Agent Claude Code
A senior architect that reviews code for structural integrity, scalability, and long-term maintainability. Use for a deep-dive analysis of a project or module's design.
not rated 598
+1 3mo ago A 37 tokens
bug-finder
02Agent Claude Code
A software detective that proactively hunts for logical errors, race conditions, and unhandled edge cases in code. Use to find hidden bugs in a specific function or module.
not rated 598
+1 3mo ago A 37 tokens
Agent Claude Code
Use this agent when C source files (.c, .h) have been created or modified, especially code involving memory allocation, file descriptors, sockets, cryptographic operations, credential handling, or external input parsing. Should be triggered on every code change to C files to catch resource lifecycle bugs and security…
not rated 598
+1 3mo ago A 492 tokens
Agent Claude Code
Use this agent when any code change modifies a public interface, contract, or format that other parts of the system consume. This includes changes to: environment variable names/semantics, JSON/HTTP API response shapes, state file formats, CLI flags, header file exports (struct fields, function signatures)…
not rated 598
+1 3mo ago A 515 tokens
Agent Claude Code
Use this agent to implement documentation changes based on review findings. This agent takes review recommendations and systematically implements the required updates, fixes, and new documentation.
not rated 598
+1 3mo ago A 35 tokens
doc-reviewer
06Agent Claude Code
Use this agent to analyze and review documentation state, identifying gaps, outdated content, and quality issues. This agent only reviews and reports - it does not make changes.
not rated 598
+1 3mo ago A 37 tokens
Agent Claude Code
Use this agent when the user needs to cherry-pick commits across a repository with submodules, following a structured two-part workflow (Analysis & Planning, then Execution). This agent should be invoked when:\n\n \nContext: User wants to move a feature branch's commits to another branch in a repository with…
not rated 598
+1 3mo ago A 0 tokens
Agent Claude Code
Use this agent when the user explicitly requests to create GitHub issues, or when during a conversation specific bugs, problems, remaining work items, or future tasks are identified that should be tracked separately. This agent should be used proactively when:\n\n \nContext: During a code review, the user discovers a…
not rated 598
+1 3mo ago A 0 tokens
Agent Claude Code
A specialist in diagnosing and fixing performance issues in desktop apps. Use when the app feels slow, uses too much memory, or has a long startup time.
not rated 598
+1 3mo ago A 35 tokens
Agent Claude Code
Use this agent after implementing features, refactoring code, or making significant modifications. Focuses on ensuring changes are fully integrated, old code is properly removed, and no technical debt is introduced. Does NOT review functional correctness, test quality, or documentation - only structural integrity and…
not rated 598
+1 3mo ago A 66 tokens
test-runner
11Agent Claude Code
Use this agent when the user requests to run tests, execute the test suite, check if tests pass, verify test results, or validate code changes through testing. This agent should be used proactively after significant code changes or when the user asks about test status.\n\nExamples:\n- User: "Run the tests for this…
not rated 598
+1 3mo ago A 0 tokens
Agent Claude Code
An expert in desktop UI/UX and accessibility. Use when building or refining user interfaces to ensure they meet platform standards and are accessible.
not rated 598
+1 3mo ago A 34 tokens
arch-review
13Command Claude Code
Review architecture of specified path(s), or staged/unstaged git changes.
not rated 598
+1 3mo ago A 0 tokens
arewedone
14Command Claude Code
Run structural completeness review.
not rated 598
+1 3mo ago A 4 tokens
bugs
15Command Claude Code
Use bug-finder agent to hunt for logical errors and potential runtime issues.
not rated 598
+1 3mo ago A 14 tokens
commit
16Command Claude Code
Create intelligent conventional commits based on conversation context. If there is not enough context in the conversation, assume the user wants to commit the current working tree changes. Use logical judgement to determine which files should be included in the commit.
not rated 598
+1 3mo ago A 0 tokens
docs
17Command Claude Code
Complete documentation workflow: review, implement fixes, and commit changes.
not rated 598
+1 3mo ago A 0 tokens
perf-check
18Command Claude Code
Check performance of specified files, or of staged/unstaged git changes.
not rated 598
+1 3mo ago A 0 tokens
Command Claude Code
Run all standard review agents in parallel on current changes.
not rated 598
+1 3mo ago A 10 tokens
ui-review
20Command Claude Code
Review UI/UX of specified files, or of staged/unstaged git changes.
not rated 598
+1 3mo ago A 0 tokens
gemini-agent
21Skill Claude CodeCodex
Delegate tasks to Gemini CLI as an agent. Use when the user wants to offload token-heavy work to Gemini, get a second opinion from a different model, or run Gemini with a custom system prompt. Triggers include "use Gemini to review X", "ask Gemini to Y", "run Gemini on Z", "delegate to Gemini", "have Gemini check X".
not rated 598
+1 3mo ago A 78 tokens
Skill Claude CodeCodex
Synthesize the current conversation into a single, self-contained /goal prompt that Claude Code can run to continue the agreed-upon work autonomously — so the user never has to hand-summarize a long discussion into a goal directive. Use when the user and Claude have converged on what to do next and the user wants to…
not rated 598
+1 3mo ago A 136 tokens
Skill Claude CodeCodex
Safely prune stale git worktrees and local branches left over from past sessions, deleting only those with no unique work so no commit is ever lost. Use when a repo has accumulated worktrees and branches over many sessions and needs cleanup. Triggers include "prune worktrees", "delete stale branches", "clean up git…
not rated 598
+1 3mo ago A 90 tokens
Skill Claude CodeCodex
End-to-end orchestrator for multi-task parallel work. Phase 1 (setup) gathers code intelligence, analyzes merge-conflict risks, groups tasks into maximally-parallel phases, writes enriched self-contained agent prompts, and generates PLAN.md + STATE.md. Phase 2 (execution) dispatches Opus agents in worktrees with a…
not rated 598
+1 3mo ago A 136 tokens
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: