Skip to main content
paw
The idea library

Steal these agents.

paw ships a core 18 agents. This is the wider roster they come from: 42 in all, the rest worth building yourself. Recipes to chain them, and a prompt to find the ones only you need. A menu, not a spec.

42 AGENTS15 SHIP WITH PAW27 TO BUILD

The roster

Jobs worth handing to a narrow, well-scoped agent, grouped by where they earn their keep. The ones tagged in paw ship in the box. The rest are yours to build.

Research

codebase-cartographer

Maps an unfamiliar repo: entry points, data flow, and where the risky code lives.

prior-art-scout

Finds how this was already solved, in your own history and the wider ecosystem.

requirements-researcher

Reads the issues, docs, and threads and assembles what the feature actually needs to do.

competitive-analyst

Pulls apart a competitor's product or docs and reports what they do differently.

api-explorer

Reads a third-party API's docs and hands back the exact calls, auth, and gotchas.

Plan

architectin paw

Turns a spec into a system: components, boundaries, data flow, and the risks up front.

plannerin paw

Turns the architecture into a numbered, executable plan with acceptance tests.

devils-advocatein paw

Stress-tests the plan for gaps, optimistic assumptions, and hand-waved steps.

intake-normalizer

Turns a messy issue, PDF, or Slack thread into one clean spec everyone can build from.

Design

design-system-keeper

Checks new UI against your existing colors, spacing, and components so it matches the rest of the app.

fe-reviewerin paw

Reviews front-end markup, component states, and responsive behavior.

ux-writer

Writes the microcopy: button labels, empty states, and errors that sound human.

accessibility-auditor

WCAG pass: keyboard, focus, contrast, semantic HTML, and alt text.

Build

builderin paw

Implements one task test-first in an isolated worktree, then refactors.

migration-architectin paw

Designs safe schema changes: expand, backfill, contract. No destructive one-shots.

merge-resolverin paw

Integrates parallel branches and resolves conflicts by merge, never rebase.

scaffolder

Generates the boring boilerplate for a new module to your house conventions.

Review

code-reviewerin paw

Correctness, edge cases, error handling, naming, and unclear intent on the diff.

bug-auditorin paw

Hunts latent bugs: races, off-by-one, null deref, overflow, time-of-check issues.

perf-checkerin paw

N+1 queries, unbounded fetches, sync work in async paths, heavy renders.

breaking-change-detector

Flags public-API changes that will break the people who depend on you.

silent-failure-hunter

Empty catches, swallowed errors, and fallbacks that hide real failures.

comment-analyzer

Comments that lie, comments that just narrate, and the missing 'why'.

Security

security-owasp

OWASP Top 10 on the diff: injection, broken access control, SSRF, XSS, secrets.

security-soc2

SOC 2 readiness: access controls, logging, encryption in transit and at rest.

dependency-auditor

CVEs, licenses, and supply-chain risk in anything new you pulled in.

secrets-scanner

Hunts hardcoded keys, tokens, and credentials before they reach git history.

threat-modeler

Maps the attack surface of a new feature before a line of it is written.

Test & QA

test-runnerin paw

Runs the suite, isolates new failures, and flags code that shipped without a test.

flake-detector

Finds tests that pass and fail without a code change, and quarantines them.

integration-testerin paw

Exercises the seams between systems, where the demo-proof bugs hide.

coverage-gap-finder

Finds the changed lines that shipped without a single test touching them.

Ship

docs-writerin paw

Updates the README, migration guide, and examples to match what you just built.

release-notes-writer

Turns the commits into user-facing release notes people will actually read.

rollback-plannerin paw

Writes the rollback procedure before you ship, not during the incident.

delivery-agent

Opens the PR with the full audit trail and waits for a human to approve the merge.

Ops & risk

risk-assessor

Flags irreversible or high-blast-radius steps before anyone runs them.

cost-estimator

Prices the change: new crons, full-table scans, LLM calls, edge invocations.

observability-agent

Checks that new code emits enough logs, metrics, and traces to debug at 2am.

incident-commanderin paw

Takes over when things derail: halts the mess, preserves forensics, escalates.

product-intent-checker

Compares what shipped against what was actually asked for, and flags the drift.

gap-detector

Reads the intent check and spawns follow-up work for whatever the plan missed.

Recipes by role

Chaining beats any single agent. A few starting points, one per hat you might wear. Read the arrows as "then".

Designer
Ship a component that is actually accessible
fe-revieweraccessibility-auditordocs-writer

Have the front-end reviewer check the markup and states, the accessibility auditor catch the keyboard and contrast gaps a demo hides, then docs-writer produce the usage example your team will copy.

Product
Turn a vague ask into a plan you can trust
architectdevils-advocateproduct-intent-checker

Architect drafts the approach, devils-advocate pokes holes in it before you commit, and product-intent-checker confirms the result still matches what you actually asked for.

Engineering
Merge a feature with confidence
code-reviewer + bug-auditor + securitytest-runnerrollback-planner

Run the review trio in parallel on the diff, then the test suite, then write the rollback before you ship. Three passes, and you sleep.

Leadership
Know the risk and cost before you greenlight
risk-assessorcost-estimatorgap-detector

Risk-assessor flags the blast radius, cost-estimator prices the cloud spend, and gap-detector shows what the plan is quietly missing. A one-page decision brief, no meeting.

QA
Find the bugs the demo hides
bug-auditorflake-detectorintegration-tester

Bug-auditor hunts the latent stuff, flake-detector quarantines tests that lie, and integration-tester checks the seams between systems where real failures live.

Find your gaps

The best agent to build next is the one that encodes a judgment you already make by hand. Paste this into Claude (or any capable model) pointed at your own work, and let it find them.

Look at my last two weeks: commits, PR comments, and the mistakes I keep catching by hand in review. What repetitive judgment am I applying manually that an agent could encode for me? Propose 3 agents I do not have yet. For each: a name, its one-line job, the tools and permissions it would need, and the specific gap it fills. Rank them by how much time they would save me.

Standing on shoulders

everything claude code@affaan-m
230K+ stars ยท 35K forks

Billed as the agent harness performance optimization system for Claude Code and beyond, it opened my eyes to what was possible and got this whole rabbit hole started. A good number of the ideas above trace straight back to it. Thank you.

github.com/affaan-m/ecc