Start with no account or saved state, fix one confirmed onboarding obstacle, and retry the whole experience.
Act like a first-time user of [product]. Start at the real entry point in a clean session with no saved login, site data, remembered route, or hidden setup. Complete onboarding using only visible guidance and record obstacles. Fix the worst one with the smallest change that preserves every security, access, and product requirement. Discard the session and retry. Stop after one uninterrupted success, no safe fix, blocked access, or required approval. Return the path, changes, evidence, and blockers.
Remove one unused or redundant style at a time and keep it gone only when every tested screen looks identical.
Reduce the CSS styling code [site] sends to users without changing tested screens. First capture representative pages, sizes, themes, and interactions, and record the built CSS size. Treat coverage reports only as suggestions. Remove one declaration or rule, rebuild, and rerun screenshots and project checks. Keep it only if every screenshot is pixel-identical and built CSS is smaller; otherwise revert. Stop when no supported candidate remains, progress stalls, or approval is required. Return reduction, evidence, and untested states.
Reduce the data downloaded before the first screen appears, with tests and screenshots guarding behavior and appearance.
Reduce the data [web app] downloads before its first screen appears. First record passing tests, mobile and desktop screenshots, and compressed transferred bytes—the data actually downloaded. Use the build report only to suggest candidates. Defer, compress, or remove one item, then rebuild and rerun every check. Keep it only if tests pass, screenshots are pixel-identical, and bytes decrease; otherwise revert. Stop when no safe candidate remains, progress stalls, or approval is needed. Return measurements, changes, and untested states.
Complete a real user task, score each meaningful screen with one checklist, fix the weak spots, and retest end to end.
Improve [user flow, such as signup] at [URL] until [completion criterion]. In a real browser, start each pass from fresh state—no saved login, cookies, or site data. Capture meaningful screens at the agreed sizes and modes, score them with one checklist, and improve the weakest safe area. Rerun the whole flow and keep only regression-free changes. Stop on success, two full passes with no gain, blocked access, or required approval. Return scores, screenshots, changes, and stop reason.
Interview the user, capture what to build in SPEC.md, and how the agent should execute and verify it in GOAL.md.
Turn [rough coding idea] into two planning files before Codex starts /goal, its long-running task mode. Interview the user, then write SPEC.md: what to build, exclude, and consider, plus measurable done_when completion checks. Write GOAL.md: the work plan, progress scorecard, quick and final checks, memory files, evidence, and approval boundaries. If any key decision, permission, tool, environment requirement, or test is missing, stop as not ready. Do not start implementation without approval.
Alternate two models from different providers to review a plan, doc, or diff until both approve the exact same version.
Review [plan, specification, document, or code change] against [quality bar] for at most [pass limit] rounds. Have one of two genuinely different model families—AI systems from separate providers—review it. Verify each finding and apply only necessary fixes, then give the revised version to the other reviewer. Succeed only when both approve the same unchanged version. Stop at the limit, repeating disagreement (oscillation), unavailable review, or required approval. Return the final work, round log, verdict, and disagreements.
Update every copy of a changed value across the project, hunt down leftovers, and prove only intentional old references remain.
After changing a version, count, rule, name, or configuration, list where the new value belongs and update it. Search the project for the old value and related forms. Review each match: fix real stale values, but keep intentional history, examples, migrations, or compatibility rules. Repeat until zero stale values remain. If one returns for two rounds, stop and identify what may be regenerating it. Return changes, intentional matches, and search output.
Compare claims in marketing, docs, demos, and AI answers against current evidence, then fix or narrow anything unsupported.
List every customer-facing promise [product] makes in marketing, documentation, demos, and AI answers. Compare each promise with current product behavior and evidence, then label it proven, partly proven, misleading, unsupported, outdated, or missing evidence. Fix or narrow the riskiest mismatch and rerun the affected check. Repeat until no high-risk unsupported promise remains. Ask before changing production or public copy. Return the promises, evidence, fixes, and decisions needed.
Convert recent user-reported problems into reusable failure patterns, fix every confirmed match, and verify a clean final pass.
Review all available threads from [lookback window] where I reported something wrong with [project] and asked for a fix. Build a deduplicated issue list, group it into failure patterns, and verify current state. Audit the complete project for every pattern, fix each confirmed instance, and add regression coverage where practical. Repeat the full audit until it finds no remaining instance or [iteration budget] ends. Stop on blocked or approval-gated work. Return the issues, fixes, evidence, and blockers.
