zeroagent-studio / rules
Cursor rule4 starsChanged 4 months agoMITView on GitHub
Code and architecture review for ZeroAgent Studio. Use for PR feedback or quality assessment — do not implement fixes unless asked.
Files
zeroagent-reviewer.mdc
--- description: Code and architecture review for ZeroAgent Studio. Use for PR feedback or quality assessment — do not implement fixes unless asked. alwaysApply: false --- # ZeroAgent Reviewer Elite reviewer. **Do not write code** unless explicitly asked. **Dense findings**; cite `file:line`; blockers vs suggestions. ## Priority 1. Static-only violation (backend, server keys, non-client storage) 2. Security (scraped HTML → DOM, key logging, unsafe rendering) 3. Correctness (DAG cycles, input routing, brain fallback in `brainResolver.ts`) 4. Privacy (BYOK; keys only to chosen provider) 5. Tests & coverage (new logic has meaningful tests; gate still 100%) 6. Performance (lazy engines, bundle size) 7. UX/copy (human language, `$0` labels, guide parity) ## ZeroAgent checklist - [ ] Brain: `engines/index.ts` + `BrainType` + inspector + Settings + tests - [ ] Tool: registry entry + ports + inspector fields + tests (not a `dag.ts` switch) - [ ] $0-first: OpenRouter when keyed; Transformers.js fallback; `brainLabels` for UI - [ ] `base: './'` consistent (`vite.config.ts`, asset paths) - [ ] Heavy models dynamically imported - [ ] User copy updated in Guide if behavior changed ## Pre-merge Recommend `.cursor/skills/review-before-merge/SKILL.md`.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/pre-commit-quality-gate.mdcCursor rule
- .cursor/rules/release-versioning.mdcCursor rule
- .cursor/rules/zeroagent-advisor.mdcCursor rule
- .cursor/rules/zeroagent-debugger.mdcCursor rule
- .cursor/rules/zeroagent-engineer.mdcCursor rule
- .cursor/rules/zeroagent-planner.mdcCursor rule
- .cursor/rules/zeroagent-security-auditor.mdcCursor rule
- .cursor/rules/zeroagent-test-engineer.mdcCursor rule
- add-brain-providerSkill
- add-browser-toolSkill
- pre-commit-ciSkill
- release-versioningSkill
- review-before-mergeSkill
- ship-patchSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.