in test/oracle/anchors.py) | 2026-10-10 | dfc289e |
| dsh-units | Unit conversion toolbox: 22 categories (length, mass, temperature, data sizes decimal-vs-binary, data transfer rates Mbps-vs-MB/s, acceleration incl. g-force, illumination lux/foot-candle, speed, time, volume, pressure, energy, angle, frequency, power with 3 horsepower definitions, force, torque, typography px/pt/em/rem, volumetric flow rate m³/s-L/min-CFM-gpm, density kg/m³-lb/ft³-lb/gal, fuel economy mpg ↔ L/100km) plus a unit-price tool that normalizes and ranks price-per-unit offers (1–6 offers with pack quantities, cheapest + spread in percent; temperatures and fuel economy refused) — zero runtime dependencies, pure math | dsh plugin --profile web add github:TYEclipse/dsh-units#v0.5.0 |
✅ active | ✅ | ✅ e2e (isolated install v0.5.0, mirror friction=none, resolved.installed 0.5.0; installed-copy execution 15/15 anchors — unit_price 3.99/lb vs 8.5/kg → best #2 at 8.5/kg spread 3.370046%, 500 g pack → 8.58/kg, 1 lb/gal → 119.826427 kg/m³, 1 gpm → 0.0630902 L/s; regressions 100 Mbps→12.5 MB/s, 100 km→62.137119 mi, 20 mpg→11.760729 l/100km) | 2026-10-08 | dc917ae |
| dsh-color | Color toolbox: parse/convert any CSS color (hex, rgb()/hsl()/hwb(), all 148 CSS Color 4 named colors), WCAG 2.x contrast ratio with AA/AAA verdicts, named-color lookup by name or value, harmonious palette generation (color_scheme: complementary / analogous / triadic / split-complementary / tetradic / square / monochromatic), color adjustments (adjust_color: lighten / darken / saturate / desaturate / hue-rotate), color blending (blend_colors: alpha compositing "over" and premultiplied sRGB interpolation "mix", i.e. the color-mix() math), contrast repair (ensure_contrast), perceptual color difference (color_difference: CIEDE2000 plus CIE76, both CIELAB colors under D65, plain-language verdict and tolerance check) and perceptually even tint/shade ramps (color_scale: tints / shades / both / between interpolated in Oklab, out-of-gamut steps clamped, each step reporting its ΔE00 from the base) — zero runtime dependencies, pure math | dsh plugin --profile web add github:TYEclipse/dsh-color#v0.4.0 |
✅ active | ✅ | ✅ e2e (R66: isolated install v0.4.0, mirror friction=none, resolved.installed 0.4.0; installed-copy execution 20/20 anchors — ΔE00 #336699 vs #3366ff = 11.7766 while ΔE76 = 61.1101, white vs black = 100, #000000 vs #010101 = 0.1571; Oklab tint ramp #336699→#658bb3→#97b1cd→#cad7e6→#ffffff against sRGB #668cb3 at the same step, translucent ramp #33669980→#97b1cdbf→#ffffff, steps clamped to 11; 138 tests green, coverage 94.74%; oracle at test/oracle/anchors.py replays the published 34-pair CIEDE2000 reference table, max deviation 4.95e-05) | 2026-10-11 | 84cb3f0 |
| Code2Skill | Three agent skills that generate portable Function / MCP Tool / workflow Skill packages (with offline tests) from user-authorized code, plus independent flow and source-semantics review — pure skill bundle, MIT | dsh plugin --profile web add github:leechen298/Code2Skill#v1.2.0 |
✅ active | ✅ | ✅ e2e (R65 re-verification, expired-row queue: re-pinned v1.1.3 → v1.2.0; isolated install friction=none, resolved 1.2.0; dump-config shows code2skill-bundled-skills + provider code2skill-bundle; installed-copy execution 18/18 — three SKILL.md files with matching frontmatter names, patch mounts @deepseek-ai/dsh-skill-filesystem with watch off, files whitelist is the bundle only. Not run: LLM-driven headless session — @deepseek-ai/dsh-headless installs from neither registry on this host) | 2026-10-10 | 27bac3f2 |
| dsh-semver | Semantic versioning toolbox: parse any semver string (semver_parse), compare versions with spec-compliant prerelease ordering (semver_compare, build metadata ignored), check npm-style ranges (semver_satisfies: ^ ~ >= <= > < =, x-ranges, hyphen, ||, AND, tuple-lock prerelease semantics, includePrerelease override), increment versions per npm semver.inc incl. prerelease counters and identifier restarts (semver_inc), report npm semver.diff release-type differences with special cases (semver_diff), and sort version lists with build-metadata tie-break (semver_sort), find the lowest version a range accepts (semver_min_version: npm minVersion parity — unsatisfiable combinations report satisfiable: false instead of a guessed bound), and check whether two ranges can be satisfied at once (semver_intersects: npm intersects parity, plus a witness version verified against both ranges). v0.4.0 adds pulling a version out of arbitrary text (semver_coerce: npm coerce parity — the first number run wins, so a changelog line coerces to its date 2026.0.0 and an unrepresentable component is reported as no-version with a reason, never rounded) and placing a version relative to a whole range (semver_outside: npm gtr/ltr parity — above/below/inside plus the gap between alternatives that neither direction covers; npm's tuple-lock quirk is reported as npm reports it) — zero runtime dependencies, pure logic; v0.3.0 fixed ~1.2.3 silently accepting 1.2.0/1.2.1 |
dsh plugin --profile web add github:TYEclipse/dsh-semver#v0.4.0 |
✅ active | ✅ | ✅ e2e (R67: isolated install #v0.4.0 friction=none, resolved 0.4.0; installed-copy execution 13/13 anchors on the published dist — 10 tools registered, semver_coerce "node v18.16.1" → 18.16.1 and "changelog 2026-10-12: 4.5.6 released" → 2026.0.0 (the date wins, as npm does), semver_outside 2.0.0 vs ^1.2.3 → above / range ^1.0.0 || ^3.0.0 → gap, v0.3.x anchors unregressed; 154 tests green, coverage 92.55%; npm-anchored oracle incl. comparator-shape sweep and a --check self-check) |
2026-10-12 | 1943b63 |
| Archify for DSH | Opt-in skill-only bundle (@tt-a1i/archify-dsh) bringing the Archify architecture-diagram skill to dsh: typed JSON specs (architecture / workflow / sequence / dataflow / lifecycle) rendered to self-contained interactive HTML with inline SVG, showcase-quality validation (9 artifact checks) — pure skill bundle, MIT | dsh plugin --profile web add @tt-a1i/archify-dsh@1.0.0 |
✅ active | ✅ zero deps, no install scripts, no telemetry or analytics SDK; render/validate/check run fully offline — only the finalize delivery receipt performs a bounded update-manifest fetch to tt-a1i.github.io |
✅ e2e (re-verified 2026-10-09 on the freshly released 1.0.0: isolated install @tt-a1i/archify-dsh@1.0.0 — China mirror on the first try, friction=none, resolved.installed 1.0.0; zero deps, no install scripts; archify-skill-filesystem row present in the composed config (370-line dump); archify doctor all-ok on Node 26; installed-copy CLI: render architecture example at showcase quality → 762,310-byte standalone HTML, then archify check 9/9 artifact checks pass. Earlier verification 2026-08-16 was the skill's own headless 9/9 showcase validation. Upstream moved 0.1.0 → 1.0.0; the row now pins the re-verified 1.0.0) |
