[Extension]: Update Applied Epistemic Engineering catalog entry to v1.5.2 #4998

Extension ID

aee

Extension Name

Applied Epistemic Engineering

Version

1.5.2

Description

Checks the claims in a spec-driven project against their evidence at every stage, and shows plainly what is verified, what is not, and what remains not understood.

Author

ElectroHire

Repository URL

https://github.com/electrohire/spec-kit-aee

Download URL

https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.5.2.zip

License

MIT

Homepage (optional)

https://github.com/electrohire/spec-kit-aee

Documentation URL (optional)

https://github.com/electrohire/spec-kit-aee#readme

Changelog URL (optional)

https://github.com/electrohire/spec-kit-aee/blob/main/CHANGELOG.md

Required Spec Kit Version

=1.0.0,<2

Required Tools (optional)

Python >=3.11; aee >=1.5.0,<2 (PyPI distribution applied-epistemic-engineering); required companion spec-kit-evaluator >=1.0.0,<2. The runner automatically provisions the compatible engine and jsonschema>=4.0, and installs SHA-256-verified evaluator v1.1.2 through Specify CLI. Optional tools: rtk, headroom, token-router, ollama.

Number of Commands

10

Number of Hooks (optional)

5

Tags

epistemics, evidence, provenance, uncertainty, governance

Key Features

• Evidence-centered claim assessment, challenge, provenance, uncertainty, recovery, and tamper-evident history.
• Automatic compatible Python runtime and pinned evaluator v1.1.2 provisioning.
• CLI, standalone agent skill, and Spec Kit operation skills.
• macOS, Windows, Linux support with Python 3.11–3.13 tests and clean installation acceptance.
• AEE records evidence and uncertainty; it does not certify truth or guarantee hallucination-free output.

Testing Checklist

• Extension installs successfully via download URL
• All commands execute without errors
• Documentation is complete and accurate
• No security vulnerabilities identified
• Tested on at least one real project

Submission Requirements

• Valid extension.yml manifest included
• README.md with installation and usage instructions
• LICENSE file included
• GitHub release created with version tag
• All command files exist and are properly formatted
• Extension ID follows naming conventions (lowercase-with-hyphens)

Testing Details

Exact published v1.5.2 public archive accepted on all nine fresh runners (macOS/Windows/Linux × Python 3.11/3.12/3.13), initially installing only Specify CLI. All nine logs confirm automatically provisioned applied-epistemic-engineering 1.5.3, jsonschema 4.26.0, and evaluator 1.1.2. Final gate passed: https://github.com/electrohire/spec-kit-aee/actions/runs/38965452714

Release PR checks (23 passed): electrohire/spec-kit-aee#28 . Covers operation runners, fail-closed behavior, generated-path fuzzing, manifest validation, dependency review, CodeQL, and sandbox acceptance.

Also installed the exact public AEE/evaluator archives in all three actual project workspaces (engine, adapter, evaluator) with Specify 1.2.0, checked installed versions, ran draft assessment and shared composition, and verified source bytes were unchanged. Engine 1.5.3 separately installed and exercised from public PyPI in a fresh environment. These were automated agent/CI checks; no independent human manual-agent testing is claimed.

Example Usage

# In a Spec Kit project, test the immutable public archive:
specify extension add aee --from https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.5.2.zip

# Ask the configured agent:
# Assess this specification with AEE and explain unsupported claims and missing evidence.
# The operation runner provisions required engine/evaluator dependencies automatically.

# With the extension available in an install-allowed trusted catalog:
specify extension add aee

Proposed Catalog Entry

{
  "aee": {
    "name": "Applied Epistemic Engineering",
    "id": "aee",
    "description": "Checks the claims in a spec-driven project against their evidence at every stage, and shows plainly what is verified, what is not, and what remains not understood.",
    "author": "ElectroHire",
    "version": "1.5.2",
    "download_url": "https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.5.2.zip",
    "sha256": "d64db9145754cf7ebb623e4630e5e09f37f59da755456160c38379927e6e9515",
    "repository": "https://github.com/electrohire/spec-kit-aee",
    "homepage": "https://github.com/electrohire/spec-kit-aee",
    "documentation": "https://github.com/electrohire/spec-kit-aee#readme",
    "changelog": "https://github.com/electrohire/spec-kit-aee/blob/main/CHANGELOG.md",
    "license": "MIT",
    "category": "process",
    "effect": "read-write",
    "requires": {
      "speckit_version": ">=1.0.0,<2",
      "tools": [
        {
          "name": "python",
          "version": ">=3.11",
          "required": true
        },
        {
          "name": "aee",
          "version": ">=1.5.0,<2",
          "required": true
        },
        {
          "name": "spec-kit-evaluator",
          "version": ">=1.0.0,<2",
          "required": true
        },
        {
          "name": "rtk",
          "required": false
        },
        {
          "name": "headroom",
          "required": false
        },
        {
          "name": "token-router",
          "required": false
        },
        {
          "name": "ollama",
          "required": false
        }
      ]
    },
    "provides": {
      "commands": 10,
      "hooks": 5
    },
    "tags": [
      "epistemics",
      "evidence",
      "provenance",
      "uncertainty",
      "governance"
    ],
    "verified": false,
    "downloads": 0,
    "stars": 0,
    "created_at": "2026-09-15T00:00:00Z",
    "updated_at": "2026-10-16T00:00:00Z"
  }
}

Additional Context

Update the existing aee community-catalog entry to the released v1.5.2 archive; this supersedes pending v1.5.1 update #4984 / generated PR #4995. No direct catalog PR has been opened. SHA-256: d64db9145754cf7ebb623e4630e5e09f37f59da755456160c38379927e6e9515. Companion evaluator v1.1.2 is submitted separately in #4997.

This release includes packaged standalone skills, documentation/assurance clarifications, security/testing improvements, and the evaluator fix for malformed non-UTF-8 inputs. OpenSSF Best Practices assessments are 97% in progress, not Passing badges; two sustained response-history criteria remain unclaimed. No known dependency vulnerability is currently identified; Scorecard process/history findings are not claimed fixed by this submission.

AI disclosure: Codex (GPT-6) performed autonomous implementation, testing, documentation, release preparation, and this submission under maintainer direction. The maintainer authorized the releases and submission; no independent human code review is claimed. The Spec Kit community catalog remains discovery-only unless an install-allowed trusted catalog is configured; the exact archive installation above is the path actually validated.