paw
01Cursor rule Cursor
You have access to specialized agent definitions in the agents/ directory. Reference them when the task matches their specialty.
Cursor rule Cursor
You have access to specialized agent definitions in the agents/ directory. Reference them when the task matches their specialty.
Instructions file CodexOpenCode
Instructions for Effulgent-Point/paw, covering paw agents — for codex cli and other ai tools, how to use, agent definitions, rules and skills.
Instructions file
Instructions for Effulgent-Point/paw, covering paw — personal agent workforce, what paw is, how to work in this repo, composability is the design and agents have scoped permissions.
Agent
Produces a system architecture for a spec — components, boundaries, data flow, risks, alternatives. Use when a non-trivial change needs design before planning.
Agent
Hunts latent bugs — race conditions, off-by-one, null deref, unbounded loops, integer overflow, encoding mismatches, time-of-check/time-of-use.
Agent
Implements a task using TDD — writes the test first, then the code, then refactors. The only agent with full access.
Agent
General code review on changed files. Flags correctness, edge cases, error handling, naming, and unclear intent. Severity levels — critical, warning, info.
Agent
Adversarial review of a plan — finds gaps, optimistic assumptions, missing rollback paths, hand-waved steps, and hidden dependencies.
Agent
Updates documentation to match code changes — README, CHANGELOG, inline docs, migration guides, examples.
Agent
Validates that the development environment is correctly set up — dependencies, env vars, database, services, build tools.
Agent
Frontend-specific reviewer for React/Vue/Angular — accessibility, component structure, hooks, render performance, state management.
Agent
Triages production incidents. Stop the bleeding first, root-cause second, prevention third.
Agent
Runs integration and end-to-end tests. Validates that components work together, not just individually.
Agent
Resolves git merge conflicts by understanding both sides' intent. Combines compatible changes, escalates competing ones.
Agent
Plans safe database migrations using the expand-backfill-contract pattern. Never destructive in production.
Agent
Performance review — N+1 queries, unbounded fetches, missing pagination, sync work in async paths, heavy renders, allocations in tight loops.
Agent
PHP/Laravel-specific reviewer — SQL injection, mass assignment, CSRF, N+1 Eloquent, auth middleware, type safety, queue idempotency.
Agent
Turns architecture into a numbered, executable implementation plan with workstreams, file targets, and acceptance tests.
Agent
Creates a rollback plan for any change — what to revert, in what order, and how to verify the rollback worked.
Agent
OWASP Top 10 review on the diff. Flags injection, broken access control, crypto failures, SSRF, XSS, prompt injection. Adversarial mindset.
Agent
Runs the project's test suite, captures results, identifies new failures, and flags missing coverage on changed code.
Skill Claude CodeCodex
When to use: Designing systems, evaluating tradeoffs, deciding component boundaries, planning integration points.
Skill Claude CodeCodex
When to use: Reviewing any plan before commitment — architecture, implementation plan, migration strategy, design proposal.
Skill Claude CodeCodex
When to use: React, Vue, or Angular work — component design, accessibility, performance, state management.