2026-10-09 | 1.0.0 |
| dsh-finance | Money math toolbox: fixed-rate loan payment with amortization schedule and extra-payment impact (loan_payment), compound growth projection with monthly contributions and any compounding frequency (compound_growth), nominal ↔ effective annual rate conversion incl. continuous (rate_convert), NPV/IRR/payback cash-flow analysis with explicit no-root/multiple-root reporting (cashflow_analysis), retirement withdrawal planning — time-to-exhaustion + sustainable withdrawal with lasts_horizon verdict (retirement_plan), goal-based saving — months to a target or the contribution a deadline requires, with the deadline payment rounded up to the cent and the projection simulated from it, plus an on_track verdict and an honest unreachable instead of an invented month count (savings_goal), inflation-adjusted purchasing power — future cost, present value, and with a nominal return the exact Fisher real return plus nominal/real future values side by side, deflation and fractional horizons included (inflation_adjust), and multi-debt payoff planning — minimums first, the leftover budget on one target debt at a time, with both avalanche (highest rate first) and snowball (smallest balance first) simulated in full so the cheaper ordering, the interest saved and the order balances actually clear in are numbers rather than slogans, and a budget that never clears reported honestly instead of an invented month count (debt_payoff) — zero runtime dependencies, pure arithmetic, headline values verified against published anchors (Excel IRR example, mortgage tables) and an independent Python oracle that ships with the repo (test/oracle/anchors.py, eight sections + --check self-test; every test file carries an ORACLE: provenance marker) |
dsh plugin --profile web add github:TYEclipse/dsh-finance#v0.4.0 |
✅ active | ✅ | ✅ e2e (isolated install #v0.4.0, friction=none, resolved 0.4.0; installed-copy anchor replay — debt_payoff two cards 5000@22% + 2000@12% on 600/mo: avalanche 13 months, paid 7739.37, interest 739.37, card A clearing month 11 and card B month 13; snowball 14 months / 895.70 → avalanche saves 156.33 and one month; a 10/mo budget on a 24% card reported as never clearing with no invented month count; regressions loan_payment 1432.25 / 215610, savings_goal 65 months, inflation_adjust real 3.414634%, plus the 0.2.x/0.3.x suites; 133 tests, coverage 92.67%, oracle --check 51 anchors green) |
2026-10-13 | b4fa073 |
| dsh-ipcalc | IP & subnet math toolbox: full IPv4 subnet layouts (ipv4_subnet: network/broadcast/mask/hosts + IANA classes, RFC 3021 /31), minimal covering CIDR aggregation (ipv4_summarize), equal subnet splitting by part count or target prefix (ipv4_split: host-bit masking, 256-subnet cap), VLSM allocation from host counts (ipv4_allocate: smallest prefix that fits each request, placement order, leftover free blocks and waste, largest-first or input order, optional RFC 3021 /31 and /32 shortcuts), pool subtraction with the surviving free space (ipv4_exclude: minimal free CIDR list, exact free address count, per-entry removal counts, exclusions outside the pool reported rather than clipped), arbitrary address ranges turned into minimal exact CIDR lists (ipv4_range: the inverse of summarizing), IPv4/IPv6 parsing with RFC 5952 normalization and embedded-IPv4 recognition (ip_parse), IPv6 subnet layouts with 128-bit BigInt math and exact decimal-string address counts (ipv6_subnet, RFC 6164 /127), and CIDR membership tests for bare IPv4/IPv6 addresses with mixed-version rejection (ip_match) — zero runtime dependencies, pure local math, no network I/O | dsh plugin --profile web add github:TYEclipse/dsh-ipcalc#v0.4.0 |
✅ active | ✅ | ✅ e2e (R70: isolated install v0.4.0, mirror friction=none, resolved.installed 0.4.0; installed-copy execution of the published dist — ipv4_allocate 10.0.0.0/16 hosts [100,50,20,20,5] → 5 subnets, 264 of 65536 addresses used, 69 wasted, 12 free blocks; point-to-point run 1 host → /32 and 2 hosts → /31; capacity error reported as "requests need 384 addresses but 10.0.0.0/24 only has 256"; ipv4_exclude 10.0.0.0/16 minus 10.0.0.0/24 and 10.0.8.0/22 → 8 free blocks, 64256 addresses, 1280 removed; regressions ipv4_subnet 10.10.10.10/255.255.255.248 → 10.10.10.8/29 and ipv6_subnet /64 exact counts; 224 tests green, coverage 96.44%, oracle test/oracle/anchors.py with --check) | 2026-10-15 | 111c80e |
| dsh-geodesy | Geodesic math toolbox: great-circle distance with bearings and compass direction (geo_distance), initial/final bearings plus great-circle midpoint (geo_bearing), direct-problem destination point with round-trip check (geo_destination), decimal/DMS coordinate parsing (coord_parse), rhumb-line constant-heading distance & bearing (geo_rhumb), great-circle path intersection with antipodal crossing (geo_intersection), spherical polygon area via spherical excess (geo_area), off-track distance to a great-circle path — signed cross-track + along-track, perpendicular foot, distance to the segment (geo_cross_track), inside/outside test for a spherical polygon reporting both sides of the boundary with the containing region's area (geo_point_in_polygon), multi-leg route totals with per-leg heading and running total plus detour vs the straight line (geo_path), and spherical-cap geometry — exact area, boundary-circle length, pole/antimeridian-aware lat/lon box, distance-based containment (geo_circle) — zero runtime dependencies, pure trigonometry on the IUGG mean Earth radius, configurable radiusKm | dsh plugin --profile web add github:TYEclipse/dsh-geodesy#v0.4.0 | ✅ active | ✅ zero deps, no network | ✅ e2e (R72: isolated install #v0.4.0 friction=none, resolved 0.4.0; 11 tools on the installed copy; published-dist execution of the new tools — route totals, zero-length leg reported without a heading, and a 300 km cap with the pole and antimeridian box cases; older anchors unchanged: geo_distance 1067.311645 km, cross-track 111.19508 km, octant area 63758235.121609 km², rhumb 7076.411574 km; 223 tests, coverage 92.09%, all anchors in one committed oracle test/oracle/anchors.py with a --check self-check) | 2026-10-17 | 7b3705d |
