Extension ID
aee
Extension Name
Applied Epistemic Engineering
Version
1.2.0
Description
Challenge claims, trace evidence, propagate uncertainty, and route epistemic failures across phases
Author
ElectroHire
Repository URL
https://github.com/electrohire/spec-kit-aee
Download URL
https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.2.0.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
Required Tools (optional)
- python (>=3.11) — required
- aee CLI — the Applied Epistemic Engineering engine (>=1.4.0,<2); 1.4.0 exposes the policy-gate, per-source reliability, and review-queue CLI surface — required
- spec-kit-evaluator (>=1.0.0,<2) — Spec Kit extension implementing the Evaluator Contract; install it first — required
Number of Commands
9 (speckit.aee.assess, speckit.aee.challenge, speckit.aee.trace, speckit.aee.verify, speckit.aee.gate, speckit.aee.gaps, speckit.aee.route-evidence, speckit.aee.report-savings, speckit.aee.review)
Number of Hooks (optional)
5 (after_specify, after_plan, after_tasks, after_implement, after_verify)
Tags
epistemics, evidence, provenance, uncertainty, governance
Key Features
- Challenge claims on atomicity, boundaries, falsifiability, dependencies, and evidence independence
- Assess explicit claims and emit a rich AEE assessment plus an Evaluator Contract result
- Attach policy gates to assessment: per-claim ACCEPT / CHALLENGE / ABSTAIN verdicts with corroboration and forced-abstention rules, and measured per-source reliability blended into scoring
- Diff two assessments into a materiality-filtered review queue (speckit.aee.review)
- Render the claim dependency graph and inspect epistemic provenance
- Verify the tamper-evident AEE ledger without claiming its contents are true
- Apply a CI-friendly decision gate to an AEE assessment
- Generate and update the gap register from a verification matrix and test evidence
- Route oversized evidence through local tools with measured-only token-savings reporting
Testing Checklist
Submission Requirements
Testing Details
Install test: the v1.2.0 archive was installed from the download URL itself into a fresh Spec Kit 1.0.10 project (after the evaluator extension, per the documented order); specify extension list reports aee 1.2.0 enabled with 9 commands and 5 hooks. scripts/check_install.py also passes against a fresh project initialized from the source tree.
Test suite: 48 tests pass in the extension repository, including integration tests that run the assess/challenge/graph/verify/gate/gaps/review operations end-to-end against the real AEE engine 1.4.0 installed from hash-locked requirements, and manifest compliance tests that parse extension.yml with Spec Kit's own manifest parser. The two new integration tests cover the policy verdicts (present with --policy, absent without) and the review queue between two assessments.
What changed in v1.2.0 vs the catalog's v1.0.1: v1.1.0 added the token-economy commands (route-evidence, report-savings); v1.2.0 wires the engine's epistemic-ledger ports into the assess flow — policy gates (corroboration, forced abstention, contested) and per-source reliability from engine 1.1.0–1.3.0, exposed through the engine 1.4.0 CLI — and adds speckit.aee.review. The engine floor rises to >=1.4.0,<2 (from >=1.0.2,<2).
Example Usage
# Install extension
specify extension add aee --from https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.2.0.zip
# Assess the claims in your current spec, with policy gates attached
/speckit.aee.assess policy=true
Proposed Catalog Entry
{
"aee": {
"name": "Applied Epistemic Engineering",
"id": "aee",
"description": "Challenge claims, trace evidence, propagate uncertainty, and route epistemic failures across phases",
"author": "ElectroHire",
"version": "1.2.0",
"download_url": "https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.2.0.zip",
"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",
"requires": {
"speckit_version": ">=1.0.0",
"tools": [
{ "name": "python", "version": ">=3.11", "required": true },
{ "name": "aee", "version": ">=1.4.0,<2", "required": true },
{ "name": "spec-kit-evaluator", "version": ">=1.0.0,<2", "required": true }
]
},
"provides": {
"commands": 9,
"hooks": 5
},
"tags": ["epistemics", "evidence", "provenance", "uncertainty", "governance"],
"verified": false,
"downloads": 0,
"stars": 0
}
}
Additional Context
Note for maintainers: this updates the existing catalog entry for the AEE extension (v1.0.1 → v1.2.0). It is separate from #4626, which requested dependency-metadata corrections for the v1.0.0 entry. The previous update, #4661 (v1.0.1), was merged; this is its successor, not a duplicate.
Extension ID
aee
Extension Name
Applied Epistemic Engineering
Version
1.2.0
Description
Challenge claims, trace evidence, propagate uncertainty, and route epistemic failures across phases
Author
ElectroHire
Repository URL
https://github.com/electrohire/spec-kit-aee
Download URL
https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.2.0.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
Required Tools (optional)
Number of Commands
9 (speckit.aee.assess, speckit.aee.challenge, speckit.aee.trace, speckit.aee.verify, speckit.aee.gate, speckit.aee.gaps, speckit.aee.route-evidence, speckit.aee.report-savings, speckit.aee.review)
Number of Hooks (optional)
5 (after_specify, after_plan, after_tasks, after_implement, after_verify)
Tags
epistemics, evidence, provenance, uncertainty, governance
Key Features
Testing Checklist
Submission Requirements
extension.ymlmanifest includedTesting Details
Install test: the v1.2.0 archive was installed from the download URL itself into a fresh Spec Kit 1.0.10 project (after the evaluator extension, per the documented order);
specify extension listreports aee 1.2.0 enabled with 9 commands and 5 hooks.scripts/check_install.pyalso passes against a fresh project initialized from the source tree.Test suite: 48 tests pass in the extension repository, including integration tests that run the assess/challenge/graph/verify/gate/gaps/review operations end-to-end against the real AEE engine 1.4.0 installed from hash-locked requirements, and manifest compliance tests that parse
extension.ymlwith Spec Kit's own manifest parser. The two new integration tests cover the policy verdicts (present with--policy, absent without) and the review queue between two assessments.What changed in v1.2.0 vs the catalog's v1.0.1: v1.1.0 added the token-economy commands (route-evidence, report-savings); v1.2.0 wires the engine's epistemic-ledger ports into the assess flow — policy gates (corroboration, forced abstention, contested) and per-source reliability from engine 1.1.0–1.3.0, exposed through the engine 1.4.0 CLI — and adds
speckit.aee.review. The engine floor rises to >=1.4.0,<2 (from >=1.0.2,<2).Example Usage
Proposed Catalog Entry
{ "aee": { "name": "Applied Epistemic Engineering", "id": "aee", "description": "Challenge claims, trace evidence, propagate uncertainty, and route epistemic failures across phases", "author": "ElectroHire", "version": "1.2.0", "download_url": "https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.2.0.zip", "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", "requires": { "speckit_version": ">=1.0.0", "tools": [ { "name": "python", "version": ">=3.11", "required": true }, { "name": "aee", "version": ">=1.4.0,<2", "required": true }, { "name": "spec-kit-evaluator", "version": ">=1.0.0,<2", "required": true } ] }, "provides": { "commands": 9, "hooks": 5 }, "tags": ["epistemics", "evidence", "provenance", "uncertainty", "governance"], "verified": false, "downloads": 0, "stars": 0 } }Additional Context
applied-epistemic-engineering==1.4.0.extension.ymlparses to idaee, version1.2.0, 9 command files, 5 hooks.