/loop cadence: weekly. Using the Zendesk MCP (read), pull tickets expressing a mismatch between expectation and reality ('I thought it...', 'the site said...'). Append (ticket theme, misread feature, suspected source page) to state-file expectation-gaps.md. Each round, trace the single most common gap back to the exact page sentence and draft a clarifying rewrite — draft only, edit nothing live. Stop after one; log errors and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
/loop cadence: every [N] days. Using the Meta Marketing API (read), watch frequency, CTR decay, and CPA drift on active creatives. Append fatigue signals to state-file ad-fatigue.md. When a creative crosses [THRESHOLD], draft the next creative variant batch (hooks, angles, copy) — draft only, launch nothing, touch no budget. Stop after drafting one batch; log API errors and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
/loop cadence: daily (morning). Using twitterapi.io to read my curated X list [LIST ID] and Typefully to hold drafts, rank the last 24h of posts by engagement-per-follower. Append top themes to state-file x-ideas.md. Each round, draft ONE post in MY voice [VOICE NOTES] on the strongest theme as a Typefully draft — never publish. Stop after one draft; log API errors and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
/loop cadence: weekly. Using the Search Console MCP, mine my own impressions/clicks for queries with demand but weak coverage. Append candidate topics (query, intent, current page, gap) to state-file brief-backlog.md. Each round, expand the single highest-opportunity topic into ONE fully-specified brief (angle, outline, target terms, internal links). Draft only. Stop after one brief; log GSC errors and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
/loop cadence: weekly. Using DataForSEO MCP for keyword/SERP data and a Firecrawl monitor on competitor blogs [LIST], detect new competitor articles and the terms they target. Append (competitor, URL, target terms, gap vs our coverage) to state-file competitor-content.md. Each round, draft ONE counter-move brief against the largest open gap. Read + draft only; publish nothing. Stop after one brief; log source errors and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
Every week, ask the AI engines the same 'best [category]' questions your buyers ask, log where your brand ranks, and track the trend over time instead of guessing.
/loop cadence: weekly. Using the Perplexity API, run my fixed list of 'best [category]' / buyer-intent queries [PASTE QUERIES]. Append each result (query, my rank/mention, competitors named, date) to state-file share-of-model.md as a time series. Each round, draft ONE action for the query where I dropped the most. Never message anyone or change any page. Stop after logging the week; if a query errors, log the failure and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
/loop cadence: weekly. Using the Search Console MCP, pull my programmatic/template page set and check each for thin content, near-duplicate bodies, and impressions-without-clicks. Append flags (URL, issue, evidence) to state-file pseo-quality.md. Each round, draft a fix or consolidation recommendation for the WORST page only — recommend, never edit or deindex. Stop after one recommendation; log GSC errors and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
/loop cadence: weekly. Using the Exa MCP, search for buyer-intent questions in [MY CATEGORY] that AI answer engines field but my site [DOMAIN] does not rank for or answer. Append findings (question, current answer source, whether we cover it) to state-file answer-engine-gaps.md. Each round, draft ONE page/section outline to close the single biggest gap — draft only, publish nothing. Stop after drafting one gap; if Exa errors, log it and stop. Budget: cap $[X]/run. Hard cap: stop after 1 iteration per run.
Split a large mechanical job into 2–5 independent Codex lanes, each isolated in its own worktree with a frozen acceptance bar and binding judge, then block the final merge behind a full integration judge.
Dispatch a parallel Codex legion for a large mechanical job. Split the work into 2–5 genuinely independent lanes, one lane per piece.
First announce a muster table with:
- each lane,
- the exact files that lane may touch,
- the frozen acceptance check for that lane.
Do not proceed until I approve the split.
Before dispatch, the orchestrator must freeze and record each lane’s acceptance bar. After dispatch, each worker treats `.git` as read-only.
Each lane must run in its own git worktree with:
- a frozen acceptance bar recorded before code changes,
- a strictly disjoint may-touch manifest,
- its own sandbox,
- read-only `.git` state for the worker.
If any lane’s file footprint overlaps another lane, refuse the split and serialize the work instead.
When a lane finishes, run a fresh-context judge against that lane’s frozen bar. The judge must return binding PASS or FAIL. Allow at most 2 retries per lane; stop after 2 failed attempts, then escalate loudly.
Merge lanes in a fixed order. After merging, require a mandatory integration judge that reruns the full test suite across the combined result. Do not commit or merge unless the integration judge returns PASS.
Hard cap: 5 workers. If there are more than 5 pieces, run later waves. Never merge without the integration judge.