| dsh-checkdigit | Check-digit mathematics toolbox: generate, validate, repair and auto-detect check digits for 17 schemes — Luhn (cards/IMEI), Verhoeff, Damm, ISBN-10 (mod-11, X) / ISBN-13, EAN-8/13, UPC-A, GTIN-14/SSCC-18, ISSN (ISO 3297, X), ISIN (ISO 6166), CUSIP (ANSI X9.6), SEDOL (7 chars, weights 1,3,1,7,3,9, letters A=10…Z=35, vowels never issued; digit-leading codes are old-style and must be all digits), IBAN (ISO 13616, 75+ country BBAN table), CAS Registry Number (position-weighted mod 10), ABA routing number (3-7-1 weighted mod 10) and NPI (US provider id: Luhn over the constant 80840 prefix, entity-type first digit 1 or 2) — plus ISBN-10 ⇄ ISBN-13 conversion (978-prefix semantics, hyphen-group preservation), a single-edit repair search (checkdigit_repair: corrected check character, swapped adjacent pair or one mistyped payload character, every candidate re-validated by the scheme itself) and a batch validator (checkdigit_batch: 1–50 values in one call, per-row scheme/validity plus valid/invalid/unrecognized counts and a per-scheme breakdown; empty or oversized lists error out instead of truncating) — zero runtime dependencies, integer arithmetic only, separators ignored on input, anchors reproducible from the in-repo oracle | dsh plugin --profile web add github:TYEclipse/dsh-checkdigit#v0.4.0 |
✅ active | ✅ | ✅ e2e (isolated install #v0.4.0 friction=none, resolved 0.4.0; published artifact executed: 6 tools registered, sedol B15KXQ → B15KXQ8, sedol B15KXQ7 → expected 8, npi 1245319599 valid, batch auto-detect 8 values → 4 valid / 3 invalid / 1 unrecognized with luhn×2 sedol×2 ean13×1 iban×1 isbn10×1 unknown×1, sedol repair 19 candidates, scheme count 17, v0.3.x anchors (luhn 79927398714 expected 3, IBAN GB82…5432 formatted) unregressed; --dump-config layer checkdigit at 364 lines) |
2026-10-16 | e17c8d6 |
| dsh-musictheory | Music theory math toolbox: parse any note name into MIDI/octave/pitch class/exact 12-TET frequency with enharmonic spellings (note_info), frequency → nearest note with cents deviation (freq_to_note), correctly spelled chords for 26 qualities (chord_build — G# major is G# B# D#, Cdim7 is C Eb Gb Bbb), correctly spelled scales for 17 types (scale_generate — F# major has E#), interval engine (interval_build — G# + M3 = B#; interval_info — C→F# is an A4, C→Gb a d5, compound intervals), and scale harmonization (scale_harmonize — C major → I ii iii IV V vi vii°, sevenths: true → Imaj7 ii7 iii7 IVmaj7 V7 vi7 viiø7), spelling-aware transposition of 1-16 notes through the letter ladder (transpose — Bb3 G3 D4 up a M2 = C4 A3 E4, G#4 up a M3 = B#4, F#4 down a P4 = C#4; aliases tritone/octave/whole_tone), and chord identification by pitch-class set with inversions, slash notation and omitted-tone voicings (chord_identify — E G C = Cmaj/E first inversion, C E G A = both C6 and Am7/C, C Eb Gb Bbb = all four dim7 rotations, C E Bb D = C9 missing the fifth, a chord written on B# stays on B#) — zero runtime dependencies, pure arithmetic, configurable A4 reference pitch, and scale identification from played notes (scale_identify — C D E F G A B = C major plus A natural minor and the other modes of the same pitch classes; C D E G A = both C major and A minor pentatonic; C# D# E# F# G# A# B# stays C# major, never Db major; A B C D E F G# = A harmonic minor only; when nothing matches exactly it falls back to containing scales with the missing degrees listed, C E G = C major pentatonic missing D A) | dsh plugin --profile web add github:TYEclipse/dsh-musictheory#v0.4.0 |
✅ active | ✅ | ✅ e2e (isolated install v0.4.0 — friction=none, mirror; resolved.installed 0.4.0; wired into profile bundles; 10 tools registered; installed-copy execution: C major set -> C major total=7, C# major spelling preserved (7 sharps), pentatonic pair C/A minor, A harmonic minor unique, contains fallback C major pentatonic missing D/A, chord_identify + transpose regressions intact; 136 tests, coverage 91.86%) | 2026-10-18 | b8c3757 |
| dsh-chem | Chemistry math toolbox: chemical formula parsing with nested parentheses, hydrates (CuSO4·5H2O), ionic charges (Fe3+/SO4^2-, documented disambiguation rule) and IUPAC molar mass with per-element breakdown (formula_mass), mass/mole/particle conversions with Avogadro constant (mass_moles, 6 modes), solution concentration math — molarity, preparation mass, C1V1=C2V2 dilution, percent w/v·v/v·mass (solution), pH/pOH/[H+]/[OH-] + Henderson–Hasselbalch buffer math at 25 °C (ph), equation balancing with exact BigInt rational arithmetic — smallest integer coefficients, charge conservation as an extra constraint when a species is charged, hydrate water included, smallest-sum solution plus unique: false when several independent balances exist, honest "cannot balance" instead of dropping species (balance_equation), and ideal-gas arithmetic with fixed units atm/L/mol/K plus kPa·mmHg·mL·°C conversions — PV=nRT solved for the missing quantity, molar volume (22.413969545014133 L/mol at STP), density ρ=P·M/(R·T) and molar mass from a measured density (gas_law) — zero runtime dependencies, pure arithmetic over the 118-element IUPAC table, anchors from an independent Python oracle (own periodic table, own tokenizer, own Fraction-based balancer) cross-validated against published textbook values |
dsh plugin --profile web add github:TYEclipse/dsh-chem#v0.2.0 |
✅ active | ✅ | ✅ e2e (isolated install #v0.2.0 friction=none, resolved 0.2.0; installed-copy execution 14/14 anchors — propane 1/5/3/4, permanganate/HCl 2/16/2/2/5/8, charge balance 1/5/8/1/5/4, multi-solution 7/5/2/1 + unique=false, impossible N2 case balanced=false, 22.413969545014133 L/mol at STP, CO2 density 1.9634630051413435 g/L, legacy formula_mass H2SO4 98.072 unchanged) |
2026-10-01 | c0b2e7a |
| dsh-probstat | Probability & statistical inference math toolbox: distribution calculator for six distributions — normal, binomial, poisson, exponential, uniform, geometric (pdf/cdf/survival/quantile/stats) (dist_calc), standard-normal z-table math — z ↔ probability/percentile, two-sided p-values, interval probabilities (z_score), confidence intervals — mean with z or Student-t critical values, proportion via Wilson score (confidence_interval), and event-probability identities — union/intersection/conditional/Bayes/complement/at-least-one (event_probability), one-sample hypothesis tests — mean with known sigma, mean with unknown sigma (Student-t, df = n − 1) and a single proportion against p0, reporting the statistic, all three p-values, the tail-specific critical value and the alpha decision, with a warning when the normal approximation is shaky (hypothesis_test), and sample-size planning for a target margin of error — mean closed form, proportion via Wald or the smallest Wilson-consistent n (sample_size) — zero runtime dependencies, pure arithmetic, normal quantile via Acklam (rel. err < 1.15e-9), Student-t cross-checked against published t-table values, anchors from an independent Python oracle (test/oracle/anchors.py) | dsh plugin --profile web add github:TYEclipse/dsh-probstat#v0.2.0 |
✅ active | ✅ | ✅ e2e (isolated install v0.2.0, mirror first try friction=none; installed-copy execution 21/21 anchors — hypothesis_test mean_z 0.8 → two-sided p 0.4237108, mean_t df 11 → p 0.3265839, proportion 40/100 → p 0.0455003 (rejects) + shaky-approximation note; sample_size mean σ=15 E=5 → n 35, proportion Wald → 1068, Wilson → 1064, unreachable target reported) | 2026-10-02 | 9a6635f |
