The graded index of
agent loops for Claude Code & Codex.
Every entry scored A–F for safety, for Claude Code and Codex. Search, grade, and generate 148 agent loops without leaving your terminal.
https://mcp.looprepo.dev/mcpclaude mcp add --transport http looprepo https://mcp.looprepo.dev/mcp- 1. install once
- 2. search or generate in-agent
- 3. run only what passes the gate
Curated from Forward Future, GitHub, X, Hacker News & community submissions — deduped, attributed, and safety-graded.
Not a developer? Start with Claude Intake →
Turn any Claude workflow into the right loop
Paste a read-only intake prompt into someone's Claude context, capture the evidence, then call looprepo MCP to return ranked real loops, safety checks, and a harness-ready goal for that specific use case.
Recently added
Fix code review blockers until convergence
Run a full review pass inline, apply validated blocking findings at their owning layer, re-run fresh until the gate clears or blockers plateau—capped at 3 rounds with escalation.
Loop operator: watch an autonomous run and escalate on stall
A second, read-only loop that babysits a first one. Every ten minutes it reads the run's state file and latest log, runs the test suite so its evidence is an exit code rather than a self-report, and applies four explicit escalation triggers (no progress across two checks, repeated identical stack trace, budget exceeded, merge-queue conflict). On any trigger it prints ESCALATE and stops so a human looks; it never restarts, edits, merges, or pushes. Exits when the state file reports PASS or DONE, and after twelve checks regardless. Adapted from ECC's loop-operator agent (affaan-m/ECC, MIT), which lists the same triggers but has no cadence, cap, check command, or exit.
Fifteen-minute verification report while you work
A recurring six-phase check (build, types, lint, tests with coverage, secret and debug-log grep, diff size) that prints one fixed-format report every fifteen minutes so you catch drift before the PR, not in review. It is strictly read-only: the loop reports, you decide what to fix. It exits when the tests pass and the report reads READY twice running, escalates instead of retrying when the same check fails three times, and stops after eight checks no matter what. Adapted from ECC's verification-loop skill (affaan-m/ECC, MIT), whose 'continuous mode' names the cadence but has no turn cap, exit, or failure path; all three are added here.
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.
Work a task to completion, then open a PR
The generic persistent-task Ralph pattern: iterate on one named task until its acceptance criteria are met and the suite is green, bounded by a 15-turn cap and a no-progress stop. Anti-reward-hacking clauses keep it from editing tests to go green, and it hands off via a PR instead of merging. Swap the check command for your stack's.
Ship avatar endpoint to spec
Build and test a new /users/:id/avatar route until it passes tests, lint, and matches the OpenAPI schema.
Top loops this week
Execute feature phases autonomously
Run Claude Code through all planned phases of a feature until completion or max iterations.
Draft a sprint plan from the backlog
Turn the open issue backlog into a proposed two-week sprint plan with estimates, a dependency ordering, and an explicit cut line, written as a document for the team to edit.
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.
Loops that read your inbox.
Email is the missing tool in your harness. ConnectMyEmail gives Claude Code and Codex a clean MCP into Gmail, Outlook, iCloud and IMAP — triage, drafts, follow-ups, on a loop.
connectmyemail.com →Hit acceptance criteria
Drive a feature to done against explicit acceptance criteria: a working paginated endpoint, passing tests, clean lint, and a hard turn cap.
Build the user profile page
Ralph autonomously constructs the user profile page and halts on completion promise signal.
Loop operator: watch an autonomous run and escalate on stall
A second, read-only loop that babysits a first one. Every ten minutes it reads the run's state file and latest log, runs the test suite so its evidence is an exit code rather than a self-report, and applies four explicit escalation triggers (no progress across two checks, repeated identical stack trace, budget exceeded, merge-queue conflict). On any trigger it prints ESCALATE and stops so a human looks; it never restarts, edits, merges, or pushes. Exits when the state file reports PASS or DONE, and after twelve checks regardless. Adapted from ECC's loop-operator agent (affaan-m/ECC, MIT), which lists the same triggers but has no cadence, cap, check command, or exit.
Every loop here carries a Safety Score
A library tells you what a loop says. looprepo tells you whether it's safe and likely to work. Each loop in the directory is graded A-F by the same default-fail evaluator that gates submissions: exit conditions, iteration budgets, verification commands, scoping, human gates. Paste any loop — yours or one you found anywhere — and get a full review — review my loop →
The only generator that ships the full harness — free
Anyone can hand you a prompt. The looprepo Builder ships the whole thing, for Claude Code or Codex: CLAUDE.md with PreToolUse safety hooks and slash commands — or AGENTS.md with a sandboxed codex-exec runner — plus a fresh-context evaluator that fails by default, handoff notes, a prd.json, stop conditions and an iteration budget. Safe loops, not runaway agents. Try it →
Loop of the Week, by email
One email a week. One-click unsubscribe, anytime.