feat: brand agent memory as Proof and the runner as Oven

.agents/skills/effort-modeling/CONTEXT-FORMAT.md

@@ -11,4 +11,4 @@ that prevents a common ambiguity.
 ```
 
 Do not put implementation plans, alternatives, or commitments here. Journal
-those in Effort Graph records.
+those in Proof records.

.agents/skills/effort-modeling/SKILL.md

@@ -1,20 +1,20 @@
 ---
 name: effort-modeling
-description: Sharpen a project's vocabulary and planning through one-question-at-a-time grilling, then journal Decisions, Constraints, Findings, Issues, and Risks into the Flatbread Effort Graph. Use when a plan needs durable reasoning instead of ADRs.
+description: Sharpen a project's vocabulary and planning through one-question-at-a-time grilling, then journal Decisions, Constraints, Findings, Issues, and Risks into the Flatbread Proof. Use when a plan needs durable reasoning instead of ADRs.
 disable-model-invocation: true
 ---
 
 # Effort modeling
 
 Use this discipline while a plan or design is being shaped. Store planning
-records in the Effort Graph. Keep project terms in a glossary such as
+records in the Proof. Keep project terms in a glossary such as
 `CONTEXT.md` or `docs/glossary.md`.
 
 ## Resume before asking
 
-From the project root, use the `effort-graph` skill's bounded reads:
+From the project root, use the `proof` skill's bounded reads:
 
-1. `flatbread effort list --status active`
+1. `flatbread proof list --status active`
 2. For the relevant Effort, inspect open Issues and blocking Decisions.
 3. Read a record or digest when a prior conclusion affects the question.
 
@@ -35,8 +35,8 @@ answer, and resolve prerequisite choices before dependent ones.
 
 ## Journal the right speech act
 
-Use `flatbread effort write` for the current Effort, following
-[the Effort Graph reference](../effort-graph/reference.md):
+Use `flatbread proof write` for the current Effort, following
+[the Proof reference](../proof/reference.md):
 
 - **Finding** — evidence about code, users, or runtime behavior.
 - **Issue** — a question, defect, gap, or blocker needing attention.

.agents/skills/grill-with-efforts/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: grill-with-efforts
-description: Run a relentless one-question-at-a-time planning interview that sharpens vocabulary and journals durable reasoning into the Flatbread Effort Graph. Use when a plan is fuzzy and needs an Effort Graph trail instead of ADRs.
+description: Run a relentless one-question-at-a-time planning interview that sharpens vocabulary and journals durable reasoning into the Flatbread Proof. Use when a plan is fuzzy and needs an Proof trail instead of ADRs.
 disable-model-invocation: true
 ---
 

.agents/skills/effort-graph/SKILL.md → .agents/skills/proof/SKILL.md

@@ -1,11 +1,11 @@
 ---
-name: effort-graph
-description: Journal reasoning (decisions, findings, issues, constraints, risks, citations, blobs) into a Flatbread Effort Graph and recall it with bounded reads. Use when starting or resuming a thread of work, recording a decision or finding, resolving an issue, checking what is blocking or still open on an effort, or when the user mentions effort graph, journaling, blocking decisions, agent memory, citation, blob, cites, longform, WriteCitation, or WriteBlob.
+name: proof
+description: Journal reasoning (decisions, findings, issues, constraints, risks, citations, blobs) into a Flatbread Proof and recall it with bounded reads. Use when starting or resuming a thread of work, recording a decision or finding, resolving an issue, checking what is blocking or still open on an effort, or when the user mentions effort graph, journaling, blocking decisions, agent memory, citation, blob, cites, longform, WriteCitation, or WriteBlob.
 ---
 
-# Effort Graph — agent journaling and recall
+# Proof — agent journaling and recall
 
-The Effort Graph stores durable project memory as markdown records in the
+The Proof stores durable project memory as markdown records in the
 repository. It has eight record types: **Effort**, **Issue**, **Finding**,
 **Decision**, **Constraint**, and **Risk** capture the work and reasoning;
 **Citation** stores a source or reference; and **Blob** stores attached
@@ -24,7 +24,7 @@ errors print JSON to stderr and exit 1.
 ## First activation
 
 Read [setup.md](./setup.md), make the reviewed config and gitignore edits, then
-run `flatbread effort bootstrap` followed by `flatbread effort bootstrap --verify`. Bootstrap is report-only and never edits project files.
+run `flatbread proof bootstrap` followed by `flatbread proof bootstrap --verify`. Bootstrap is report-only and never edits project files.
 
 ## Prerequisites
 
@@ -35,26 +35,26 @@ import {
   defineConfig,
   sourceFilesystem,
   transformerMarkdown,
-  effortGraphContent,
+  proofContent,
 } from 'flatbread';
 
 export default defineConfig({
   source: sourceFilesystem(),
   transformer: transformerMarkdown(),
-  content: [...effortGraphContent()],
+  content: [...proofContent()],
 });
 ```
 
