Which AI agents does this loop work with?

Triage new issues, suggest labels is written for claude-code.

Is this loop safe to run unattended?

This loop is graded C (50/100) by looprepo's automatic safety evaluator (Safety Score v2), which checks for exit conditions, iteration budgets, verification steps, and scoping before publishing.

Loop/loop Code Reviewlow riskbeginnersafety C · 50 GitHub

Triage new issues, suggest labels

Run the issue-triage skill every 2 hours, read current state, suggest labels for new items without auto-applying them, and escalate ambiguous cases.

Prompt

→ Claude Code

/loop 2h Run issue-triage skill. Read issue-triage-state.md first. Produce updated state + suggested labels for new items only. No auto-label or close. Escalate anything ambiguous

claude-code

Source: chenxingqiang ↗graded C · 50/100 — how grades work (Safety Score v2) →

Similar loops

All code review loops →

/goalCode Reviewmedium risknew

Land a change through verified review

Implement a requested change, run documented checks, and surface verification evidence in the transcript until complete or blocked after 20 turns.

prompt

→ Claude Code

/goal The requested change is implemented, reviewed, verified by the project’s documented checks, and Claude has surfaced evidence in the transcript: changed files, commands run, exit codes, risks, rollback notes, and next steps. Stop after 20 turns if blocked or if progress stalls

added 11d agoZulfaqarHafez ↗claude-code

/goalCode Reviewhigh risk

Dual-reviewer convergence gate before opening a PR

Two reviewers from different model families, each in a fresh context, must both pass an objective rubric before a PR is opened — the maker-checker split with real model diversity. Each failed round fixes only what was flagged and re-reviews with reviewers that have no memory of the last round, so nothing anchors on prior findings. Hard cap of three rounds, tests may never be edited to pass, and the loop ends by opening a PR rather than pushing. Adapted from ECC's /santa-loop (affaan-m/ECC, MIT), which auto-pushes on agreement and has no verifiable exit; this version adds the test-exit condition and the human merge gate.

prompt

→ Claude Code

/goal Ship the current diff only after two independent reviewers both PASS. Scope is `git diff --name-only HEAD` (or the path in $ARGUMENTS). First write a rubric with objective PASS/FAIL criteria: correctness, security (no secrets, injection, OWASP top 10), error handling, completeness, internal consistency, no regressions. Each round launch two reviewers in parallel with fresh context and no memory of earlier rounds: Reviewer A is a Claude subagent, Reviewer B is a different model via `codex exec --sandbox read-only` (fall back to a second Claude subagent and say so in the report). Both return a JSON verdict with per-criterion PASS/FAIL and critical issues. If either FAILs: fix only the flagged issues with minimal diffs, never modify the tests to make them pass, commit "fix: address review findings (round N)", run `npm test`, and re-review with fresh reviewers. Exit when both reviewers PASS and `npm test` exits 0 — then open a PR for me to merge; never push to main or merge. Stop after 3 rounds; if still failing, print the unresolved issues and escalate to me instead of shipping.

added Sep 24ECC (affaan-m) — hardened by looprepo ↗codex

/loopCode Reviewhigh risk

The nested perfect loop

A loop wrapping a goal wrapping a review: every 30 minutes, drive all PR review comments to resolved via /review, 10 turns max per pass.

prompt

→ Claude Code

/loop 30m /goal all PR review comments resolved via /review, stop after 10 turns

added Jul 2awesome-agent-loops ↗claude-code