CodaColaLight/nightmill
Claude Code plugin: a lights-out development workflow driven by a GitHub project board. The maintainer sets Ready and Approved; agents write specs and implement stories in parallel worktree slots.
field: unknown workflow: Planning & specsGit & commitsPR / code reviewDocsTesting & TDD runs claude in CI
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 CodaColaLight/nightmill/.claude ./rig-nightmill # 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 CodaColaLight/nightmill/skills/check .claude/skills/check $ npx degit CodaColaLight/nightmill/skills/control .claude/skills/control $ npx degit CodaColaLight/nightmill/skills/fix .claude/skills/fix $ npx degit CodaColaLight/nightmill/skills/init .claude/skills/init $ npx degit CodaColaLight/nightmill/skills/models .claude/skills/models $ npx degit CodaColaLight/nightmill/skills/next .claude/skills/next $ npx degit CodaColaLight/nightmill/skills/spec .claude/skills/spec $ npx degit CodaColaLight/nightmill/skills/status .claude/skills/status $ npx degit CodaColaLight/nightmill/skills/story .claude/skills/story $ npx degit CodaColaLight/nightmill/skills/workflow .claude/skills/workflow
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (10)
Permissions
deny (0)
—
ask (0)
—
allow (9)
Write(docs/specs/**)
Bash(gh project:*)
Bash(gh issue:*)
Bash(gh pr:*)
Bash(gh api:*)
Bash(git status:*)
Bash(git diff:*)
Bash(git log:*)
Bash(bash tests/check.sh)
Similar rigs
warrendeanlangeveldt/context-graph
Gives AI coding agents the why behind your code, and makes them keep it: file cards, rules and decisions in git, delivered before every edit. Claude Code and Codex.
Pragmatist 3.7k tok · · Q0
koyakimu/apd-framework
APD (Autopilot Development): a Claude Code plugin where humans only make the decisions and the AI builds autonomously to completion. Works in your language.
Pragmatist 252 tok · · Q0
arsen-ask-lx/Agent_Quality_Kit
A check that cannot fail looks exactly like a check that passes. AQK plants a known defect into a copy of your most-repaired file, runs your own declared checks against it, and counts a catch only when one names the planted file. Zero depen
Fort Knox 32.1k tok · · Q23
warrendeanlangeveldt/code-kit
Keeps AI coding agents inside your project's rules: lanes, layer rules, protected paths and proof before finish, enforced by Claude Code hooks and in CI
Skill Collector 3.3k tok · · Q0