Agents

Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.

investigate-error

01

react/react

Agent Claude Code

Investigates React compiler errors to determine the root cause and identify potential mitigation(s). Use this agent when the user asks to 'investigate a bug', 'debug why this fixture errors', 'understand why the compiler is failing', 'find the root cause of a compiler issue', or when they provide a snippet of code and…

not rated 251k +60 today A 90 tokens original MIT

css

02

anomalyco/opencode

Agent OpenCode

Agent "css" from anomalyco/opencode, covering example of correct implementation, reusable components and key clarifications.

not rated 212k +868 today A 9 tokens original MIT

worker

03

google-gemini/gemini-cli

Agent Claude CodeGemini CLI ✓ vendor

General purpose agent for any tasks that need a scoped context window.

not rated 107k +36 today A 15 tokens original Apache-2.0

microsoft/playwright

Agent Claude Code ✓ vendor

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

not rated 97k +257 today A 151 tokens original Apache-2.0

agents-directory

05

code-yeongyu/oh-my-openagent

Agent Claude Code

Developer reference for all 11 Oh My OpenAgent agent definitions, factory patterns, tool restrictions, and model routing.

not rated 70k +138 changed 14d ago A 26 tokens

requirement-parser

06

shanraisshan/claude-code-best-practice

Agent Claude Code

Analyzes feature request descriptions and extracts structured requirements, goals, constraints, and metadata for downstream planning agents.

not rated 67k +289 yesterday A 25 tokens original MIT

gsd-debugger

07

gsd-build/get-shit-done

Agent Claude Code

Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd:debug orchestrator.

not rated 64k +55 4mo ago A 30 tokens original MIT archived

docs-researcher

08

upstash/context7

Agent Claude Code

Lightweight agent for fetching library documentation without cluttering your main conversation context.

not rated 63k +193 changed 9d ago A 20 tokens original MIT

code-reviewer

09

anthropics/claude-cookbooks

Agent Claude Code ✓ vendor

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

not rated 53k +129 10d ago A 52 tokens original MIT

review-triager

10

prisma/orm

Agent Claude Code ✓ vendor

Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.

not rated 48k +15 today A 0 tokens original Apache-2.0

access-control

11

PostHog/posthog

Agent Claude Code

PostHog access control system implementation expert - use when adding access controls to new products, debugging access control issues, or questions about RBAC patterns.

not rated 40k +100 changed 1mo ago A 32 tokens

AVM Owner Triage

12

github/awesome-copilot

Agent Claude Code ✓ vendor

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

not rated 40k +176 today A 61 tokens original MIT

continuedev/continue

Agent Claude Code ✓ vendor

Flag renamed commands, APIs, or config options with stale references.

not rated 36k +64 today A 16 tokens original Apache-2.0

reviewer

14

can1357/oh-my-pi

Agent Claude Code

Code review specialist for quality/security analysis.

not rated 35k +550 changed 17d ago A 10 tokens original MIT

OWASP/CheatSheetSeries

Agent Claude Code

Duplication and placement reviewer for OWASP cheat sheet changes. Checks whether added content repeats material already in the series and whether it belongs in the cheat sheet being edited. Invoked by /review-cheatsheet-pr.

not rated 34k +157 2d ago A 52 tokens CC-BY-SA-4.0

test-engineer

16

QwenLM/qwen-code

Agent Claude Code needs its repo ✓ vendor

Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…

not rated 28k +72 today A 119 tokens original Apache-2.0

creative-director

17

Donchitos/Claude-Code-Game-Studios

Agent Claude Code

Highest creative authority — vision, tone, aesthetic direction. Use when a decision affects game identity or department leads deadlock.

not rated 26k +241 changed 8d ago A 28 tokens original MIT

i18n-translator

18

slopus/happy

Agent Claude Code

Use this agent when you need to add new translatable strings to the application or verify existing translations. This includes: adding new UI text that needs to be translated, ensuring translations are consistent across all language files, verifying that translations fit the UI context (headers, buttons, multiline…

not rated 24k +77 yesterday A 0 tokens original MIT

issue-analyzer

19

JanDeDobbeleer/oh-my-posh

Agent Claude Code

Investigates a GitHub issue and reports the analysis in the conversation only. Reads the issue, reproduces the reported behavior when possible, and traces the root cause in the code. Never posts to the issue, edits it, or changes labels. Use when someone says "analyze issue #N", "investigate this issue", "look into…

not rated 24k +33 changed 21d ago A 113 tokens original MIT

Forge

20

danielmiessler/LifeOS

Agent Claude Code

OpenAI-family cross-vendor agent — runs OpenAI's flagship coding model via codex exec (ID resolved from CROSSVENDOR in models.ts, never pinned in prose). TWO MODES set by the spawn prompt. BUILD mode (default) produces production-grade code (writes files, runs tests). AUDIT mode (read-only) is the cross-vendor…

not rated 19k +89 1mo ago A 0 tokens original MIT

tester

22

Arindam200/awesome-ai-apps

Agent Claude Code

Tester role definition for /implement-universal. Loaded by the orchestrator at the start of the Tester phase, on logic tickets only. Trusts the SWE phase's happy-path e2e excerpt (does NOT re-run the Make target), runs at most 1 adversarial break path, walks every Acceptance Criterion with concrete evidence, and emits…

not rated 16k +46 9d ago A 99 tokens original MIT

architect

23

spree/spree

Agent Claude Code

You are the architecture planning agent for Spree Commerce.

not rated 16k +8 today A 0 tokens original BSD-3-Clause

architect

24

mindfold-ai/Trellis

Agent Claude Code

Architecture sparring partner for Trellis. Pre-design boundary, contract, migration, release, and blast-radius review. Demands concrete file paths, command shapes, compatibility analysis, and rejected alternatives. NOT an implementer.

not rated 15k +24 9d ago A 46 tokens AGPL-3.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: