Governance harness for Claude Code & Codex CLI — 57 MCP tools, 45 quality-gate hooks, 64 enterprise skills, HMAC-signed evidence, 2FA infrastructure locks. Vibe prompt in, enterprise quality out.
Skill Claude CodeCodex
Creates mechanical contracts with postconditions, invariants, error cases, and consumer maps. Every postcondition is traceable to a test and a code line. Contracts must exist before any source code edits. Use after enterprise-plan.
Skill Claude CodeCodex
Creates mechanical contracts with postconditions, invariants, error cases, and consumer maps. Every postcondition is traceable to a test and a code line. Contracts must exist before any source code edits. Use after enterprise-plan.
Skill Claude CodeCodex
Use when an enterprise implementation plan exists and work needs a locked contract with postconditions, invariants, consumer mapping, and traceability before build starts.
Skill Claude CodeCodex
Systematic enterprise debugging for bugs, failing tests, and unexpected behavior. Reproduce, trace, scan blast radius, identify root cause, then fix with TDD and prevention records.
Skill Claude CodeCodex
Full enterprise workflow for legacy enterprise-dev invocations. Use when starting a feature, significant refactor, enterprise hardening effort, GitHub issue intake/processing, or multi-stage bugfix that needs end-to-end workflow control, portable repo-local artifacts, and explicit proof scope.
Skill Claude CodeCodex
Use when starting enterprise work in a new repo, new worktree, unfamiliar package, or new computer, or whenever commands, paths, conventions, portability, or project traps are not yet known.
Skill Claude CodeCodex
Use when reviewed enterprise work still needs adversarial probing, mechanical checks, and recycle-loop bug closure before final verification.
Skill Claude CodeCodex
Use when enterprise work has been built and reviewed and needs a final mechanical ship or release gate before merge, PR readiness, install, deploy, or signoff. Checks proof trace, current diff, architecture, post-merge test kit, rollback, observability, security/privacy, and performance regression readiness.
Skill Claude CodeCodex
Use when an enterprise lane needs a read-only next-action recommendation from the current repo profile, traps, and agent session state.
Skill Claude CodeCodex
Use when an approved enterprise design exists and the next step is to turn it into an exact implementation plan with file paths, task boundaries, and verification commands.
Skill Claude CodeCodex
End-to-end PR conversation closer and advisory review harvester for enterprise work. Use this whenever the user mentions unresolved PR conversations, Copilot/GitHub review comments, a PR that cannot merge, skipped/non-blocking Copilot feedback, a failed PR review, or asks to address/resolve/learn from PR feedback. It…
Skill Codex
End-to-end enterprise workflow for turning multiple refactor opportunities into serial green pull requests. Use when the user asks to identify refactor/domain opportunities, create lane plans, run Helpdesk enterprise gates, use specialist subagents, loop code reviews such as /review, CodeRabbit, Copilot, or GitHub…
Skill Claude CodeCodex
Use when enterprise implementation is complete enough for a structured review that separates spec compliance from code quality and classifies drift explicitly.
Skill Claude CodeCodex
Tech stack decision phase for the enterprise pipeline. Auto-detects which technology domains need decisions (runtime, framework, database, auth, etc.), presents options with decision matrices, and locks choices into stack-decisions.json for downstream consumption by enterprise-plan. Incumbent bias for existing…
Skill Claude CodeCodex
Evidence-based verification before any completion claim. No 'should work' or 'probably fine' — paste fresh test output or don't claim done. 7-check verification sequence. Use before committing or claiming work is complete.
Skill Claude CodeCodex
Use when enterprise work is about to be declared complete and the claim needs fresh evidence, postcondition tracing, and an explicit proof-scope verdict.
Skill Claude CodeCodex
Use when starting a feature, significant refactor, enterprise hardening effort, GitHub issue intake/processing, or multi-stage bugfix that needs end-to-end workflow control, portable repo-local artifacts, and explicit proof scope.
Skill Claude CodeCodex
Multi-orchestrator fleet management. Takes a batch of tasks, analyzes dependencies and boundaries, assigns optimal models (Opus/Sonnet/Haiku/Worker), sets up isolated worktrees, and dispatches concurrent orchestrators with merge coordination. Use when the user has multiple tasks to parallelize across agents.
Skill Codex
Plan, implement, or review frontend UI code with clean architecture guardrails and a default single-purpose file architecture. Use for React, TypeScript, UI components, custom hooks, client-side services, API integration views, design-system components, frontend feature setup, frontend refactors, and code review where…
Skill Claude CodeCodex
Lightweight rapid development workflow. Agent Harness with minimal ceremony. No research agents, no review agents, no TDD enforcement. Just analyze, plan, build, verify. Use for small features, config changes, quick fixes that are too big for "just do it" but don't need the full pipeline. Invoked with /full-cycle-fast…
Skill Claude CodeCodex
Research-heavy development workflow. Agent Harness + Compound Engineering deep research. 8+ parallel research agents explore best practices, framework docs, security patterns, and performance before any code is written. Use for unfamiliar territory, new integrations, architectural decisions, or when you want maximum…
Skill Claude CodeCodex
TDD-first development workflow. Agent Harness + Superpowers TDD discipline. Every task starts with a failing test. No code without a test first. Use for bug fixes, features where correctness is critical, or when you want maximum test coverage. Invoked with /full-cycle-tdd followed by a description.
Skill Claude CodeCodex
Complete structured development workflow combining Agent Harness, Superpowers, Compound Engineering, and Agent Teams. Use when starting any new feature, bug fix, refactor, or development task. Invoked with /full-cycle followed by a description of what to build. Interactive planning then fully autonomous execution.…
Skill Codex
Use when turning a diagnose.buildpacket.v1 JSON packet, bug diagnosis, or agent handoff into GitHub issues or issue comments, especially when the user wants ready-for-agent work items created without implementing code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: