smileynet/line-cook
Structured AI workflow execution with guardrails. prep→cook→serve→tidy for Claude Code, OpenCode, and Kiro.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit smileynet/line-cook/.claude ./rig-line-cook # 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 smileynet/line-cook/.claude/skills/feedback-broker .claude/skills/feedback-broker $ npx degit smileynet/line-cook/plugins/kiro/skills/line-cook .claude/skills/line-cook
$ curl -fsSL --create-dirs -o .claude/agents/inspector.md https://raw.githubusercontent.com/smileynet/line-cook/main/.claude/agents/inspector.md $ curl -fsSL --create-dirs -o .claude/agents/issue-reviewer.md https://raw.githubusercontent.com/smileynet/line-cook/main/.claude/agents/issue-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/release-editor.md https://raw.githubusercontent.com/smileynet/line-cook/main/.claude/agents/release-editor.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (2)
Subagents (3)
| inspector | Reviews bot-created issue/PR pairs for validity, intent alignment, scope, security risks, code quality, what changed, project value, and root cause depth. Invoked by the inspect-issues command. Read-o |
| issue-reviewer | Reviews standalone GitHub issues for validity, actionability, relevance, priority, and duplicates. Invoked by inspect-issues command. Read-only. |
| release-editor | Interactive release coordinator. Guides the user through readiness checks, changelog review, validation, and release execution. Use when preparing a new version. |
Slash commands (4)
/inspect-issues/release/respond/smoke-test
Similar rigs
matthieurosset/claude-custom-workflow
Multi-agent orchestration workflow template for Claude Code — one lead agent, six specialist subagents, guardrails, hook-driven quality gates, and a self-improving process loop. Battle-tested on a production app, generic and ready to adopt.
Orchestrator 447 tok ·
OdradekAI/bundles-forge
An agentic skills framework & bundle-plugin engineering toolkit that works.
Pragmatist 2.4k tok ·
raiki61/claude-plugins
Two Claude Code loops that keep reviewing and researching until they reach a fixed point: the implementer and the grader are held in separate contexts, and the machine may only ever declare failure, never convergence. Japanese only for now.
Orchestrator 1.2k tok ·
NSEvteev/FullSpec
A spec-driven framework that turns ideas into production code through formal analysis chains, automated testing, and structured delivery.
Orchestrator 6.7k tok ·