mamertofabian

Review an implementation produced from an approved MAID manifest. Confirms changed files stay within manifest scope, declared artifacts exist, validations pass, and the behavior matches the contract. Use after maid-implementer or after any MAID-backed code change before merge.

Implement code against an approved MAID manifest. Loads only the declared files, writes code to pass behavioral tests, validates with `maid validate --mode implementation`, and iterates until all checks pass. Use after a manifest is approved by maid-planner (or manually).

Plan a coding task as a machine-checkable MAID manifest instead of free-form markdown. Analyzes the project, asks clarifying questions, drafts or refines a manifest, and for implementation-ready plans adds behavioral tests, validates with `maid validate --mode behavioral`, and gets user approval. The promoted manifest becomes the implementation contract. Use at the start of every new feature, bug fix, or refactor.

Use when implementing maid-runner MAID draft manifests from manifests/drafts, promoting them into manifests, and validating implementation batches with review before handoff in Claude Code.

Review an implementation produced from an approved MAID manifest. Confirms changed files stay within manifest scope, declared artifacts exist, validations pass, and the behavior matches the contract. Use after maid-implementer or after any MAID-backed code change before merge.

Implement code against an approved MAID manifest. Loads only the declared files, writes code to pass behavioral tests, validates with `maid validate --mode implementation`, and iterates until all checks pass. Use after a manifest is approved by maid-planner (or manually).

Plan a coding task as a machine-checkable MAID manifest instead of free-form markdown. Analyzes the project, asks clarifying questions, drafts or refines a manifest, and for implementation-ready plans adds behavioral tests, validates with `maid validate --mode behavioral`, and gets user approval. The promoted manifest becomes the implementation contract. Use at the start of every new feature, bug fix, or refactor.

Use when implementing maid-runner MAID draft manifests from manifests/drafts, promoting them into manifests, and validating implementation batches with review before handoff.

Use in bolt-to-github when asked to bug hunt, harden, or improve reliability for this deployed Chrome MV3 extension. Synthesizes evidence from tests, insights, release notes, logs, TODOs, e2e gaps, Chrome MV3 lifecycle risks, bolt.new DOM drift, GitHub API failures, Supabase auth/session issues, storage migrations, permissions, privacy, and user-visible degraded states; produces a prioritized hardening backlog and optional draft MAID manifests.

Use in bolt-to-github when asked to clean up, simplify, or refactor this deployed Chrome MV3 extension without changing behavior. Audits dead code, duplication, long services/components, weak test seams, stale TODOs, oversized fixtures, and brownfield MAID gaps; produces a confirmed cleanup backlog and optional draft MAID manifests for safe-refactor work. Specialized for Svelte, TypeScript, Chrome extension service workers/content scripts, GitHub sync/auth flows, and bolt.new DOM integration.

Use in bolt-to-github when asked to improve performance, latency, bundle size, memory use, battery impact, or efficiency for this deployed Chrome MV3 extension. Profiles popup rendering, content-script injection, bolt.new DOM observation, ZIP/download processing, GitHub sync, Chrome storage, service-worker wakeups, build chunks, and test/runtime bottlenecks; produces measured findings and optional draft MAID manifests without weakening correctness.

Recover the Chrome extension's bolt.new DOM selectors after Bolt redesigns its UI. Use when the Push to GitHub button stops appearing, or the Download / Export flow fails with "Export menu trigger not found" or "Download button not found". Also use after running scripts/capture-bolt-dom.mjs when a fresh DOM capture is sitting in /tmp/bolt-dom-capture/.