cobusgreyling/loop-engineering
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit cobusgreyling/loop-engineering/starters/changelog-drafter/.claude ./rig-loop-engineering # 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 cobusgreyling/loop-engineering/skills/budget-negotiator .claude/skills/budget-negotiator $ npx degit cobusgreyling/loop-engineering/skills/install-loop .claude/skills/install-loop $ npx degit cobusgreyling/loop-engineering/skills/loop-budget .claude/skills/loop-budget $ npx degit cobusgreyling/loop-engineering/skills/loop-constraints .claude/skills/loop-constraints $ npx degit cobusgreyling/loop-engineering/skills/loop-triage .claude/skills/loop-triage $ npx degit cobusgreyling/loop-engineering/skills/loop-verifier .claude/skills/loop-verifier $ npx degit cobusgreyling/loop-engineering/skills/minimal-fix .claude/skills/minimal-fix $ npx degit cobusgreyling/loop-engineering/starters/changelog-drafter-opencode/skills/changelog-scan .claude/skills/changelog-scan $ npx degit cobusgreyling/loop-engineering/starters/changelog-drafter/.claude/skills/draft-release-notes .claude/skills/draft-release-notes $ npx degit cobusgreyling/loop-engineering/starters/ci-sweeper-opencode/skills/ci-triage .claude/skills/ci-triage $ npx degit cobusgreyling/loop-engineering/starters/dependency-sweeper-opencode/skills/dependency-triage .claude/skills/dependency-triage $ npx degit cobusgreyling/loop-engineering/starters/issue-triage-opencode/skills/issue-triage .claude/skills/issue-triage $ npx degit cobusgreyling/loop-engineering/starters/post-merge-cleanup-opencode/skills/post-merge-scan .claude/skills/post-merge-scan $ npx degit cobusgreyling/loop-engineering/starters/pr-babysitter-opencode/skills/pr-review-triage .claude/skills/pr-review-triage
$ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/cobusgreyling/loop-engineering/main/starters/changelog-drafter/.claude/agents/verifier.md $ curl -fsSL --create-dirs -o .claude/agents/loop-verifier.md https://raw.githubusercontent.com/cobusgreyling/loop-engineering/main/starters/ci-sweeper/.claude/agents/loop-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/loop-verifier.md https://raw.githubusercontent.com/cobusgreyling/loop-engineering/main/starters/dependency-sweeper/.claude/agents/loop-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/loop-verifier.md https://raw.githubusercontent.com/cobusgreyling/loop-engineering/main/starters/issue-triage/.claude/agents/loop-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/loop-verifier.md https://raw.githubusercontent.com/cobusgreyling/loop-engineering/main/starters/minimal-loop-claude/.claude/agents/loop-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/loop-verifier.md https://raw.githubusercontent.com/cobusgreyling/loop-engineering/main/starters/post-merge-cleanup/.claude/agents/loop-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/loop-verifier.md https://raw.githubusercontent.com/cobusgreyling/loop-engineering/main/starters/pr-babysitter/.claude/agents/loop-verifier.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 (14)
budget-negotiatorinstall-looploop-budgetloop-constraintsloop-triageloop-verifierminimal-fixchangelog-scandraft-release-notesci-triagedependency-triageissue-triagepost-merge-scanpr-review-triage
Subagents (7)
| verifier | — |
| loop-verifier model: inherit | Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes. |
| loop-verifier model: inherit | Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes. |
| loop-verifier model: inherit | Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes. |
| loop-verifier model: inherit | Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes. |
| loop-verifier model: inherit | Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes. |
| loop-verifier model: inherit | Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes. |
Similar rigs
AdamAkhlaq/claude-code-toolkit
A browsable catalog of Claude Code building blocks — CLAUDE.md, settings, hooks, agents, and doc-writing skills — to copy into your own project and make your own.
Pragmatist 747 tok ·
Remus3/Legion-Wallpaper
Self-auditing AI image restoration pipeline (super-resolution, LaMa inpainting, face repair, metric-plus-vision gate ladder), built by a multi-agent Claude Code system with independent verifiers, git-hook gates and headless background lanes
Automator 5.5k tok ·
leavemagic-cyber/earned-confidence
A behavior contract for AI coding agents — every rule added after a real failure. Ships with a verifier agent that cannot edit what it judges.
Pragmatist 3.6k tok ·
vitaliikapliuk/modelharness
Make every model cheaper or better. Zero-config behavioral harness for Claude Code, with a reproducible 408-run benchmark
Pragmatist 236 tok ·