PR Self Review
A structured self-review protocol that turns a diff into review comments before asking a human to review it.
Use loop copies the kickoff prompt. Copy Markdown and Download loop include the complete Markdown page with context, source attribution, anchors, and guardrails. Cursor / Claude Code buttons prepare the shorter kickoff prompt only.
Supported agents
Goal
Identify problems in the agent’s own PR before human review.
Feedback gate
git diff --stat main...HEAD && git diff --check main...HEADStop condition
No must-fix review issues remain, or unresolved issues are clearly documented.
Give the agent these inputs before it starts the loop. This keeps discovery bounded and prevents vague retries.
The loop assumes these commands or integrations are available. Missing tools should be reported as blockers, not ignored.
Two separate pieces: the kickoff prompt starts the loop, while the downloaded Markdown carries the complete reference page.
1. Copy or download
Use the kickoff for a fast agent run. Download the full Markdown when you need source, context, and attribution in one file.
2. Paste into the agent
Start a fresh agent session in the target repo and provide the requested project context if the loop asks for it.
3. Let it self-pace
The agent should act, check evidence, retry only when the gate fails, and stop at the stated exit condition.
The diagram shows the order. This checklist keeps only the action, command, and failure handling needed during a real pass.
1. Read the task and diff
Compare requested behavior to changed files.
git diff --stat main...HEAD2. Review by risk category
Check behavior, tests, API compatibility, accessibility, SEO, and deployment risk where relevant.
3. Fix must-fix issues
Patch critical omissions and rerun relevant checks.
4. Write review summary
Return review findings and verification evidence.
This is the text copied by Use loop. It is intentionally shorter than the Markdown export.
Review your own PR against the original task, changed files, tests, and risk categories. Fix must-fix issues and report evidence.
Goal: Identify problems in the agent’s own PR before human review.
Check command: git diff --stat main...HEAD && git diff --check main...HEAD
Exit condition: No must-fix review issues remain, or unresolved issues are clearly documented.
Max iterations: 3
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not hide unresolved issues; label them as risks or blockers.Quality
87/100
Safety
91/100
Expected output
A review report with must-fix issues, nice-to-have issues, and verification evidence.
Related loops
Browse allIndependent Verifier Pass
Review an agent-produced change as a skeptical verifier before it is marked done.
Kickoff preview
Act as an independent verifier. Restate the requirements, inspect the diff, run relevant checks, and return a pass/fail/blocker verdict with evidence. Goal: Prove the implementation satisfies the request without relying on the implementer’s claim. Check command: git diff --stat && git diff --check Exit condition: The verifier can map each requirement to code and verification evidence. Max iterations: 3 Guardrails: - Do not weaken, skip, delete, or rewrite the validation command to force success. - Do not claim completion until the stated exit condition is actually satisfied. - If blocked, report the blocker, evidence, and next safest action instead of gaming the metric. - Do not rubber-stamp. Find at least one plausible failure mode and check it.
Regression Risk Audit
Map a change to likely regressions, then run or propose focused checks for those risks.
Kickoff preview
Map the changed files to affected call chains, list likely regressions, verify the top risks, and report remaining uncertainty. Goal: Identify likely regressions and verify the highest-risk paths. Check command: git diff --name-only main...HEAD Exit condition: Top regression risks are either tested, ruled out, or documented as unresolved. Max iterations: 4 Guardrails: - Do not weaken, skip, delete, or rewrite the validation command to force success. - Do not claim completion until the stated exit condition is actually satisfied. - If blocked, report the blocker, evidence, and next safest action instead of gaming the metric. - Do not overstate confidence when a risk was not actually verified.
Ship PR Until Green
Implement a scoped change, open or update a pull request, inspect CI, and continue until all required PR checks pass.
Kickoff preview
Take this branch to a green pull request. Implement the requested change, run local verification, open or update the PR, run `gh pr checks`, inspect failures, fix root causes, and repeat until every required check passes or you hit the iteration cap. Goal: Open or update a pull request and stop only when all required PR checks are green. Check command: gh pr checks Exit condition: All required pull request checks are successful and the PR is ready for review or merge. Max iterations: 10 Guardrails: - Do not weaken, skip, delete, or rewrite the validation command to force success. - Do not claim completion until the stated exit condition is actually satisfied. - If blocked, report the blocker, evidence, and next safest action instead of gaming the metric. - Do not disable required checks, edit loops to skip jobs, or remove tests to make CI green. - Do not merge the PR unless the user explicitly asked for merge authority.
SEO Metadata Audit Loop
Audit title, description, canonical, Open Graph, headings, and indexability for SEO-critical pages.
Kickoff preview
Audit SEO metadata from server-rendered HTML for the target pages. Verify title, description, canonical, H1, Open Graph, and indexability, then fix and re-check. Goal: Ensure SEO-critical pages have unique, server-rendered metadata and indexable content. Check command: curl -sL $URL | head -80 Exit condition: Each target page has unique title, description, canonical, visible H1, and no accidental noindex. Max iterations: 5 Guardrails: - Do not weaken, skip, delete, or rewrite the validation command to force success. - Do not claim completion until the stated exit condition is actually satisfied. - If blocked, report the blocker, evidence, and next safest action instead of gaming the metric. - Do not rely only on client-rendered metadata for SEO-critical pages. Verify server HTML.