# Self-review before done

> Eight questions your AI answers against its own diff before it says done, so the gaps show up before you find them.

Page: https://videotomd.com/b/text-self-review-before-done/
Tool: Any AI · Tags: self-review, agents-md, done-check, quality · 369 words, about 480 tokens
Pills: free · ran in Claude Code · self-check · done check · checked 2026-10-12 · Any AI · Claude Code · Codex · Cursor · Any text chat · chat only · always on · 7B ok · coding

## Recipe

- Kind: eval
- Stage: not set
- Loads: always on
- Works in: Any AI, Claude Code, Codex, Cursor, Any text chat
- Needs: chat only
- Bring: nothing
- Cost: free
- Model: 7B ok
- Tested in: Claude Code
- Checked: 2026-10-12
- For: coding

## When this is useful
- Your agent says "done" and the tests were never run.
- A diff touched files nobody asked about and you found out in review.
- You want one habit that catches the last ten percent without a second reviewer.


## Change it to
- Claude Code: the same block in CLAUDE.md, or in .claude/rules/done.md to keep the main file short (the claude-code row).
- Chat-only: paste the block with your first message and end each request with "then answer the eight" (the any-chat row).
- 7B model: keep questions 1, 3, 5 and 7 only; small models drop the middle of a long list.
- Enforced version: a git pre-commit hook that runs the checks beats question 1, because git runs it whether or not the model remembers.


## If your AI needs to look something up
- Which file your harness reads: fetch https://agents.md/ for the AGENTS.md convention, or your harness's own instructions page.


## Put it here

Always on: put it where your tool reads instructions every session:

- Any AI: Coding agent: save as AGENTS.md in the project root (read natively by Codex, Cursor, Copilot, Gemini CLI, Kiro, Devin, Cline, Roo, OpenHands, OpenCode, Goose, Amp, Zed, Warp, Junie, Factory and Jules; Claude Code when no CLAUDE.md exists; Aider with --read). Chat: paste it first. Reload: new session. Check it loaded: ask it to repeat one rule from the file. Source: https://agents.md/ (checked 2026-10-12).
- Claude Code: Save as CLAUDE.md in the project root, or .claude/CLAUDE.md. Other agents share the repo: put the shared rules in AGENTS.md and make CLAUDE.md one line, @AGENTS.md. Commit it. Start a new session: the file is read at launch. Reload: new session (or /memory to open the files). Check it loaded: /context lists the Memory files it read; /skills, /agents, /hooks list the rest; the InstructionsLoaded hook event fires once per loaded instruction file. Source: https://code.claude.com/docs/en/memory (checked 2026-10-12).
- Codex: Save as AGENTS.md in the repo root. Codex concatenates AGENTS.md from the git root down to the working directory, closer wins. Commit it. Start a new session. Reload: new session. Check it loaded: ask: Summarize the current instructions; `codex status`. Source: https://learn.chatgpt.com/docs/agent-configuration/agents-md (checked 2026-10-12).
- Cursor: Save as AGENTS.md in the repo root, or as .cursor/rules/<name>.mdc with `alwaysApply: true` in its frontmatter. Commit it. Reopen the project so it reindexes. Reload: reopen the project. Check it loaded: Cursor Settings → Rules shows each rule and its status; no per-reply indicator. Source: https://cursor.com/docs/context/rules (checked 2026-10-12).
- Any text chat: Paste the whole file as your first message, then your task. A chat cannot read files or run commands: it must hand you the command and wait for the output. Reload: paste it again in a new chat. Check it loaded: ask it to repeat one rule from the file; a general answer means it is not in context. Source: https://videotomd.com/use-with-your-ai/ (checked 2026-10-12).

## Access

Membership: plans at https://videotomd.com/pricing/, or email then a plan at https://videotomd.com/b/text-self-review-before-done/. A member's browser downloads the file there; an AI without that session needs the member to attach it.