Extension ID
aee
Extension Name
Applied Epistemic Engineering
Version
1.0.0
Description
Challenges claims, traces evidence, propagates uncertainty, and routes epistemic failures between Spec Kit phases.
Author
ElectroHire
Repository URL
https://github.com/electrohire/spec-kit-aee
Download URL
https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.0.1.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)
-
aee (applied-epistemic-engineering>=1.0.0,<2) — required
-
Evaluator Contract commands from spec-kit-evaluator>=1.0.0 — required
Number of Commands
5
Number of Hooks (optional)
4
Tags
epistemics, evidence, provenance, uncertainty, governance
Key Features
-
Extracts only explicit, stable-ID claims from Markdown or structured JSON.
-
Challenges atomicity, boundaries, falsifiability, provenance, evidence independence, cycles, and contradictions.
-
Applies published evidence weights and weakest-link dependency propagation.
-
Produces bounded recovery actions with verifiable completion conditions.
-
Emits rich AEE assessments and Evaluator Contract 1.0 results.
-
Maintains an optional tamper-evident SHA-256 JSONL ledger.
Testing Checklist
Submission Requirements
Testing Details
Tested on Windows with Python 3.12 and Spec Kit 1.0.5.dev0. Spec Kit's own ExtensionManifest accepted the manifest with zero warnings. GitHub CI also passed on Python 3.11, 3.12, and 3.13 across Linux, Windows, and macOS, and CodeQL passed.
A clean project installed Evaluator Contract 1.0.0 followed by AEE 1.0.1 from their exact public tagged download URLs, scaffolded configuration, registered all commands and hooks, and listed both extensions as enabled. The public applied-epistemic-engineering==1.0.1 package installed from PyPI in a clean environment and ran aee demo. End-to-end adapter validation produced an AEE assessment, Evaluator Contract result, Mermaid claim graph, valid ledger verification, and successful gate decision, with all generated paths confined to the project root. The runner also has path-escape and symlink-refusal tests.
Example Usage
python -m pip install "applied-epistemic-engineering>=1.0.0,<2"
specify extension add evaluator --from https://github.com/electrohire/spec-kit-evaluator/archive/refs/tags/v1.0.0.zip
specify extension add aee --from https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.0.1.zip
/speckit.aee.assess phase=after_specify artifact=specs/001-search/spec.md
Proposed Catalog Entry
{
"aee": {
"name": "Applied Epistemic Engineering",
"id": "aee",
"description": "Challenges claims, traces evidence, propagates uncertainty, and routes epistemic failures between Spec Kit phases.",
"author": "ElectroHire",
"version": "1.0.1",
"download_url": "https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.0.1.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",
"license": "MIT",
"requires": {
"speckit_version": ">=1.0.0"
},
"provides": {
"commands": 5,
"hooks": 4
},
"tags": ["epistemics", "evidence", "provenance", "uncertainty", "governance"],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-09-04T00:00:00Z",
"updated_at": "2026-09-04T00:00:00Z"
}
}
Additional Context
This is an original ElectroHire implementation. The domain engine is independently packaged at https://github.com/electrohire/applied-epistemic-engineering and documented at https://applied-epistemic-engineering.readthedocs.io/. It deliberately excludes private runtime coupling. AI assistance was used during implementation, testing, documentation, and release preparation; the maintainer reviewed the design and remains responsible for the submission.
Extension ID
aee
Extension Name
Applied Epistemic Engineering
Version
1.0.0
Description
Challenges claims, traces evidence, propagates uncertainty, and routes epistemic failures between Spec Kit phases.
Author
ElectroHire
Repository URL
https://github.com/electrohire/spec-kit-aee
Download URL
https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.0.1.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)
aee(applied-epistemic-engineering>=1.0.0,<2) — requiredEvaluator Contract commands from
spec-kit-evaluator>=1.0.0— requiredNumber of Commands
5
Number of Hooks (optional)
4
Tags
epistemics, evidence, provenance, uncertainty, governance
Key Features
Extracts only explicit, stable-ID claims from Markdown or structured JSON.
Challenges atomicity, boundaries, falsifiability, provenance, evidence independence, cycles, and contradictions.
Applies published evidence weights and weakest-link dependency propagation.
Produces bounded recovery actions with verifiable completion conditions.
Emits rich AEE assessments and Evaluator Contract 1.0 results.
Maintains an optional tamper-evident SHA-256 JSONL ledger.
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.ymlmanifest includedREADME.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
Tested on Windows with Python 3.12 and Spec Kit 1.0.5.dev0. Spec Kit's own
ExtensionManifestaccepted the manifest with zero warnings. GitHub CI also passed on Python 3.11, 3.12, and 3.13 across Linux, Windows, and macOS, and CodeQL passed.A clean project installed Evaluator Contract 1.0.0 followed by AEE 1.0.1 from their exact public tagged download URLs, scaffolded configuration, registered all commands and hooks, and listed both extensions as enabled. The public
applied-epistemic-engineering==1.0.1package installed from PyPI in a clean environment and ranaee demo. End-to-end adapter validation produced an AEE assessment, Evaluator Contract result, Mermaid claim graph, valid ledger verification, and successful gate decision, with all generated paths confined to the project root. The runner also has path-escape and symlink-refusal tests.Example Usage
python -m pip install "applied-epistemic-engineering>=1.0.0,<2" specify extension add evaluator --from https://github.com/electrohire/spec-kit-evaluator/archive/refs/tags/v1.0.0.zip specify extension add aee --from https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.0.1.zip /speckit.aee.assess phase=after_specify artifact=specs/001-search/spec.mdProposed Catalog Entry
{ "aee": { "name": "Applied Epistemic Engineering", "id": "aee", "description": "Challenges claims, traces evidence, propagates uncertainty, and routes epistemic failures between Spec Kit phases.", "author": "ElectroHire", "version": "1.0.1", "download_url": "https://github.com/electrohire/spec-kit-aee/archive/refs/tags/v1.0.1.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", "license": "MIT", "requires": { "speckit_version": ">=1.0.0" }, "provides": { "commands": 5, "hooks": 4 }, "tags": ["epistemics", "evidence", "provenance", "uncertainty", "governance"], "verified": false, "downloads": 0, "stars": 0, "created_at": "2026-09-04T00:00:00Z", "updated_at": "2026-09-04T00:00:00Z" } }Additional Context
This is an original ElectroHire implementation. The domain engine is independently packaged at https://github.com/electrohire/applied-epistemic-engineering and documented at https://applied-epistemic-engineering.readthedocs.io/. It deliberately excludes private runtime coupling. AI assistance was used during implementation, testing, documentation, and release preparation; the maintainer reviewed the design and remains responsible for the submission.