| dsh-linalg | Linear algebra math toolbox: matrix multiplication with dimension checking (matrix_multiply), single-operation matrix math — transpose / determinant / inverse / trace / reduced row echelon form / rank / integer powers (matrix_compute), linear system solver Ax=b with unique / infinite (particular solution + nullspace basis + free-variable count) / no-solution classification (solve_linear), symmetric eigen-decomposition with descending eigenvalues, unit eigenvectors signed so the leading non-zero component is positive and a measured max|A·v − λ·v| residual (matrix_eigen), and vector operations — dot / cross (3D) / norm / projection / angle in degrees (vector_ops) — zero runtime dependencies, pure local arithmetic, Gaussian elimination with partial pivoting, outputs rounded to 10 decimals, singular and inconsistent systems fail cleanly with explicit messages, anchors from an independent exact-arithmetic (fractions) oracle | dsh plugin --profile web add github:TYEclipse/dsh-linalg#v0.2.0 |
✅ active | ✅ | ✅ e2e (installed copy 22/22 anchors: matrix_compute inverse [[4,7],[2,6]] → [[0.6,-0.7],[-0.2,0.4]], rank 3x3 → 2, power Fibonacci^20 → [[10946,6765],[6765,4181]]; vector_ops cross [1,2,3]×[4,5,6] → [-3,6,-3]; solve_linear under-determined → particular (-2,8,0) + nullspace basis (1,-2,1); matrix_eigen [[2,1],[1,2]] → 3, 1 and 4x4 tridiagonal → 3.6180339887 / 2.6180339887 / 1.3819660113 / 0.3819660113; non-symmetric and non-square input fail cleanly; oracle test/oracle/anchors.py = exact-fraction elimination + closed-form spectra cross-checked against an independent Jacobi implementation) | 2026-10-03 | 86cb3f7 |
| dsh-complex | Complex-number math toolbox: parse rectangular/polar strings into the full identity (complex_parse — "3+4i"/"5∠53.13°", modulus, argument rad & deg, conjugate), one-operation arithmetic — add/subtract/multiply/divide/conjugate/reciprocal/integer power via De Moivre plus the general complex power a^b = exp(b·log a) with both operands complex and honest 0^0 / 0^non-positive rejections (i^i, 2^(1+i), (-1)^0.5) (complex_calc), polar ↔ rectangular conversion (complex_convert), principal values of exp/log/sin/cos/tan/sinh/cosh/sqrt plus the six inverses asin/acos/atan/asinh/acosh/atanh with each branch cut reported in the note (complex_functions), complete n-th root sets listed from the principal root (complex_roots, n ≤ 64), and a solver for quadratics with complex coefficients — discriminant, both roots, the Vieta invariants −b/a and c/a, each root's residual, linear degeneration and an honest every-z / no-solution (complex_quadratic) — zero runtime dependencies, closed-form formulas on the principal branch (C99 continuation exactly on the cuts), output rounded at the boundary only, anchors from an in-repo independent Python cmath oracle covering all four branch cuts | dsh plugin --profile web add github:TYEclipse/dsh-complex#v0.2.0 |
✅ active | ✅ zero deps, no network | ✅ e2e (isolated install #v0.2.0 friction=none, resolved 0.2.0; installed-copy execution 27/27 anchors — i^i 0.2078795764, 2^(1+i) 1.5384778027+1.2779225526i, asin(1+i) 0.6662394325+1.0612750619i, branch-cut values asin(2) 1.5707963268+1.3169578969i, acos(2) -1.3169578969i, atan(-2i) 1.5707963268-0.5493061443i, atanh(2) 0.5493061443+1.5707963268i, asinh(2i) 1.3169578969+1.5707963268i, log(-1) iπ, cube roots of -8, z²-2z+2 → 1±i with sum 2 / product 2 / residuals 0, z²+iz+1 → golden-ratio pair 0.6180339887i and -1.6180339887i, linear and degenerate cases; 181 tests, coverage 92.72%) |
2026-10-05 | b43c67c |
| dsh-boolean | Boolean algebra toolbox: parse logic expressions over single-letter variables with symbol, word or unicode operators (truth_table — full table up to 8 variables with per-row results, minterm/maxterm indices, tautology/contradiction/satisfiability flags and canonical DNF+CNF strings; logic_eval — evaluate under one complete trueVars/falseVars assignment, missing variables reported never silently defaulted; logic_equiv — equivalence check over the combined table plus a concrete counterexample when expressions differ; logic_convert — canonical nnf/dnf/cnf plus NAND-only and NOR-only gate networks in NAND()/NOR() call syntax; logic_minimize — Quine–McCluskey minimum sum of products with prime implicants, essential implicants, optional don't-care minterm indices (e.g. a&!b&c | a&!b&!c with dontCare [6,7] collapses to a), deterministic tie-break and an honest exact/unique flag) — zero runtime dependencies, XOR/IMPLIES/IFF desugared at parse time, truth-table and minimization anchors from an independent Python oracle (itertools enumeration + exhaustive set-cover search, no QMC code shared), 144 unit tests / 96.3% lines | dsh plugin --profile web add github:TYEclipse/dsh-boolean#v0.2.0 |
✅ active | ✅ | ✅ e2e (installed copy v0.2.0: 5 tools registered; logic_minimize majority → a & b | a & c | b & c, don't-care case → a, contradiction → empty cover, tautology → 1, node-budget path → exact false + essentials+greedy; truth_table a^b → minterms [1,2]; logic_convert a->b cnf → (!a | b)) | 2026-10-06 | fd847cc |
| MemOS Cloud for DSH | Cloud lifecycle-memory plugin: pre-step recall injection and post-turn memory sync backed by the MemOS Cloud API (memos.memtensor.cn); no tools registered — agent/pre-step + session/event hooks with graceful degradation when no API key is configured; MIT | dsh plugin --profile web add @memtensor/memos-cloud-dsh-plugin@0.1.0 |
✅ | peerDependencies pinned to ^0.1.0-rc.6 || ^0.1.2-rc.1, so dsh 0.2.0-rc.2 rejects the install on both the China mirror and npmjs (exact-version exemption not granted). Previous verification 2026-08-20 (on the 0.1.x runtime): headless turn completed with the plugin mounted and no-credential degradation verified. Needs an upstream release compatible with dsh 0.2.x; failure 1/3 before the row is removed from the table |
2026-10-09 | 0.1.0 | |
| PicGo Upload for DSH | Image & file uploading to the user's configured image host (PicGo Cloud, GitHub, S3, …) via the PicGo engine: picgo_upload tool + /picgo command + bundled picgo-upload skill; prefers the running PicGo desktop app (local server, 127.0.0.1:36677) and falls back to the in-process PicGo library reading ~/.picgo/config.json; MIT |
dsh plugin --profile web add @picgo/dsh-plugin@0.2.0 |
✅ active | ✅ | ✅ e2e (R67 re-verify of the expired row: upstream latest is still 0.2.0 so no re-pin; isolated install friction=none, resolved 0.2.0; structure — dsh.bundle.patch → cordis.patch.yml, lib/, skills/picgo-upload/SKILL.md all present; boot/compose check — the picgo layer mounts in --dump-config (367-line dump); earlier evidence stands: picgo-upload skill surfaced in a headless session, signed-out degradation relays /picgo login with no hang and empty input is rejected) |
