Agent
Implements or refactors C/C++ against the repo's conventions, verifying with its build/tests/clang-tidy/format gate; returns a change report with verbatim gate output. Spawn one per module-sized task.
Agent
Digests a large file or doc set into a structured brief against the caller's question template, keeping raw bytes out of the caller's context; coverage mode returns only the gaps for a doc slated for deletion or merge. Read-only on inputs; writes only its brief, to a caller-named path outside the repo. Spawn one per…
Agent
Reconciles README, docs/, CLAUDE.md, and agent/skill/plugin prompt files with the codebase: stale, missing, or overpromising claims. Edits docs only. Spawn one per repo.
Agent
Implements or refactors Flutter/Dart against the repo's conventions, verifying with its codegen/format/analyze/test gate; returns a change report with verbatim gate output. Spawn one per module-sized task. Not for reviewing a diff (flutter-reviewer).
Agent
Reviews Flutter/Dart diffs read-only on source and returns a findings table: correctness, async/context safety, rebuild perf, state-management misuse. Writes only its report, to a caller-named path outside the repo. Spawn one per diff. Not for implementing (flutter-pro).
Agent
Builds self-contained single-file frontends: canvas/WebAudio demos, inline-SVG icons/favicons, no-build client-side pages. Writes frontend files only. Spawn one per artifact.
Agent
Implements or refactors Go against the repo's conventions, verifying with its build/test/vet or golangci-lint gate; returns a change report with verbatim gate output. Spawn one per module-sized task.
Agent
Tests a Flutter or mobile app like a real user on an Android AVD or iOS simulator, verifying with parsed screenshots and integration tests. Read-only on source; reports pass/fail with evidence paths. Spawn one per app or flow.
Agent
Runs a build, test, lint, or any command and returns a pass/fail probe (exit code, warn/error counts) instead of the full log. Never mutates. Spawn one per check.
Agent
Implements or refactors Python against the repo's conventions, verifying with its test/lint/type-check gate; returns a change report with verbatim gate output. Spawn one per module-sized task. Not for reviewing a diff (python-reviewer).
Agent
Reviews Python diffs read-only on source and returns a findings table: correctness, typing, security, clarity. Writes only its report, to a caller-named path outside the repo. Spawn one per diff. Not for implementing (python-pro).
Agent
Implements, refactors, or tests Rust TUI code with current-ratatui built-ins, writing TestBackend tests and running the repo's gate. Use for ratatui/crossterm widgets, layout, or event loops. Edits Rust source plus the target repo's ratatui punch-list. Spawn one per module-sized task.
Agent
Evidence-first diagnosis of bugs with an unclear or disputed cause: multiple suspects, a 'started failing recently', symptoms across unrelated components. Builds repro harnesses, runs A/B and version-matrix experiments, returns a hypothesis ledger with an attributed cause. Never fixes or posts; writes only its harness…
Agent
Implements or refactors Rust against the repo's conventions, verifying with its build/test/clippy/fmt gate; returns a change report with verbatim gate output. Spawn one per module-sized task. Not for reviewing a diff (rust-reviewer).
Agent
Reviews Rust diffs read-only on source and returns a findings table: correctness, safety, async, invariants. Writes only its report, to a caller-named path outside the repo. Spawn one per diff. Not for implementing (rust-pro).
Agent
Writes or refactors shell scripts (bash or POSIX sh) matching the repo's portability posture, verifying with shellcheck and the repo's tests. Spawn one per script or module-sized task. Not for reviewing a diff (shell-reviewer).
Agent
Reviews shell scripts read-only on source and returns a findings table: quoting, error handling, injection, portability. Writes only its report, to a caller-named path outside the repo. Spawn one per diff or script set. Not for implementing (shell-pro).
Agent
Folds a decided spec or approved decision into one design doc that doesn't mention it yet, matching the doc's voice. Edits docs only. Spawn one per doc.
Agent
Architecture-level threat modeler (STRIDE, attack trees, requirement extraction): identifies threats, designs mitigations for a system or feature. Read-only on code; writes only the threat-model doc. Spawn one per system or feature.
Agent
Reviews TypeScript/JavaScript diffs read-only on source and returns a findings table: correctness, type-safety, XSS/injection, any leakage. Writes only its report, to a caller-named path outside the repo. Spawn one per diff.
Agent
Drives a TUI or CLI program like a real user in a local tmux pty. Read-only on source; builds or launches the target itself, reports pass/fail with captured screens. Spawn one per program or flow.
Agent
Implements a screen's interaction behavior with the repo's own components: loading/success/error/empty/partial states, form validation, error placement, accessibility wiring. Use when a screen misses non-happy-path states or a flow needs error handling. Returns a five-state inventory with verbatim gate output. Spawn…
Agent
Reviews UI behavior read-only on source and returns a findings table: missing loading/error/empty/partial states, silent failures, error wording and placement, validation gaps, missing undo, status-message accessibility. Writes only its report, to a caller-named path outside the repo. Spawn one per screen or diff. Not…
Agent
Single-topic web researcher for fan-out: multi-query search, full-source fetch, cross-verification, a cited markdown brief written to a path. Spawn one per topic.