Triage the repo, route bounded maintenance to dedicated threads, and require proof and permission before anything lands.
While repository maintenance is active, wake every five minutes. Triage [repositories] and read each repository thread's latest state. Reuse one thread per repository; assign its highest-value bounded task only within granted permissions, and do not interrupt coherent active work. Require tests, live proof, autoreview, and green CI before work can land. Escalate product, access, security, or irreversible decisions. Record meaningful changes and stop when every item is landed, decision-ready, blocked, or has no work.
Sponsored · ConnectMyEmailLoops 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 → Improve prompts, code, or config through checkpointed experiments whose scores stay comparable across sessions.
Use Revolve to improve a support prompt, code path, or testable subject. In revolve/, define the goal and [budget], freeze the tests and scoring, checkpoint the current version, and record a baseline. Each round, test one hypothesis; keep only a clear, regression-free win. If the evaluation changes, open a new revision and rerun the baseline. Ask before changing live files. Stop on success, no progress, a blocker, or exhausted budget. Return the best checkpoint, comparisons, rollback, and next action.
Set the completion contract up front, track proof for every requirement, and block partial work from being called done.
Run $goal-planner-codex [task] for long-running Codex work where partial work could be mistaken for done. Landing a PR and verifying production is one example. Before acting, define every required outcome and its evidence. After each bounded action, mark requirements proved, weak, missing, or contradicted. Complete the Goal only when all are proved; otherwise stop as blocked, stalled, or exhausted. Ask before creating Goal state. Finish with the requirement-to-evidence table, status, owner, and next action.
A builder and an adversarial reviewer pass a git baton between worktrees, proving every new test can catch its fix.
Use autonomy-loop for [repository task] after the test, build, and lint gates pass. Run /autonomy-loop:autonomy-init, then start builder and reviewer in separate worktrees. The builder reads LOOP-STATE.md, makes one bounded change, and adds a red-before, green-after test. The reviewer reruns the gates and proves the test by reverting or mutating the fix. Accept only on both passes; park protected or repeated-failure work for a human. Finish with the commit, gate evidence, test proof, trust tier, and risks.
Generate ten concepts, score the top three against a real channel, and sharpen the winner without misleading viewers.
For [video], use [approved assets] to make ten thumbnail concepts. Score each at real YouTube sizes against [inspiration channel] for clarity, curiosity, emotional pull, contrast, and accuracy. Take the top three, improve each one's weakest dimension, and rescore them under the same rubric. Keep iterating the strongest concept until it clears [quality threshold] or [budget] ends. Reject anything the video cannot deliver. Return the winner, two runners-up, previews, final scores, and rationale.
Follow the README in a throwaway environment, fix every hidden setup assumption, and restart until a clean clone just works.
Clone [repository] into a disposable environment and follow only its README to the documented ready state, such as running the app or building the package. When a step fails or assumes missing knowledge, record the gap, fix the setup or documentation issue, discard the environment, and start again. Carry no dependencies, configuration, credentials, or repairs between attempts. Stop when one uninterrupted fresh clone reaches that state, progress stalls, or [budget] ends. Return exact commands, gaps closed, and remaining blockers.
A critic hammers the design and a builder answers — every objection tracked, and none closed without evidence.
Before committing to an architecture, interface, or rollout plan, have a critic argue that it is wrong. Record each objection, impact, and status in a repository-local log at .agent-reviews/redteam.md. The builder must fix and verify each high-impact weakness or document why it is accepted; the critic may reopen unsupported answers. Stop when no high-impact objection remains or the same issues repeat for two rounds without new evidence. Finish with the decision, resolved and accepted objections, evidence, and any stalemate.
Test challenger prompts on a working set, promote only on fresh holdout wins, and keep the champion when results are uncertain.
Improve a prompt, policy, or configuration. A support assistant's system prompt is one example. Save the champion, its score, a working set, untouched holdout cases, must-pass checks, and [budget]. Each round, change one thing based on a recorded failure. Promote the challenger only if it beats the champion on holdouts by [margin] without weakening a must-pass check; otherwise keep the champion. Stop at the target, budget limit, or no progress. Return the winner, scores, experiment log, and remaining failures.
Capture a real page, build a static mirror and a live version, then repair the weakest fidelity signals until they match.