2026-10-12 | 0.2.0 |
| WeKnora for DSH | Tencent WeKnora knowledge-base plugin: four tools — list the credential's knowledge bases (weknora_list_knowledge_bases), hybrid vector+keyword retrieval returning passages verbatim with rank/score/chunk metadata plus by-name document matches (weknora_search), reassembled document reading with paging and generated summaries (weknora_read_document), and WeKnora-composed answers with citations (weknora_ask) — env-var configuration (WEKNORA_BASE_URL / WEKNORA_API_KEY / WEKNORA_KNOWLEDGE_BASE_IDS), load-time config validation, tool prefixing for two deployments side by side; zero runtime dependencies, MIT |
dsh plugin --profile web add @wxg-prc-cpg/dsh-weknora@0.1.0 |
✅ active | ✅ | ✅ e2e (isolated install; 4-tool registration verified; list / search / read_document executed against a mock deployment — ranked passages with scores, named-document enrichment, ordered chunk assembly; unreachable deployment errors cleanly and fast; headless mount session 17×23=391) | 2026-10-16 | 0.1.0 |
| dsh-web | DSH Web GUI plugin family (npm aggregate @linxin666/dsh-web-all of 19 family packages + external dsh-better-sidebar): task board with host-side cron execution, mobile/PC remote access via device pairing, SSH panel (terminal / transfer / tunnels), usage stats, model capability profiles, session archive with auto policies, git graph, preset / skin / market / community browsers, pet, i18n — mounted as 20 namespaced web-ui-* rows (counted in a 1330-line composed config at 0.4.6); five opt-in rows (ssh / describe-image / liangshen / skill-explorer / doctor) ship disabled by default; Apache-2.0 |
dsh plugin --profile web add @linxin666/dsh-web-all@0.4.6 | ✅ active | ✅ (anon. daily install heartbeat — code-confirmed at 0.4.6 and documented; package name + version + a localStorage UUID, no conversation data) | ✅ e2e (R72 reverification: stale row 31 d → upstream had moved 0.3.22 → 0.4.6, re-pinned; isolated install 0.4.6 via mirror, resolved 0.4.6, friction = allowBuilds for cloudflared/cpu-features/ssh2 (documented in the upstream 安装排障 section); 20 web-ui-* rows in a 1330-line composed config; boot smoke 401 → 303 + Set-Cookie → 200 with data-dsh-skin=blue-fantasy, skin-center client module served 200 / 268889 B with a matching module id; unverified: live SSH panel, host-side cron run, device pairing, market/community browsers) | 2026-10-17 | 3cd1849 |
| dsh-market | Visual plugin market inside DSH: browse/search the community catalog (2300+ plugins) with category filters and host-aware compatibility hints; one-click install (prefers repo-verified npm packages, then prebuilt GitHub Release tarballs, then source), per-plugin update checks, community themes/skins with live switching, favorites, backup & restore (readable JSON export / WebDAV / private GitHub Gist), hot enable/disable and load-order editing via the profile patch layer, a plugin diagnostics page, and a capability-gated public update API v1 — MIT | dsh plugin --profile web add dshmarket@1.66.37 |
✅ active | ✅ (no telemetry — "never phones home"; documented outbound: catalog + GitHub content routes, gh-proxy/ghfast acceleration fallbacks; comments contact giscus.app/GitHub only when opened; installs restricted to the curated registry; build scripts stay blocked by default; same-origin install endpoint) | ✅ e2e (re-verified 2026-10-18 from 1.47.0 → 1.66.37 — isolated install dshmarket@1.66.37, prebuilt npm, friction=none on mirror, resolved.installed 1.66.37; dsh-market layer in the 369-line composed config; web boot smoke 401 → 303 + Set-Cookie → 200; live /dsh-market/api/v1/capabilities → 200 JSON, marketVersion 1.66.37, schema dsh-market/update-api/v1, features check/update/progress/rollback true, restart false (operator-managed). Not verified: in-page client module — no dsh-market entry in the served /plugins/?? modules bundle under host 0.2.1-rc.2, so the rendered market UI itself was not inspected; client-side install/theme flows untested) |
2026-10-18 | 8470948 |
| dsh-honcho | Honcho memory for DSH — persistent cross-session memory that survives context resets: injects your profile, this project's session summary and Honcho's relevant conclusions at session start, captures every user/assistant turn in the background (debounced, flushed at turn boundaries, before compaction and on shutdown) with best-effort secret redaction, and registers three tools — honcho_search (raw messages plus derived conclusions), honcho_chat (judgement questions over everything Honcho knows) and honcho_remember (durable facts / preferences / decisions); configured through the shared ~/.honcho/config.json contract (workspace, peer name, baseUrl, global kill switch), shared with the sibling claude-honcho / codex-honcho integrations — MIT |
dsh plugin --profile web add @honcho-ai/dsh-honcho |
✅ active | api.honcho.dev by default (self-hostable via baseUrl / HONCHO_BASE_URL); secrets are regex-redacted before upload and the redactor is documented as best-effort, so novel secret formats can pass through; also reads/writes ~/.honcho/config.json and shells out to git for repo metadata; no telemetry or analytics SDKs found |
✅ e2e (isolated install of npm @honcho-ai/dsh-honcho@0.1.0 — prebuilt tarball, 2.1s, no build scripts; honcho layer present in the composed config; plugin loads in a headless dsh-base + dsh-headless profile on host 0.1.5-rc.2 with no apply error despite newer peer pins; no-credential degradation verified — "[honcho] no API key … Memory is off." and the turn still completes; memory round-trip not exercised, it needs a Honcho API key or a self-hosted instance. Use the npm package: a github: install would run its prepare build) |
2026-09-18 | 0.1.0 |
| dsh-ouroboros | Ouroboros (spec-first AI dev workflow engine: Socratic interview → Seed spec → execute → evaluate → evolve) mounted into DSH as native tools by a config-only bundle row that spawns ouroboros mcp serve over stdio — 36 tools registered (ouroboros_interview / ouroboros_pm_interview / ouroboros_generate_seed / ouroboros_execute_seed / ouroboros_auto / ouroboros_evaluate / ouroboros_evolve_step / ouroboros_qa / ouroboros_ralph …) so "ooo interview " or "ooo auto " in chat resolves to the matching tool on its own; ouroboros_auto gets a 30-minute MCP timeout, the execution step defaults to the host model (OUROBOROS_AGENT_RUNTIME=host) with claude-cli / codex / opencode selectable, and failOnStartupError: false keeps DSH booting on machines without uv/Ouroboros — MIT |
dsh plugin --profile web add "github:Q00/ouroboros#main&path:integrations/dsh-plugin" |