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.
praetor is a Claude Code plugin that runs a plan → freeze acceptance bar → dispatch → independent fresh-context judge → resolve loop. Claude plans and judges, Codex executes; a FAIL from the judge cannot be overridden, with at most 2 retries before a loud takeover.
Plan the task and freeze the acceptance criteria in .codex/ACCEPTANCE.md before any work begins. Isolate on a throwaway branch, write a self-contained brief, then dispatch execution to Codex. When Codex finishes, spawn a fresh-context independent judge that runs every check in the frozen bar against the uncommitted working tree and returns a binding PASS or FAIL — a FAIL cannot be overridden. The judge never fixes anything and commits nothing; it touches manifest paths only. Resolve with at most 2 retries; on continued failure, hand back with a loud takeover. Commit only after the judge passes, then clean up and write the ledger. Iron laws: frozen bar before dispatch, binding judge, max 2 retries then loud takeover.
# Ralph  Ralph is a minimal, file‑based agent loop for autonomous coding. Each iteration starts fresh, reads the same on‑disk state, and commits work for one story at a time. ## How it works Ralph treats files and git as memory, not the model context: - PRD (JSON) defines stories, gates, and status - Loop executes one story per iteration - State persists in .ralph/  ## Global CLI (recommended) Install and run Ralph from anywhere: bash npm i -g @iannuttall/ralph ralph prd # launches an interactive prompt ralph build 1 # one Ralph run ### Template hierarchy Ralph will look for templates in this order: 1. .agents/ralph/ in the current project (if present) 2. Bundled defaults shipped with this repo State and logs always go to .ralph/ in the project. ### Install templates into a project (optional overrides) bash ralph install This creates .agents/ralph/ in the current repo so you can customize prompts and loop behavior. During install, you’ll be asked if you want to add the required skills. ### Install required skills (optional) bash ralph install --skills You’ll be prom Cap the run at 25 iterations; leave remaining work for the next session.
# CLAUDE.md — Project Constitution Claude Code reads this file automatically at the start of every run. In a Ralph loop each iteration is a FRESH context, so this file is the only memory that survives. Treat every rule here as non-negotiable. ## What we are building An audit-grade verification gate : an inline API an AI agent calls before it commits a high-stakes output. It returns a verdict AND a signed, tamper- evident audit receipt that a compliance officer can hand to a regulator. The receipt — not the detection — is the product. Full spec: specs/verification-gate.md . ## The Ten Golden Rules (violating any is a failed iteration) 1. One task per loop. Read fix plan.md , pick the single highest-priority unchecked [ ] item, do ONLY that. Do not batch. 2. Tests are law. Never mark a task done unless the full test suite is green. Run it; do not assume. 3. Never weaken a test to pass it. Deleting, skipping, or loosening an assertion to get green is a critical failure. If a test is genuinely wrong, record why in the progress log and stop. 4. Small diffs. If your change touches more than ~3 files or ~150 lines, you have taken too much Cap the run at 25 iterations; leave remaining work for the next session.
/ralph-loop "Read the brief at /redesign/briefs/clients-brief.md. Compare the current implementation to the brief's requirements (every section of the brief, including Recipe Context and Implementation Notes). Apply one focused improvement. Re-check against the brief. If all brief requirements are met, output <promise PAGE-POLISH-COMPLETE</promise ." --max-iterations 8 --completion-promise "PAGE-POLISH-COMPLETE
/goal Implement the work described in PLAN.md. Stop only when npm run lint and npm run test:e2e pass. Follow AGENTS.md, keep changes scoped, and report verification evidence Stop after 25 turns even if the goal is not reached.
/goal "Execute all phases of <run-root /ROADMAP.md sequentially. Read <run-root /phases/phase-N.md for each phase; do the work; run mandatory commands; print SUPERGOAL PHASE VERIFY then SUPERGOAL PHASE DONE for each phase; follow the failure-recovery protocol in <run-root /PROTOCOL.md if any criterion fails. After the last phase, run the FINAL AUDIT in <run-root /PROTOCOL.md (re-verify against <run-root /ROADMAP.md; re-run aggregated mandatory commands; spot-check criteria; on gaps, write <run-root /phases/audit-fix-<round .md and execute inline). Only after AUDIT COMPLETE, print SUPERGOAL RUN COMPLETE. Done when SUPERGOAL RUN COMPLETE appears in the transcript with one SUPERGOAL PHASE DONE per phase, AUDIT COMPLETE printed before SUPERGOAL RUN COMPLETE, and no FAILURE HANDOFF or AUDIT HANDOFF this run
/goal Complete GOALS.md phases 1-13 in order. For each phase, implement the deliverables, add/update tests, run the common validation plus that phase's Automated QA, commit after the phase passes, and push after stable milestones. Preserve unrelated user changes. Stop only if blocked by missing credentials, external service access, or an explicit product decision that cannot be safely inferred Cap the run at 20 turns.
