Governance plugins

Cedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin — decisions are policy-gated before they run and every decision produces a tamper-evident receipt verifiable offline.

1 skill · 2 commands · 2 agents · hooks

Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI configuration. Joins protect-mcp and signed-audit-trails in the governance category; composes with protect-mcp for runtime enforcement.

1 skill · 2 commands · 1 agent · hooks

Teaching skill: cookbook-style walkthrough for signed audit trails on every Claude Code tool call. Cedar policy, Ed25519 receipts, offline verification, CI/CD integration, SLSA composition. Pairs with the protect-mcp runtime plugin.

1 skill

Recursive governance for Executable Operating Units (EOUs). Faceted classification, generating-EOU constraints, ECP-governed change, no-self-approval. v0.7.0: Stage 0 (reference-grounded captured_workflow + per-app domain_values constitutional layer + Rule 96). v0.8.0: agentic judgment (judgment_authorized flag, value_invocations trace, F14–F17 taxonomy, judgment_maturity J0–J4 axis, $audit-judgment skill, Rule 97, counterfactual-swap audit).

14 skills · 1 command

Builds an evidence pack for an Apache Incubator podling against the 38 items of the Apache Project Maturity Model, marking each evidenced, proxy or human. Never a score or verdict.

1 skill

Compares the ipmc MCP's graduation-readiness verdict with what an Apache Incubator podling says in its own reports, checked against the mail archives.

1 skill

Assembles an Apache Incubator podling's graduation case and drafts the DISCUSS email and the board resolution.

1 skill

DPF-native agent plugin for contributor sessions and in-portal coworker seed source.

88 skills · hooks

DSG Spacetime production MCP client: governed plan, discover, owner approval, execute, verify evidence. Uses the existing https://aws.dsg.pics/mcp backend; does not deploy another control plane.

3 skills · 1 MCP server

Enforces the repo truth boundary and claim policy. Helps classify statements as verified fact / inference / pending / blocked / not verified, and warns about forbidden readiness claims. Ships an advisory PostToolUse hook.

1 skill · hooks

外部システム(Notion / GitHub / Slack など)との統合アダプタスクリプト群。skill-governance-config のアダプタレジストリと連動する。

2 skills · hooks

ガバナンスポリシー・rubric レジストリ・アダプタ登録・テンプレート変数など、governance 基盤の設定ファイル群を管理するプラグイン。

2 skills

Skill / Agent / Hook / manifest の静的解析スクリプト群。命名・依存方向・rubric 参照・frontmatter 整合などを自動検証する lint プラグイン。

2 skills

Життєвий цикл навичок: створення, версії, аудит екосистеми, гейти безпеки та валідації перед видачею. (7 скілів)

AI governance toolkit — DLP scanning, data guardrails, risk register, compliance evidence, audit trail, and EU AI Act classification embedded in your workflow.

12 skills

Cedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin — decisions are policy-gated before they run and every decision produces a tamper-evident receipt verifiable offline.

1 skill · 2 commands · 2 agents · hooks

Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI configuration. Joins protect-mcp and signed-audit-trails in the governance category; composes with protect-mcp for runtime enforcement.

1 skill · 2 commands · 1 agent · hooks

Teaching skill: cookbook-style walkthrough for signed audit trails on every Claude Code tool call. Cedar policy, Ed25519 receipts, offline verification, CI/CD integration, SLSA composition. Pairs with the protect-mcp runtime plugin.

1 skill

Repo governance hooks: constitution gates, catalog guards, and CI drift checks for the profile itself.

Operator standards and decision records (curated-standards.txt): routing, testing, security, workflow.

Shared schema contracts (typed-result-schema.md) kept at the repo root for cross-harness reuse.

Audit trail, confidence tagging, and ethical checks on every AI decision. Primary framework: Prospect Theory (Kahneman & Tversky, 1979). MOAT-01.

1 skill

Ten drift classes scanned continuously. Catches regressions before they ship. Primary framework: Signal Detection Theory (Green & Swets, 1966). MOAT-03.

1 skill

Decision memory for Claude Code. Automatically tracks architectural decisions, code changes, and engineering choices into TraceMem's governed audit trail.

2 skills · 9 commands · 2 agents

Work on the Humanities-AI Rights Constitution from your own agent.

1 skill · 4 commands · 3 agents · 1 MCP server

An operating constitution for AI coding agents. Supreme layer: the Ten Base Laws — invariant-grounded, precedence-ordered, model-agnostic. Below it: dispatch discipline, never-self-verify acceptance, escalation ladders, judgment rubrics, and a perishable bindings layer.

3 skills · 4 commands · 2 agents

Portable governance skills with runnable MSDMD block-only helpers and drift gates, plus a native-first metadata ingestion contract whose native readers remain implementation work. Block syntax supplements metadata already expressed by code, manifests, schemas, documentation, ownership rules, and tooling; unsupported inputs stay visible as hmmm.

47 skills

openIndu org-wide Agent behavior principles (11), 20 maintainer agents, organization Issue intake, tiered SDLC workflows, and a main-branch protection hook

23 skills · 20 agents · hooks

バランス — deliberate before executing, verify after. Governance skills covering the full development lifecycle.

24 skills · 7 agents

Recursive governance for Executable Operating Units (EOUs). Faceted classification, generating-EOU constraints, ECP-governed change, no-self-approval. v0.7.0: Stage 0 (captured_workflow + domain_values constitutional layer + Rule 96). v0.8.0: agentic judgment (judgment_authorized flag, value_invocations trace, F14–F17 taxonomy, $audit-judgment skill, Rule 97, counterfactual-swap audit).

14 skills · 1 command