Claude Code Canary — Testing skill for Claude Code
Regression testing and version bisecting for Claude Code.
How to install Claude Code Canary
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open SLP-DEV1/claude-code-canary and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Code Canary does
Regression testing and version bisecting for Claude Code. Compare releases, CLAUDE.md configs, hooks and plugins with deterministic scenarios.
Alternatives in Testing
- Marketing Skills Versions — Current versions of all skills 13.8k ★
- Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
- Test Scenarios — Create comprehensive test scenarios from user stories 7.8k ★
README
Claude Code Canary
**Deterministic regression testing and compatibility intelligence for Claude Code.**
Claude Code changes. Your `CLAUDE.md`, hooks, plugins, MCP servers and permission rules change too. Canary gives you a repeatable answer to the question that normally becomes guesswork:
**What broke, and which Claude Code release first broke it?**
Canary runs the same scenario from the same Git commit in disposable worktrees, captures tool/token/reported-cost/duration metrics, checks deterministic assertions, compares releases, bisects regressions and builds full plugin compatibility matrices.
The 30-second demo
Plugin author? Turn your plugin surface into smoke tests, then test every generated scenario across recent Claude Code releases:
claude-canary plugin-init ./my-plugin
claude-canary plugin-suite --plugin ./my-plugin --last 10
You get one report like this:
| Claude Code | load | command-review | skill-api | hook-stop | mcp-github | Overall |
|-------------|:----:|:--------------:|:---------:|:---------:|:----------:|---------|
| 2.1.231 | ✅ | ✅ | ✅ | ✅ |
Related Skills
Dodoguard
Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare
Init Spec Project
Bootstrap a new project with the full spec-driven development workflow — docs/, CLAUDE.md, commands, hooks, an
Quinn
Activates Quinn, QA Engineer. Validates releases, runs regression checks, verifies service wiring, tests API e
Canary Debug Flake
Diagnose a flaky test and propose a deterministic fix from code, CI logs, or a failure description.
Code Quality Skill
Deterministic code quality gate for AI coding agents (Claude Code, Codex, pi): git hooks that block test tampe
Skill Vision Control
Safe MCP Skill version manager - detect updates, A/B testing, smart merge
Related Agents
QA UI
Visual fidelity QA for the Auxi React Native app. Two modes — (1) Maestro mode: authors deterministic YAML flo
Metago Deploy Engineer
Deployment Engineer - specializes in private/cloud/edge deployments, Helm charts, canary releases, and rollbac
Sf DevOps Engineer
DevOps Engineer of the Software Factory cell. Use to build CI/CD pipelines, infrastructure as code, blue-green