Codex ops
Practical design judgment for AI coding agents: 78 installable skills for craft, research, generation, Figma, and Memoire.
npx -y skills add sarveshsea/design-skills --skill codex-opsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Codex and Claude operating workflow for Memoire - JSON-first commands, commit hygiene, review loops, memory capture, and safe autonomous repo operation
SKILL.md
2.9 KB, as published. Nobody here has run it
Codex Ops
Use this when Codex or Claude is operating inside the Memoire repository and needs a stable workflow for safe autonomous changes.
Core Rule
Prefer machine-readable command output whenever Memoire exposes it. Do not scrape terminal prose if a JSON surface exists.
Current JSON-first commands:
memi status --jsonmemi connect --jsonmemi notes list --jsonmemi notes info <name> --jsonmemi compose "..." --jsonmemi doctor --jsonmemi generate --jsonmemi export --json
Execution Pattern
- Inspect state first with JSON-capable commands.
- Use dry-run modes before mutating files when available.
- Make one coherent change at a time.
- Verify with focused tests or typecheck.
- Commit and push each lane separately.
Commit Hygiene
- Keep each commit scoped to one behavior or one workflow lane.
- Do not mix note content, command changes, and unrelated generated output.
- If the worktree is already dirty, treat existing changes as user state unless you know they were produced by your own current lane.
- Do not rewrite or revert unrelated files to make your diff cleaner.
Review Loop
- Read the diff before every commit.
- Prefer targeted regression tests over broad reruns first.
- If a command has a
--jsonmode, add or update tests against the structured payload rather than asserting on human-readable formatting. - When a fix changes behavior, verify both the focused path and the combined command suite that overlaps it.
Memory Capture
- If a workflow becomes stable, encode it in a built-in note or skill instead of repeating it in freeform prompts.
- If a command repeatedly needs structured output, add
--jsoninstead of teaching agents to parse ASCII tables or prose. - If a repository convention matters across many commits, capture it in a note, not only in one changelog entry or one conversation.
Safe Autonomy
- Prefer additive or explicitly scoped changes.
- Use
--dry-run,doctor, andstatus --jsonbefore destructive or broad operations. - Treat
.memoire/, generated outputs, preview artifacts, and user specs as project state, not disposable scratch space. - When a lane is already pushed to
main, reconcile local work toHEADinstead of silently diverging.
Recommended Sequence
For a normal implementation lane:
memi status --jsonmemi connect --jsonmemi doctor --json- edit the smallest viable set of files
- run focused tests
- run
npm run typecheck - commit one lane
- push immediately
For note work:
- add
note.json - add the markdown skill file
- add a focused note regression test
- run the note tests plus typecheck
- commit and push that note as its own lane