 Records live under `<root>/{efforts,issues,findings,decisions,constraints,risks,citations,blobs}/`.
 The write journal is `<root>/.journal/`; read digests cache under
-`.flatbread/effort-graph/read-cache/` (both gitignored).
+`.flatbread/proof/read-cache/` (both gitignored).
 
 ## Writing (journaling)
 
 One command for all 15 mutations — pass the payload as a single JSON argument:
 
 ```bash
-flatbread effort write '{"type":"WriteDecision","effort":"<eff-id>","title":"...","body":"...","derives_from":["<id>"]}'
+flatbread proof write '{"type":"WriteDecision","effort":"<eff-id>","title":"...","body":"...","derives_from":["<id>"]}'
 ```
 
 Response: `{"generation":"<token>","artifacts":[{"id","path","operation"}],"touched":[...]}`.
@@ -79,7 +79,7 @@ Critical semantics:
   `cites: ["<cit-id>"]` when creating an Issue, Finding, Decision,
   Constraint, or Risk. Both the Citation in `cites` and the Blob in
   `Citation.blob` must belong to the same Effort as the record that links to
-  them. Bounded digests omit Blob bodies; use `effort get <blob-id>` to read
+  them. Bounded digests omit Blob bodies; use `proof get <blob-id>` to read
   one.
 - When superseding, open the new record's body with a short rollup of what
   changed and why — reads render ancestors only as one-line checkpoints.
@@ -97,63 +97,63 @@ Read on it, or grep it), `served_generation`, page info, and ≤10 executable
 `hints`. Digests cap at 25 records / one-hop expansion / 50 edges / 64 KiB.
 
 Browse digests (`list`, `records`, `relations`, `blocking-decisions`) excerpt
-each body at 600 chars / 12 lines (`[…truncated]`). **`effort get` digests
+each body at 600 chars / 12 lines (`[…truncated]`). **`proof get` digests
 always include the full record body** (still subject to the 64 KiB digest
 byte cap). Zoom in with `get`, then Read/grep that digest — do not open
-`.flatbread-efforts/**/*.md` for normal full-body recall.
+`.flatbread-proof/**/*.md` for normal full-body recall.
 
 ```bash
 # What's gating this effort? (proposed Decisions deriving from open blocker Issues)
-flatbread effort blocking-decisions <effortId>
+flatbread proof blocking-decisions <effortId>
 
 # Resume: discover active Efforts first
-flatbread effort list --status active
+flatbread proof list --status active
 
 # Scoped listing with filters (AND across flags, OR within comma lists).
 # --status filters Issues and --state filters Decisions, so combining them in
 # one call ANDs across kinds and matches nothing — query each kind separately.
-flatbread effort records <effortId> --kinds issue --status open --since 2026-07-01T00:00:00Z --limit 10
-flatbread effort records <effortId> --kinds decision --state proposed --limit 10
+flatbread proof records <effortId> --kinds issue --status open --since 2026-07-01T00:00:00Z --limit 10
+flatbread proof records <effortId> --kinds decision --state proposed --limit 10
 
 # One-hop neighbors of a record
-flatbread effort relations <effortId> <fromId> --relations derives_from,superseded_by
+flatbread proof relations <effortId> <fromId> --relations derives_from,superseded_by
 
 # Single record with full body; --resolve head follows supersession to the tip
-flatbread effort get <id> [--resolve head]
+flatbread proof get <id> [--resolve head]
 ```
 
 Flags shared by reads: `--strict-min-generation <token>` (with optional
 `--timeout-ms <ms>`, default 3000) and, on `list`/`records`/`relations`, `--limit`
 (≤25) and `--cursor` (opaque `next_cursor` from a prior page; only valid for
 the same query at the same generation).
 