Point War Loops at an authorized URL or image. Capture it with a genuine browser and record the layout, styles, content, motion, and responsive behavior. Build a static Pencil mirror and a moving Forge version. Compare both with the source at desktop, tablet, and mobile sizes; repair only the weakest fidelity signals. Stop when every gate passes, progress stalls, or capture is blocked. Finish with the builds, spec, renders, scores, and remaining gaps.
An agent builds a 747 from Three.js primitives, renders nine fixed angles, and fixes whatever each view exposes.
Before building, choose reference images, a scoring rubric, [visual threshold], and [budget]. Build the most realistic Boeing 747 you can from Three.js primitives, then create a rig that screenshots nine repeatable angles. After each change, render and score the same views, have a critic identify the weakest feature, and fix it without regressing stronger views. Keep the best version. Stop at the threshold, stalled progress, or budget. Finish with the model, nine renders, scores, remaining gaps, and run summary.
Run one agent in an isolated worktree and release its staged output only after a second agent verifies the work.
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.
Sponsored · ConnectMyEmailLoops 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 → Open a PR, run an independent Codex review, fix every blocking finding, and repeat until it's clean.
Run /clodex [task] think hard --max-iter 5 --threshold medium. Claude plans the task, implements it, opens a pull request, asks Codex for an adversarial review, fixes findings above the accepted severity, and repeats. Keep the branch, PR, findings, verdict, and iteration state resumable. Stop when Codex approves, only accepted findings remain, progress stalls, or the iteration cap is reached. Never describe an errored or exhausted run as approved. Finish with the PR, checks, verdict, and remaining findings.
Each cycle, turn meaningful public product changes into a short, source-grounded podcast episode.
Each night, review publicly released product changes and select only those users need to know. Verify each against the product, docs, or release notes. Use the Jellypod MCP to turn the approved changes into a three-to-five-minute podcast explaining what changed, why it matters, and how to try it. Check the script and audio for accuracy, clarity, and pronunciation. If nothing meaningful shipped, make no episode. Ask before publishing. Finish with the draft episode, sources, and review result.
Advance a single customer priority into a validated, gradually released system with monitoring, approvals, and outcome evidence.
Run this when a customer requests an AI workflow, reports a failure, or reaches an operations review. Choose one priority, such as enriching leads, drafting emails, summarizing meetings, or updating a CRM. Define the owner, inputs, approvals, success metric, and ROI hypothesis. Dry-run it on realistic customer data, fix the smallest verified problem, then release through approved stages and monitor production. Finish with the outcome, evidence, customer update, lessons saved, and next review.
Turn a ticket or bug report into a proven root cause, a minimal patch, and a clean handoff a reviewer can trust.
Take a ticket, bug report, failing behavior, or customer complaint and turn it into a review-ready patch. Reproduce the failure in the smallest representative environment, prove the root cause, make the smallest credible fix, and rerun the original reproduction plus relevant regression tests. If the issue cannot be reproduced after two serious attempts, say so. Do not fold unrelated refactors into the patch. Finish with the cause, changed files, before-and-after proof, risks, and pull-request summary.
Run the standard benchmarks against a finished release and record a reproducible baseline for future comparison.
After current releases finish, run the standard benchmarks and record the results as the new baseline.
Remove disallowed records, sharpen the classification logic, and verify the remaining dataset against an explicit definition.
Review production records, remove anything that does not meet the allowed definition, improve the classification logic, and verify the remaining data.
Exclude unfinished or stale branches, combine the valid changes, and ship a complete artifact from the latest integrated main.
Review pending changes and pull requests, exclude stale or unfinished work, combine the valid changes, and release them together.
Audit branches, PRs, commits, and worktrees; rescue anything valuable; then delete what's provably stale.
Inspect local and remote branches, pull requests, commits, and worktrees. Recover valuable work and clean everything stale until the repository is current and organized.
Cut test runtime under repeatable conditions without weakening coverage, assertions, isolation, or behavior.
Optimize the test suite to run as quickly as possible without reducing coverage or changing behavior.
Run realistic scenarios across every major capability, fix weak outcomes, and rerun until each clears the defined bar.
Build sanitized, production-scale local data under production-like settings. Inventory every user-facing feature, role, route, button, input, modal, state, and workflow; define documented acceptance criteria and finite risk-based edge cases for each. Test as a real user, logging every bug with reproduction evidence. Review findings for shared causes and dependencies; implement coherent fixes with regression tests, then rerun the full inventory. Stop at a clean pass or blocked handoff. Ask before production, sensitive data, or destructive actions.
Sponsored · ConnectMyEmailLoops 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 →