Self Test — Testing skill for Claude Code
In-process governance guard self-test — asserts the 3 core guards block crafted payloads, $0 hermetic — /self-test.
How to install Self Test
Installs to ~/.claude/commands/canhada-labs-ceo-orchestration-self-test.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Canhada-Labs/ceo-orchestration/HEAD/.claude/commands/self-test.md -o ~/.claude/commands/canhada-labs-ceo-orchestration-self-test.md Restart Claude Code, or start a new session, for it to be picked up.
What Self Test does
description: In-process governance guard self-test — asserts the 3 core guards block crafted payloads, $0 hermetic — /self-test allowed-tools: Bash, Read
/self-test — Governance guard self-test (PLAN-133 C5)
Drives the three **core governance guard hooks IN-PROCESS** against crafted (synthetic) payloads and asserts each one **BLOCKS**. It NEVER spawns a live subagent and NEVER constructs an Anthropic client, so it is **$0 hermetic** — it exercises only the pure decision functions of
Alternatives in Testing
- Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
- Inkline — by inkline - Structures development workflow using pnpm with emphasis on TypeScript and Vue 3 Composition API 1.4k ★
- GAAI Framework — 95+ Drop-in governance layer (.gaai/ folder) -- backlog authorization, cross-session memory, decision tracking 113 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Red First Review Skill
Review a PR by measuring which of its own guards its own test suite actually catches. Neutralise each guard, r
Test Health Check
Probe whether a test genuinely guards its behavior via targeted fault injection.
MCP Smoke
Post-publish MCP smoke test — installs the published tarball in /tmp, performs MCP initialize + tools/list JSO
Gsd Omc Verify
End-to-end smoke test of the GSD↔OMC adapter. Creates a synthetic 1-wave / 2-plan phase, runs /gsd-omc-execute
Claude Code Hooks Cookbook
Copy-paste Claude Code hooks that actually do something — auto-format, block dangerous commands, test gates, n
Code Quality Skill
Deterministic code quality gate for AI coding agents (Claude Code, Codex, pi): git hooks that block test tampe
Related Agents
Cr Boundary Guard
Guards the project's declared critical dimension — data isolation between tenants/accounts/users, authenticati
Octopus Reviewer
Reviews code against this project's standards — the core/UI split, typing, process safety, test coverage, desi
Adequacy Auditor
Meta adversary - finds where the test suite's own assertions don't bite, via mutation testing. A green suite i