/goal ./scripts/verify.sh exits 0, .ai/spec-tdd/state.json phase is done, frozen tests and acceptance gates are unchanged, no tests are skipped/weakened, and no TODO/stub/hardcoded test-only implementation remains; or stop after 20 turns with a clear blocked report
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.
/loop 20m Continue autoresearch. Read research-state.yaml and findings.md. Re-read the autoresearch SKILL.md occasionally to stay aligned. Step back and reflect holistically — is the research making real progress? Are you deepening understanding or just running experiments? If stalling, pivot or search literature for new ideas. Keep making research progress — never idle, never stop. Update findings.md, research-log.md, and research-state.yaml when there's new progress. Git commit periodically and clean up the repo if needed. Show the human your research progress with key plots and findings by preparing a report in to human/ and opening the HTML/PDF. Only when you believe the research is truly complete, invoke the ml-paper-writing skill to write the paper
Guardrails: Stop when the goal is verifiably met, or stop after 15 iterations, whichever comes first. Verify each pass by running the relevant tests or checks — self-reported success does not count.
Framework-agnostic (Claude Code, Codex, OpenClaw, or any LLM agent), markdown-only skill bundle (79+ skills) for running ML research unattended overnight: literature search, idea generation, experiment execution, and cross-model paper review, with a silent-death watchdog and a stall/pivot mechanism so a stuck loop changes approach instead of looping forever on minor variants.
Install the ARIS markdown-only skills, then run the overnight research loop: the agent reviews relevant literature, proposes and critiques experiment ideas, runs GPU experiments, updates a persistent Research Wiki, and has a second model cross-review the draft paper each round. A watchdog checks the state file's modification time and flags the run STALE/MISSING/COMPLETED if it goes silent. An iteration log counts new findings per round; at 2 consecutive stale rounds it forces a structural pivot (reframe and try a new direction), and at 4 it escalates to a human instead of continuing to retry near-identical variants. Cap the run at 25 iterations; leave remaining work for the next session.
Runs Claude Code/Codex as an autonomous multi-role dev team — planner → reviewer ↔ fixer → worker — across all of a user's GitHub repos, entirely driven by issue labels. Each loop runs in its own git worktree so multiple repos/issues proceed in parallel without collisions.
Register a repo with looper, then label an issue `looper:plan` and assign it to yourself. The planner reads the issue, explores the repo, drafts a spec, critiques and revises it, and opens a spec PR labeled `looper:spec-reviewing`. A reviewer re-reads the PR on every commit and posts inline review threads; a fixer pulls those threads, addresses them in its own worktree, and pushes, ping-ponging with the reviewer until every thread is resolved. Once labeled `looper:spec-ready`, a worker implements the spec, runs checks, and iterates on its own output until checks pass and the PR is ready for human review and merge. Every phase transition is gated on a GitHub label via `looperd`, so a human can pause or take over at any boundary.
A graduated path to unattended Ralph runs: start with a single bounded task, add a PROMPT.md spec file, add verification, and only then remove the human from the loop for overnight builds.
Staged path from basic prompt → PROMPT.md spec → overnight Ralph run: start with a single bounded task, add a spec file, add verification, only then remove the human from the loop. Cap the run at 25 iterations; leave remaining work for the next session.
A cost-safety pattern that pairs every overnight loop with a second, dumber loop whose only job is stopping the first: spend alerts, a hard iteration cap, and a cron check that kills the worker when token burn spikes or the same command keeps repeating.
Pair every overnight loop with a watchdog: spend/usage alert thresholds, a hard `MAX_ITER`, and a cron check that kills the loop process if tokens-per-minute spikes or the same command repeats N times. The watchdog is a second, dumber loop whose only job is stopping the first one. Cap the run at 25 iterations; leave remaining work for the next session.
First-party Cursor guidance for the iterate-until-green loop, with the key anti-reward-hacking clause: the agent may never modify the tests it is trying to satisfy. Works in Cursor, Claude Code /goal, and Codex.
"Write code that makes these tests pass. Do NOT modify the tests. Keep iterating — run the suite, fix failures, run again — until all tests pass." (paraphrase of Cursor's official agent best-practices guidance)
/goal all database migrations apply cleanly — run them, fix schema or SQL errors, repeat until `npx prisma migrate status` is clean; stop after 6 turns
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.