Agent · opus
architect
Produces a system architecture for a spec: components, boundaries, data flow, risks, alternatives. Use when a non-trivial change needs design before planning.
Read · Grep · Glob
Every agent, skill, hook, and command paw ships, pulled straight from the source. Search it, or filter the agents by phase and permission tier.
46 results
Agent · opus
Produces a system architecture for a spec: components, boundaries, data flow, risks, alternatives. Use when a non-trivial change needs design before planning.
Read · Grep · Glob
Agent · opus
Turns architecture into a numbered, executable implementation plan with workstreams, file targets, and acceptance tests.
Read · Grep · Glob
Agent · opus
Adversarial review of a plan. Finds gaps, optimistic assumptions, missing rollback paths, hand-waved steps, and hidden dependencies.
Read · Grep · Glob
Agent · sonnet
Creates a rollback plan for any change: what to revert, in what order, and how to verify the rollback worked.
Read · Grep · Glob
Agent · sonnet
Implements a task using TDD: writes the test first, then the code, then refactors. The only agent with full access.
Read · Write · Edit · Bash · Grep · Glob
Agent · sonnet
Resolves git merge conflicts by understanding both sides' intent. Combines compatible changes, escalates competing ones.
Read · Write · Edit · Bash · Grep · Glob
Agent · sonnet
Plans safe database migrations using the expand-backfill-contract pattern. Never destructive in production.
Read · Write · Edit · Bash · Grep · Glob
Agent · opus
General code review on changed files. Flags correctness, edge cases, error handling, naming, and unclear intent. Severity levels: critical, warning, info.
Read · Grep · Glob
Agent · sonnet
Hunts latent bugs: race conditions, off-by-one, null deref, unbounded loops, integer overflow, encoding mismatches, time-of-check/time-of-use.
Read · Grep · Glob
Agent · opus
OWASP Top 10 review on the diff. Flags injection, broken access control, crypto failures, SSRF, XSS, prompt injection. Adversarial mindset.
Read · Grep · Glob
Agent · sonnet
Performance review: N+1 queries, unbounded fetches, missing pagination, sync work in async paths, heavy renders, allocations in tight loops.
Read · Grep · Glob
Agent · sonnet
Frontend-specific reviewer for React/Vue/Angular: accessibility, component structure, hooks, render performance, state management.
Read · Grep · Glob
Agent · sonnet
PHP/Laravel-specific reviewer: SQL injection, mass assignment, CSRF, N+1 Eloquent, auth middleware, type safety, queue idempotency.
Read · Grep · Glob
Agent · sonnet
Runs the project's test suite, captures results, identifies new failures, and flags missing coverage on changed code.
Read · Bash · Grep · Glob
Agent · sonnet
Runs integration and end-to-end tests. Validates that components work together, not just individually.
Read · Bash · Grep · Glob
Agent · sonnet
Validates that the development environment is correctly set up: dependencies, env vars, database, services, build tools.
Read · Bash · Grep · Glob
Agent · opus
Triages production incidents. Stop the bleeding first, root-cause second, prevention third.
Read · Write · Edit · Bash · Grep · Glob
Agent · sonnet
Updates documentation to match code changes: README, CHANGELOG, inline docs, migration guides, examples.
Read · Write · Edit · Grep · Glob
Skill · Design
Designing systems, evaluating tradeoffs, deciding component boundaries, planning integration points.
skills/architecture/SKILL.md
Skill · Review
Reviewing any plan before commitment: architecture, implementation plan, migration strategy, design proposal.
skills/devils-advocate/SKILL.md
Skill · Stack
React, Vue, or Angular work: component design, accessibility, performance, state management.
skills/frontend/SKILL.md
Skill · Stack
PHP or Laravel work: Eloquent, middleware, validation, queues, migrations, testing.
skills/php-laravel/SKILL.md
Skill · Security
Any code touching authentication, user input, external APIs, or sensitive data.
skills/security/SKILL.md
Skill · Review
Reviewing code before merge. Running multiple review agents. Deciding what blocks and what doesn't.
skills/quality-gate/SKILL.md
Skill · Git
Any git operation that could lose work: pull, push, merge, rebase, branch management, conflict resolution.
skills/git-safety/SKILL.md
Hook · PreToolUse
Blocks dangerous git operations: rebase, pull --rebase, force-push (-f / --force), branch -D, reset --hard, and checkout dot. Allows --force-with-lease by design.
override: PAW_ALLOW_REBASE, PAW_ALLOW_FORCE_PUSH
Hook · PreToolUse
Blocks git commits on protected branches (main, master, develop, trunk, release). Fails closed if the branch cannot be determined.
Hook · pre-commit
The pre-commit framework build of branch_guard. Blocks commits on protected branches as a standard git hook, no Claude Code required.
Hook · PostToolUse
Warns when a source file is written or edited and no matching test file exists nearby. It nudges, it does not run tests.
CLI · Setup
Check requirements, install hooks.
CLI · Learn
Interactive TUI walkthrough with 9 tracks.
CLI · Learn
Open the browser-based tutorial.
CLI · Setup
Diagnose problems with your install.
CLI · Config
Scaffold a .paw.json config into a project.
CLI · Quality
Standard quality gate: 3 reviewers.
CLI · Quality
Quick gate: code-reviewer only.
CLI · Quality
Thorough gate: all 8 reviewers.
CLI · Quality
Run a single review agent. Targets: security, bugs, perf, frontend, php, tests, docs, env.
CLI · Learn
List all 18 agents.
CLI · Smart
Suggested next steps based on your progress.
CLI · Smart
Detect your stack, recommend agents.
CLI · Learn
Print the quick reference card.
CLI · Setup
Create a Desktop app launcher (macOS).
CLI · Setup
Remove hooks and symlink.
CLI · Setup
Shell tab-completion (zsh or bash).
CLI · Meta
Show the installed version.