curl -fsSL https://api.cheatcodehq.com/install.sh | sh -s -- loop-engineering --to allCopies 14 skills into each app's skills folder (Claude Code: ~/.claude/skills), after checking every file against cobusgreyling/loop-engineering at commit 6d5a94a. Nothing else on your computer changes. To undo it, run the terminal command with --uninstall at the end; that also removes what the app added.
Then start a new session in your AI app and ask for the work in plain words; it picks the skill from its description. In Claude Code you can also type /loop-engineering:budget-negotiator.
See it in use
After installing, start a new session and say: Our open issues are in issues.csv. Triage them: what to look at first, labels for each, likely duplicates and what a person must decide. Don't change anything, write the queue to issue-triage-state.md.
What else it can do, and its limits
- 14 skills for agent loops on a code project: triage of issues, CI failures, open pull requests, dependencies and recent merges
- Release notes: scans merged changes and drafts categorized notes, breaking and security changes flagged first, for a person to review
- Fixes: a minimal fix skill for one well scoped problem and a separate verifier that looks for reasons to reject it
- Guardrails: a constraints file read at the start of every run, a token budget check, and a path denylist for secrets, auth and billing code
- Propose only at the first level: it never labels, closes or merges on its own
- Setting up the loop itself (install-loop) runs a command line tool and needs a terminal; live GitHub or CI data needs a connection or an export
Sample input Recorded Oct 24, 2026 in Claude Code 2.1.308 with Sonnet 5.5. The video replays that session; nothing in it was acted or edited.
What's inside 14 skills
budget-negotiatorAn advanced skill for L3 autonomous loops. When the token budget nears exhaustion, the agent analyzes its ROI and autonomously drafts a negotiation request for a budget increase rather than silently failing.
An advanced skill for L3 autonomous loops. When the token budget nears exhaustion, the agent analyzes its ROI and autonomously drafts a negotiation request for a budget increase rather than silently failing.
changelog-scanScan merged PRs and commits since a given reference, extract titles, labels, types, and signals. Produces structured input for release notes drafting.
Scan merged PRs and commits since a given reference, extract titles, labels, types, and signals. Produces structured input for release notes drafting.
ci-triageClassify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.
Classify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.
dependency-triageScan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.
Scan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.
draft-release-notesTurn changelog-scan output into polished, categorized release notes draft. Propose only.
Turn changelog-scan output into polished, categorized release notes draft. Propose only.
install-loopInstall Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately. Week-one is report-only; never enable auto-merge or unattended fixes unless the human explicitly asks and doctor is healthy.
Install Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately. Week-one is report-only; never enable auto-merge or unattended fixes unless the human explicitly asks and doctor is healthy.
issue-triageScan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.
Scan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.
loop-budgetCheck token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.
Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.
Show all 14 skills
loop-constraintsRead loop-constraints.md at the start of every run and enforce every rule. This skill runs BEFORE triage or any action skill. Constraints are binding.
Read loop-constraints.md at the start of every run and enforce every rule. This skill runs BEFORE triage or any action skill. Constraints are binding.
loop-triageTriage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or Linear board.
Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or Linear board.
loop-verifierIndependent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.
Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.
minimal-fixProduce the smallest possible code change that fixes a specific, well-scoped issue (CI failure, reviewer comment, typo). Use only when the fix target is explicit. Never refactor unrelated code.
Produce the smallest possible code change that fixes a specific, well-scoped issue (CI failure, reviewer comment, typo). Use only when the fix target is explicit. Never refactor unrelated code.
post-merge-scanScan recent merges to main for tech debt, TODOs, debug code, and small cleanup opportunities. Produces a prioritized fix list.
Scan recent merges to main for tech debt, TODOs, debug code, and small cleanup opportunities. Produces a prioritized fix list.
pr-review-triageWatch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
About
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
Something wrong with this listing, or it did not install? Tell us