✅ active | us.i.posthog.com via the bundled ouroboros-ai Python package): closed command/status dimensions, runtime backend, version, OS and failure-reason codes only — never code, prompts, seed content, file paths or arguments; identity is a random UUID; opt out with DO_NOT_TRACK=1, OUROBOROS_TELEMETRY=0 or telemetry.enabled: false in ~/.ouroboros/config.yaml (contract in the repo's TELEMETRY.md). The row also forwards DEEPSEEK_API_KEY + ANTHROPIC_API_KEY into the spawned child (explicit short allowlist after dsh's credential scrub), executes a third-party PyPI distribution at runtime, and keeps its project state in the working directory it is launched from |
✅ e2e (isolated install of github:Q00/ouroboros#main&path:integrations/dsh-plugin — whole-repo clone ~3m50s, +1 package, no build step; dsh-ouroboros layer with the mcp-ouroboros row present in the composed config; LLM-driven headless turn on host 0.1.5-rc.2 — 36 tools registered from ouroboros-ai 0.54.4 and a real ouroboros_project_status call returned its payload, clean shutdown, rc=0. Needs Python ≥3.12 for uvx, which does not auto-download it: on a 3.11 host the row soft-fails silently and no ouroboros tools appear — remedy uv python install 3.12 (verified here) or UV_PYTHON=3.12. Install follows #main (no tag/npm package available). Full interview → seed → execute → evaluate workflow not exercised) |
2026-09-19 | 0.1.0 (repo main @2026-09-15) |
| ModLens | Vision bridge for text-only models: registers one modlens_read_image tool (name configurable) and auto-discovers every provider route that carries an eligible text-only DeepSeek / GLM / MiMo model, adding a "(modlens vision)" wrapped entry per route so a pasted image is turned into structured JSON evidence at request time — summary, full transcription, reading-order layout regions, entities and relations, and an explicit uncertainty list instead of invented values; the engine is the CLI shipped inside the same package (dist/main.js, spawned from the plugin and version-locked to it), providers / keys / failover / cooldown / reuse grants live in a shared ~/.modlens/config.json, modlens doctor reports local routing and providers offline without spending quota; can reuse existing logins of locally installed agents (Claude Code, Codex, OpenCode, Pi, Kimi CLI) and ships a zero-config start — MIT |
dsh plugin --profile web add @liustack/modlens@3.26.2 |
✅ active | prepublishOnly release hook), but it is a vision bridge by design: the image leaves the machine to whichever third-party provider is selected (Antigravity CLI built-in default, or Gemini API / OpenAI / Anthropic / agent CLIs with user-supplied keys in ~/.modlens/config.json), and it can reuse logins of other locally installed agents — on the verification host modlens doctor printed decisions: claude granted, codex not asked, opencode not asked, pi not asked, grok not asked, i.e. the Claude Code reuse grant is on by default; it spawns the bundled CLI as a child process, recovers pastes as 0600 files in fresh 0700 temp dirs and deletes the throwaway working copy after the read, and redacts keys from errors. Its own docs/security.md is unusually explicit (image content treated as untrusted input, --dangerously-skip-permissions for agy, --allowedTools Read for claude-cli, kimi-cli run only when named) and states plainly that this is exposure reduction, not a sandbox |
✅ e2e (isolated install of npm @liustack/modlens@3.26.2 — prebuilt tarball, 1.9s, no build step and no allowBuilds approval; modlens layer present in the composed config; modlens doctor ran clean and offline on the host — Node v26.8.1 ≥ 22.19, node:sqlite available, guard verdict allow; LLM-driven headless turn on host 0.1.5-rc.2 with a synthetic image fixture — modlens_read_image was registered, invoked with a real image path and the bundled CLI was spawned, exiting 1 with its documented, actionable "no vision provider is set up on this machine" message (install Antigravity CLI or modlens config set gemini-api.apiKey); clean exit, rc=0. The actual vision read was not exercised — this host has no provider configured, so image → evidence was never produced) |
2026-09-20 | 3.26.2 |
| dsh-better-sidebar | Sidebar workbench for the DSH web GUI: registers its tab types through DSH's native right-sidebar API (ctx.sidebarRightTabs / ctx.sidebarRight, dsh-resource://file/… opens) and keeps a bottom workbench — lazy file explorer, CodeMirror editor, inline previews (Markdown with Mermaid and DOMPurify-sanitised README-level HTML, HTML, PDF), multi-tab embedded browser (sandboxed iframe; HTTPS goes to the system browser by default), a real terminal (xterm.js + node-pty, reconnect replay, opt-in terminal_* tools for the model), a git view (real diffs, history, stage/commit/restore — no push/pull/fetch) alongside a per-turn changed-file view, background-task and subagent pages, side chat threads (beta), pinned terminals, session-isolated layout, declarative per-feature settings, and an opt-in sidebar_open tool — the same ctx.betterSidebar service is open to third-party plugins (registerTab / registerFileViewer / registerFileIcon), MIT |
dsh plugin --profile web add dsh-better-sidebar@0.19.1 |
✅ active | sandbox; the address bar rejects javascript:/data:/file: and loopback URLs by default; the sandbox can be switched off per feature in settings, with a warning) — upstream README documents the trust-fence and sandbox model; no telemetry or analytics SDK found and no install-time callbacks, so outbound traffic is limited to URLs the user opens in the embedded browser tab and to the user's own git remotes |
✅ e2e (isolated install v0.19.1 — npm prebuilt, needs the documented pnpm 11 approve-builds step for node-pty; better-sidebar row present in the composed config; web host boot smoke: token fence 401 → 303 → 200, the served client bundle list carries dsh-better-sidebar/client.js, live host route POST /sidebar/api/terminal.deps → 200 {"ok":true}; interactive sidebar pages not browser-driven) |
2026-09-21 | 0.19.1 |
| dsh-TUI | Interactive terminal interface for DeepSeek Harness — pixel-whale header, live work-status line (model, reasoning effort, tokens, TPS, cache-hit rate, git/session info), streaming thinking display, double-Esc time rewind, context progress bar, session management shared with /resume//home//bg (workspace registry persisted to ~/.dsh-tui, pinning, cross-terminal takeover rules), model hot-switching, session fork/compact/export, native subagents, vim input mode and full-screen draft editor, /settings toggles (terminal images, mermaid diagrams rendered to Unicode, whale idle animation), inline image preview via Kitty graphics / Sixel with text fallback, VS Code extension launch mode with editor-selection piping, and a self-updating launcher (dsh-tui / dst) — mounted as a pure plugin bundle patch over dsh-base (18 restated rows, no core patching; uninstall leaves nothing behind); MIT |
