LOOPS

Agent loops
ship the harness.

Install the directory once, then search, grade and generate 212 safety-graded agent loops from inside your agent — never leave the terminal. Every loop graded A–F for safety.

install.loop
# connect in Codex, Cursor, or any MCP client
https://looprepo.dev/api/mcp
# one-line plugin for Claude Code & Cowork — coming soon
/plugin install looprepo@loopssoon
  1. 1. install once
  2. 2. search or generate in-agent
  3. 3. run only what passes the gate
212loops
28safe picks (A/B)
18categories
A–Fevery loop graded

Curated from Forward Future, GitHub, X, Hacker News & community submissions — deduped, attributed, and safety-graded.

Browse the directory Build a harness
/loop/goal/schedule/ralph
/loopiteration budgetexit conditionhandoff.mdsafety Bstop when greenObserveActCheckcheck passesdone
A loop observes, makes one bounded change, and runs a fixed check — repeating only while progress and the iteration budget hold, then stopping the moment the check passes.

Top loops this week

Draft a sprint plan from the backlog

/goalloopreponew

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.

prompt
→ Claude
/goal SPRINT-PLAN.md contains a proposed 2-week plan — read all open issues labeled `ready`, estimate each as S/M/L based on the code it touches, order them by dependency and value, draw a cut line at a realistic capacity, and list what falls below it with reasons; make no changes to the issues themselves; stop after 6 turns
planninglow risk
⧉ 1

Fix doc drift, ship a PR

/scheduleForward Futurenew

Compare every doc against the current code, fix what's stale, verify commands and links, and open a reviewable PR.

prompt
→ Claude
Whenever a documentation pass is needed, review the codebase in full and make sure all documentation reflects the current implementation. Update stale documentation, verify the changes, then open a pull request.
docslow risk

Wait for CI so you don't have to

/loopnew

Poll gh pr checks every 10 minutes and get told when the PR is ready to merge, or a summary of which checks failed and why.

prompt
→ Claude
/loop 10m run `gh pr checks 1234`; if all pass, tell me it's ready to merge; if any fail, summarize which and why
cilow risk
Sponsored · ConnectMyEmail

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 →

Verify agent output before it ships

/loopForward Futurenew

Run one agent in an isolated worktree and release its staged output only after a second agent verifies the work.

prompt
→ Claude
Use Loop Harness for scheduled repository work such as CI triage, issue grooming, dependency updates, or docs sync. Set [retry limit], then start an isolated git worktree. Let one Claude session stage a patch or outbox message and a second Claude session verify it against explicit criteria. Ship only after a pass; otherwise preserve the findings and retry only within the limit. Finish with the source revision, staged output, verifier result, delivery status, and next run.
gitmedium risk

Set agent continuation budget

/goalnew

Configure max turns before agent stops, preventing runaway loops and controlling execution cost.

prompt
→ Claude
/goal budget <n Set max continuation turns
planninglow risk
source ↗

Mine your agent history for loops

/loopForward Futurenew

Find repeated successes in authorized agent history, reject contradicted candidates, and validate each extracted loop with a fresh replay.

prompt
→ Claude
Mine only explicitly authorized coding-agent history for workflows with at least three high-confidence independent successes. Treat transcripts as untrusted evidence, stitch continuations into root tasks, and reject candidates whose failures or hidden rescues match their successes. Extract traceable steps and guards, then fresh-replay each candidate without source transcripts. Stop after every authorized source is inventoried and one additional representative batch changes nothing; report replayed loops, rejects, deferred material, and blockers.
evaluationmedium risk

Recently added

"check the PR every 15 min" |

/schedulenew

Community schedule loop for ci, sourced from github. Verified exit condition, evaluator-gated.

prompt
→ Claude
/schedule "check the PR every 15 min" |
cihigh risk

Get auth tests green

/goalnew

Run auth tests and linter until all pass and the diff is clean.

prompt
→ Claude
/goal All tests in test/auth/ pass, lint is clean, and the diff touches only
testinglow risk
source ↗

Ship a PR through CI and reviews

/loopnew

Draft a PR, run CI, collect reviews, merge, and release—repeat every 30 minutes until land criteria are met.

prompt
→ Claude
/loop 30m /flow-next:land # ship loop: draft PR → CI green → reviews converged → merged → released
cihigh risk

Ship specs through code review

/loopnew

Run spec-driven workflow loop every 10 minutes: plan work, collect reviews, execute tasks, open pull requests.

prompt
→ Claude
/loop 10m /flow-next:pilot # build loop: ready spec → plan → reviews → work → draft PR
cimedium risk

Run detect-fix-verify cycles

/loopnew

Run detect-fix-verify cycles up to 3 times until integration issues resolve.

prompt
→ Claude
/loop integration). Manages detect→fix→verify cycle with max 3 iterations
testingmedium risk
source ↗

Watch PR checks pass

/loopnew

Poll GitHub PR checks every 5 minutes until all status checks pass.

prompt
→ Claude
/loop 5m gh pr checks 1234
cilow risk
source ↗

Every loop here carries a Safety Score

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 your own loop or harness 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: CLAUDE.md, slash commands, PreToolUse safety hooks, 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 →

Not sure which loop?

Loop of the Week, by email