-`effort list` is bounded Effort discovery. It defaults to `active`; valid
+`proof list` is bounded Effort discovery. It defaults to `active`; valid
 statuses are exactly `active`, `paused`, `completed`, and `abandoned`.
 Comma-separated statuses are ORed. Results use the shared `created_at`, then
 `id` ordering. After discovery, use bounded effort-scoped reads.
 
 **Consistency:** reads are eventual by default. Immediately after a write,
 pass the returned generation as `--strict-min-generation` — you get either
-fresh data or an `EFFORT_GRAPH_GENERATION_WAIT_TIMEOUT` error (exit 1),
+fresh data or a `PROOF_GENERATION_WAIT_TIMEOUT` error (exit 1),
 never silently stale results. Do not build polling loops; the wait is
 server-side.
 
 ## Recommended session workflow
 
-1. **Resume / status briefing (bounded fast-path):** `effort list --status active`
+1. **Resume / status briefing (bounded fast-path):** `proof list --status active`
    and trust the returned digest. For each active Effort, run
-   `effort records <effortId> --kinds issue,decision` and read each record's
-   status/state from that one digest. Run `effort blocking-decisions <effortId>`
+   `proof records <effortId> --kinds issue,decision` and read each record's
+   status/state from that one digest. Run `proof blocking-decisions <effortId>`
    only for an Effort whose digest shows an open `blocker` Issue — skip it
-   otherwise. Do not open raw `.flatbread-efforts/**/*.md` for briefing;
+   otherwise. Do not open raw `.flatbread-proof/**/*.md` for briefing;
    browse digests are authoritative for status/state. Budget ≈ (1 + number
    of active Efforts) digest reads. A 12-run experiment across three model
    families showed this roughly halves recall tool calls with no loss of
    answer quality (Decision
    `dec-adopt-a-bounded-status-briefing-fast-path-for-ef--kcw0rw39g3b2ym2h`).
 2. **When a browse digest shows `[…truncated]` and you need the body:** run
-   `flatbread effort get <id>`, then Read/grep that digest (`artifact_path`)
-   for the full body. Reserve opening `.flatbread-efforts/**/*.md` for rare
+   `flatbread proof get <id>`, then Read/grep that digest (`artifact_path`)
+   for the full body. Reserve opening `.flatbread-proof/**/*.md` for rare
    cases (e.g. digest byte-cap miss on an oversized record), not normal
    zoom-in.
 3. **During work:** when outside material supports a record, save large
@@ -165,5 +165,5 @@ server-side.
    they respond to.
 4. **On commitment:** `AcceptDecision` (mind `rejectSiblings`), `ResolveIssue`
    with `resolvedBy` citing the closing Decision/Findings.
-5. Maintenance: `flatbread effort cache prune` deletes digests older than
+5. Maintenance: `flatbread proof cache prune` deletes digests older than
    24h / over the 100 MiB ceiling.

.agents/skills/effort-graph/glossary.md → .agents/skills/proof/glossary.md

@@ -1,6 +1,6 @@
-# Effort Graph glossary
+# Proof glossary
 
-The Effort Graph is persistent, queryable memory for long-horizon software
+The Proof is persistent, queryable memory for long-horizon software
 work. It builds on Flatbread's content vocabulary: each primitive is a
 Collection, its instances are Records, and cross-primitive references are
 Relations in frontmatter.
@@ -63,7 +63,7 @@ have a proposed/accepted lifecycle. They are ordinary Flatbread content:
 filesystem-backed today, with other sources such as S3 or a CDN possible
 later. Records do not cite Blobs directly. Instead, they cite a Citation,
 which may optionally point to a Blob. Bounded digests omit Blob bodies by
-default; use `effort get <blob-id>` to read the content.
+default; use `proof get <blob-id>` to read the content.
 
 ## Edges
 
@@ -74,8 +74,8 @@ writer-materialized reverse projections.
 
 `cites` links an Issue, Finding, Decision, Constraint, or Risk to a Citation.
 It accepts Citation ids only, never Blob ids. A Citation may optionally point
-to a Blob. Both links must stay within the same Effort. `flatbread effort relations` follows `cites` links, but does not follow Blob attachments; use
-`flatbread effort get <blob-id>` to read an attachment.
+to a Blob. Both links must stay within the same Effort. `flatbread proof relations` follows `cites` links, but does not follow Blob attachments; use
+`flatbread proof get <blob-id>` to read an attachment.
 
 New edge vocabulary needs a dogfooded query the existing vocabulary cannot
 express.