sunitghub/canon-skills
The agent workflow harness: plans, decisions and acceptance criteria live in your repo, and a second agent grades the work before a sprint closes.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit sunitghub/canon-skills/.claude ./rig-canon-skills # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit sunitghub/canon-skills/skills/ai-audit .claude/skills/ai-audit $ npx degit sunitghub/canon-skills/skills/bulk-read .claude/skills/bulk-read $ npx degit sunitghub/canon-skills/skills/canon-slides .claude/skills/canon-slides $ npx degit sunitghub/canon-skills/skills/capture .claude/skills/capture $ npx degit sunitghub/canon-skills/skills/context-check .claude/skills/context-check $ npx degit sunitghub/canon-skills/skills/context-doctor .claude/skills/context-doctor $ npx degit sunitghub/canon-skills/skills/dead-code-cleanup .claude/skills/dead-code-cleanup $ npx degit sunitghub/canon-skills/skills/doc-audit .claude/skills/doc-audit $ npx degit sunitghub/canon-skills/skills/learnings-sweep .claude/skills/learnings-sweep $ npx degit sunitghub/canon-skills/skills/mikado .claude/skills/mikado $ npx degit sunitghub/canon-skills/skills/mutation-test .claude/skills/mutation-test $ npx degit sunitghub/canon-skills/skills/output-validator .claude/skills/output-validator $ npx degit sunitghub/canon-skills/skills/pr-review .claude/skills/pr-review $ npx degit sunitghub/canon-skills/skills/promote-learnings .claude/skills/promote-learnings $ npx degit sunitghub/canon-skills/skills/repo-audit .claude/skills/repo-audit $ npx degit sunitghub/canon-skills/skills/repo-workflow-audit .claude/skills/repo-workflow-audit $ npx degit sunitghub/canon-skills/skills/sdlc-audit .claude/skills/sdlc-audit $ npx degit sunitghub/canon-skills/skills/skill-eval .claude/skills/skill-eval $ npx degit sunitghub/canon-skills/skills/skill-export .claude/skills/skill-export $ npx degit sunitghub/canon-skills/skills/sprint .claude/skills/sprint $ npx degit sunitghub/canon-skills/skills/wrapup .claude/skills/wrapup
$ curl -fsSL --create-dirs -o .claude/agents/canon-evaluator.md https://raw.githubusercontent.com/sunitghub/canon-skills/main/agents/canon-evaluator.md $ curl -fsSL --create-dirs -o .claude/agents/canon-reviewer.md https://raw.githubusercontent.com/sunitghub/canon-skills/main/agents/canon-reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (21)
ai-auditbulk-readcanon-slidescapturecontext-checkcontext-doctordead-code-cleanupdoc-auditlearnings-sweepmikadomutation-testoutput-validatorpr-reviewpromote-learningsrepo-auditrepo-workflow-auditsdlc-auditskill-evalskill-exportsprintwrapup
Subagents (2)
| canon-evaluator model: claude-sonnet-5 | canon's binding close-gate evaluator. Dispatched by sprint complete (skills/sprint/reference/complete.md step 3) only; not for general use. |
| canon-reviewer model: claude-sonnet-5 | canon's advisory close-gate reviewer. Dispatched by sprint complete (skills/sprint/reference/complete.md step 2) only; not for general use. |
Similar rigs
lee-to/aif-handoff
Autonomous Kanban board where AI agents plan, implement, and review your tasks — fully hands-off.
Pragmatist 4.5k tok ·
workflow/dotfiles
💫 NixOS configuration files
Minimalist 235 tok ·
teabranch/open-responses-server
Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing stateful features. Ollama and Vllm compliant.
Minimalist 1.3k tok ·
onsails/skills
Claude Code skills: codex-sprint, review-loop (iterative simplify-review-fix), rust-dev (FAIL FAST standards)
Minimalist 209 tok ·