dsh plugin --profile web add @deepseek-harness-tui/dsh-tui@0.10.2 |
✅ active | DSH_TELEMETRY_MODE, restated explicitly in its own patch layer), and outbound traffic only happens on explicit user action: the launcher update subcommand / /update queries the npm registry and api.github.com for the latest release and verifies SHA256SUMS before installing a standalone package, and the balance feature calls api.deepseek.com/user/balance with the user's own DEEPSEEK_API_KEY; boot itself makes no call. Local capabilities are documented: /restart spawns a replacement process, it reads/writes ~/.dsh-tui (workspace registry, pins) and $DSH_HOME profile state, and update rewrites only its own launcher file + package.json |
✅ e2e (isolated install v0.10.2 — npm prebuilt, 3.5s, +76 packages, no build-script approval and no local compilation; dsh-tui bundle layer present in the composed config as 18 restated rows; TUI host boot smoke on host 0.1.5-rc.2 — a real PTY launch rendered the first screen, captured markers: whale banner + status line deepseek-flash · Max effort, workspace /tmp, Context loaded · System prompt 18 sections, input box and status footer. Upstream validates against 0.1.5-rc.1, so the UI shows its own warning banner that the engine is one version newer — disclosed, not silent. Interactive paths (session management, image preview, mermaid, /update) not exercised) |
2026-09-22 | 0.10.2 |
| ReMe | Long-term memory for DSH from the ReMe memory kit (Apache-2.0, AgentScope): instead of dumping history into the prompt, the plugin injects long-term-memory guidance at session start (when to consult memory, treat retrieved memory as evidence rather than instructions) and registers one read-only tool — reme_search (query, optional limit 1–50, min_score) returns ReMe's answer, or No relevant memory found., or an explicit ReMe search failed: … instead of an invented answer; completed user/assistant turns are captured per session and submitted to ReMe auto_memory (default every 5 turns plus a shutdown flush; plugin context and tool results are excluded from capture so they cannot be laundered back into memory), and autoDreamEnabled runs a daily auto_dream pass (default 0 23 * * *, workspace timezone) that consolidates journal files into a deduplicated personal knowledge base; mounting is one isolated remeMemory runtime row, and the package also ships a web Status page (connectivity/version, Auto Memory pipeline, consolidation, component health, Journal and personal-KB browsers); every knob is exposed in DSH settings — endpoint, language (en/zh), searchLimit, autoMemory*/autoDream* switches, dreamCron, timezone — and the plugin is a client: it needs a ReMe service (default endpoint http://127.0.0.1:2333, local-first) |
dsh plugin --profile web add @agentscope-ai/reme-dsh-plugin --registry=https://registry.npmjs.org |
✅ active | dist/ is a "website" link button on the status page, not a data endpoint), but capture is on by default: autoMemoryEnabled submits finished conversation turns to the configured ReMe endpoint, which defaults to local http://127.0.0.1:2333 (ReMe's HTTP API has no authentication — upstream warns against exposing it, and pointing endpoint / REME_URL at a remote host means conversation text leaves the machine); only user and assistant text is captured (measured: the auto_memory payload carried exactly those two messages, with no plugin context and no tool results), no local disk writes by the plugin itself (the ReMe service owns the daily/ + digest/ workspace files), and no credentials are read |
✅ e2e (isolated install of npm @agentscope-ai/reme-dsh-plugin@0.1.0 — prebuilt tarball, 3.1s, +1 package, no build step; note the package is not on the China mirror yet: registry.npmmirror.com → 404, so the --registry=https://registry.npmjs.org flag is required, which upstream does not mention; reme-memory group row with isolate: remeMemory present in the composed config; installed-copy LLM-driven execution on host 0.1.5-rc.2 against a local mock ReMe endpoint — session-start guidance present in the session log, reme_search really called (mock received {"query":"verification marker","limit":5,"min_score":0}) and answered from the returned evidence, service-down path returns ReMe search failed: fetch failed without fabricating memory; web boot smoke 401 → 303 → 200 with the plugin's client module served (200, 11.2 MB bundle). Real ReMe service not exercised (mock contract only) and the six status-page tabs were not asserted at UI level) |
2026-09-23 | 0.1.0 |
| dsh-whale-widget | DeepSeek balance pet for the DSH web GUI: a floating whale in the bottom-right corner that keeps an eye on the account balance, today's usage and peak/off-peak pricing, mounted as one bundle row; bubbles are fully configurable (click sequence of text / balance / today / peak-valley / images / weighted random statements), with per-line typography, drag-and-snap plus left-edge flip, custom roles / animations / sounds, per-turn cost readout and a hover quick-edit popover — and 32 built-in provider templates (DeepSeek, Moonshot CN + Intl, OpenRouter, SiliconFlow CN + Intl, StepFun, Novita, Ark, DashScope, Qianfan, GLM, Hunyuan, xAI, OpenAI, Gemini, Groq, Mistral, Together, Fireworks, Cerebras, DeepInfra, ModelScope, OpenCode Zen, custom models) so one widget can show whichever vendor you actually pay; today's usage is estimated from local session events rather than fetched from the cloud; code is MIT | dsh plugin --profile web add dsh-whale-widget@0.3.11 |
✅ active | Bearer only to that vendor's own balance/usage endpoint (32 built-in templates, each called only when configured as the current model; no third-party relay, no usage upload — "today's usage" comes from local session events); local state lives in $DSH_HOME/.dshw-*.json plus $DSH_HOME/whale-{roles,bubble-imgs,audio}/ for custom art and sound, and the source comments state that keys are not written into those files (they go to the host credential store); the code is MIT while the assets/ artwork and audio are not MIT-covered (upstream PROVENANCE.md ships them as-is, no relicense, takedown on claim) |
✅ e2e (isolated install of npm dsh-whale-widget@0.3.11 — China mirror on the first try, prebuilt, no build step and no build-script approval; mirror and upstream tarballs are byte-identical, sha256 92d7d93a…; dsh-whale-widget row present in the composed profile tree; web boot smoke 401 → 303 → 200 with the widget's client asset served (200, 738 KB) and the host routes /dsh-whale/{balance,roles,last-turn,size}.json all returning 200 JSON (401 without the token cookie); degradation is honest — no key → NO_KEY, invalid key → HTTP 401, never an invented balance; note that installing without a version resolves to the previous release for the first ~24h (pnpm 11 publish-age gate), which is why the install command is pinned; real balance values and the browser-level UI interaction were not exercised — the host has no valid provider key and there is no browser assertion harness) |
2026-09-24 | 0.3.11 |
| treg | Tool registry and credential-injecting proxy for agents ("OpenRouter, but for agent tools"): this bundle ships the packaged treg skill plus a token-gated MCP connector row. The skill — a 28 KB SKILL.md published through a ctx.skills provider implemented directly inside the package (plain hand-written ESM, no build step, no @deepseek-ai/* dependency, so a github: install needs no allowBuilds approval) — tells the agent when to reach for the catalog and how to call it by the task at hand, not by vendor: 3,600+ endpoints across 97 providers covering SEO/SERP data, keyword volume, backlinks and site authority, AI visibility, social profiles and trends, people/company enrichment, ad libraries, web data, and image/video/voice generation. The second row mounts @deepseek-ai/dsh-mcp-client against https://treg.to/mcp/ (streamable-http) and registers mcp__treg__catalog_search / catalog_get / call / balance / my_tools — but only when TREG_TOKEN is present at boot: the row carries disabled: !!js (process.env.TREG_TOKEN ?? '') === '', so a tokenless install gets a clean profile with zero always-on 401-ing tools and a skill that walks the human through sign-in instead. Own credentials never leave the server: the registry injects auth upstream-side, treg's own accounts cover subscription-walled providers, and calls are metered per use (new teams get $1 of trial balance). Apache-2.0 |
dsh plugin --profile web add github:superdesigndev/treg#d4f2949 |
✅ active | TREG_TOKEN is set: it then talks to the hosted commercial service treg.to and sends the tool-call arguments and results with Authorization: Bearer $TREG_TOKEN. Worth knowing before installing: with no token the skill steers the agent to the CLI path — curl -fsSL https://treg.to/install.sh | sh then treg login — i.e. an agent-executable remote install script; the plugin itself writes nothing to disk and reads no credential files, TREG_TOKEN comes from the environment only. Upstream documents the row's boot-time gate, the token contract and the deliberate exclusion of treg mcp install in docs/DSH-PLUGIN.md |
✅ e2e (isolated install of github:superdesigndev/treg — China mirror on the first try, friction=none, no build step and no build-script approval; the 90 MB monorepo is not cloned — the package's files whitelist fetches 4 entries (package.json, README.md, LICENSE, dsh/), install in seconds; installed copy 0.21.3, same as the repo root; treg-skill + treg-mcp rows present in the composed profile tree (539 → 551 lines); installed-copy execution — ctx.skills.registerProvider called, list() returns one model-invocable skill treg, get() returns the 28,447-byte SKILL.md with its frontmatter description parsed; web boot smoke on a web-template profile 401 → 303 (+Set-Cookie) → 200, and a fake-token boot stays clean. Pinned to commit d4f2949 because upstream publishes no tags or releases. The real MCP session was not exercised — no valid TREG_TOKEN on the verification host; the row is mounted at boot but the connector connects on demand (no MCP traffic in the boot log), and no paid catalog call was made. Note the dsh install command lives in docs/DSH-PLUGIN.md, not the README) |
2026-09-25 | d4f2949 |
| DSH Intelligent UI | Interactive answers inside DSH Web: the agent answers with real interfaces instead of prose — calculators, charts (line/area/bar/scatter/pie with an accessible raw-data table), tables, forms, checklists, diagrams, simulations and small games — authored as openui fenced blocks, rendered by a client module that reuses the host's models, sessions and tool loop. Local controls (inputs, counters, sliders, tabs, scene playback with click/key/drag rules) update state without model calls, interfaces expand in place and state persists across refreshes; only an explicit submit or button action sends values back to the conversation. Also ships the on-demand /intelligent-ui skill and a dedicated chat preset, so the feature can be turned on per conversation. Standalone plugin — no other UI bundle required. MIT, source included (src/ ships in the tarball) |
dsh plugin --profile web add https://github.com/gulagala001/dsh-intelligent-ui/releases/download/v0.2.0-rc.2.iui.1.0.0/dsh-intelligent-ui-0.2.0-rc.2.iui.1.0.0.tgz |
✅ active | docs/contracts.md); worth knowing: it declares a runtime dependency (zod@4.5.4) and on Windows spawns PowerShell via execFile (src/host/windows-private.mjs) purely to tighten the ACLs of its private state directory — a hardening use, but a subprocess the submission does not mention; the browser may load public HTTPS images; peer requirements are declared optional and the build is host-matched |
✅ e2e (isolated install of the host-matched 0.2.0-rc.2 asset — sha256 8d244c6c… verified against the release SHA256SUMS.txt, install friction=none, resolved 0.2.0-rc.2.iui.1.0.0; structure: non-empty dsh.bundle.patch for both cordis.patch.yml and the preset patch, layer intelligent-ui plus preset-intelligent-chat present in a 1304-line --dump-config, files payload (src/lib/presets/skills) installed with the /intelligent-ui skill's frontmatter intact; web boot smoke: no token 401 → token URL 303 + Set-Cookie → cookie 200 (35,371-byte app page), and the plugin's client module /plugins/??dsh-intelligent-ui/client.js served 200 / 810,741 bytes containing OpenUI/Calculator/Chart/Checklist/Simulation markers, its inject list matching dsh.client.inject item for item; not run: LLM-driven in-browser interaction and refresh-persistence (needs a browser session; this host has no headless bundle to drive it) and macOS/Windows platforms) |
2026-10-13 | 83c9ffe |
Columns: Security = passed preliminary source review (TRACE-lite: trust / reliability / auditability / confidentiality / effectiveness); Trial = verified in an isolated profile with a real end-to-end tool call; Commit = the exact revision that was verified.
- Add the
dsh-plugintopic to your plugin repository - Open an issue in this repository using the Plugin Submission template (plugin name, repo link, release tag, license, install command)
- The pipeline verifies the submission in an isolated profile — security review, install, and one real end-to-end tool call
- Verified plugins are added to the index and the issue is closed; failed submissions stay open with a
needs-fixlabel and a summary reply
- Independent community index (not affiliated with DeepSeek AI)
- Updated automatically on a daily basis
- MIT License
Maintained by the dsh-autopilot pipeline.