Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Executes an approved agentmaster-plan plan end to end. Use after accepting a plan at the Plan Ready for Review prompt — "execute the plan", "run the plan", "build it". Dispatches one implementer subagent per conflict-free parallel group, gates on per-task verification, then performs the full frontier code review…
Agent Claude Code
A code-review agent that checks changes against a project's design patterns, ADRs, and recommended practices. ADRs are short records explaining important architecture decisions.
Agent Claude Code needs its repo
Council Pilot — Research specialist. Discovers expert candidates via web search, collects source URLs, evaluates source tier quality, and produces candidate dossiers ready for distillation.
Agent Claude Code
Claude Code plugin development specialist. Knows plugin structure, official docs, and marketplace best practices.
Agent Claude Code
Use when a task requires running the same instruction over many items - classifying, extracting, summarising or rewriting tens to thousands of records. Delegates to a cheap model through the sidequest CLI and returns only a summary, keeping bulk output out of the main context.
Agent Claude Code
Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…
ReviewToolkits/cpython-security-toolkit
Agent Claude Code
Detects file-loading paths that bypass sys.audit() hooks by using open() instead of io.opencode(), and shell-calling paths where validation occurs before template substitution. Invoke when scanning importlib, webbrowser, or venv.
Ingramradical235/anty-framework
Agent Claude Code
KPI tracking, post-execution verification, root cause analysis, cycle detection, retention cohort analysis, unit economics, and anti-pattern detection.
Agent Claude Code
Implement ONE plan phase, serially, inside an already-active fr-isolation workspace, then return a structured result. Dispatch it INTO that workspace, never into a second worktree — fr's worktree already IS this agent's working copy, and a second one strands it on main with the spec and plan invisible and every…
Agent Claude Code
Use for systematic investigation of bugs, test failures, or runtime errors. Reproduces first, then forms 2-3 ranked hypotheses with evidence, investigates code paths and git history, and proposes the minimal fix. Never guesses; never shotgun-debugs. Returns a single report — does not modify code.
Agent Claude Code
Quality check agent for sequant /qa phase. Runs type safety, scope/size, security, and documentation checks on diffs. Use when spawned by the /qa skill to perform parallel or sequential quality checks.
jeroromano/claude-code-orchestration-template
Agent Claude Code
Local code reviewer and the designated reviewer for Codex-authored diffs. Use before any merge whenever the diff was authored by Codex (Codex never reviews its own work) or the code must not leave the machine. For a Claude-authored diff it is the fallback the delegation-protocol skill names - the standard review tries…
Agent Claude Code
"Is this correct?" — Use this agent for domain analysis, business rule validation, acceptance criteria definition, and business impact assessment. Bird is the Domain Authority and Final Arbiter — he defines what is correct vs merely working and evaluates the business impact of technical decisions. Use via /team for…
Agent Claude Code
Use this agent when you need to actively test applications, APIs, infrastructure, or code for exploitable vulnerabilities. This agent thinks like an attacker and finds entry points before real attackers do. It complements the security-master agent through practical attack simulation. This agent should be used…
Agent Claude Code
Expert in AI/ML pipelines, LLM integration, RAG systems, embeddings, and intelligent automation. Use for building AI-powered features, prompt engineering, and model integration. Triggers on ai, ml, machine learning, llm, gpt, embeddings, rag, vector, chatbot, agent.
Agent Claude Code
Deep, sourced web-research engine. Confirms every datum with ≥2 independent sources, extracts verbatim quotes, flags contradictions and unknowns. Output: findings+provenance JSON artifact (written to file) + one-line return. Shared worker for ds-research and ds-brief.
Agent Claude CodeCursor
Expert code quality reviewer for newly created/modified code. Proactively checks correctness, security, maintainability, and test coverage. Use proactively after code changes.
RoninForge/roninforge-kotlin-compose
Agent Claude Code
Reviews Kotlin / Jetpack Compose / Android code for findViewById, setContentView(R.layout), GlobalScope, LiveData + observeAsState, MutableState exposed publicly, force-unwrap !!, lowercase composables, LazyColumn without key, LaunchedEffect(true), Material 2 imports, padding-before-clickable…
Agent Claude Code
Coding agent via Codex CLI. Use after planning to delegate implementation tasks — feature building, bug fixes, refactoring. Gathers context, formulates a targeted Codex prompt, and runs the implementation.
Agent Claude CodeCursor
Analyzes DevExperience history every 10 tasks. Identifies specific tasks needing correction, passes explicit task IDs to FixPlanner. Updates developer-addendum only (never overwrites developer.md).
Agent Claude Code
Delegate to this subagent when you need changeset@2 artifacts produced from a git diff. Input is a git diff, optionally a linked spec@1, and optionally smith's criteriaevidence from the TDD run that produced this diff. A diff spanning multiple independent topics produces one changeset@2 per topic, never one bundled…
Agent Claude Code
Use this agent when you want to eliminate code duplication across your codebase. Examples: Context: User has just written several similar functions and wants to clean up duplication. user: 'I just added these three validation functions that seem really similar' assistant: 'Let me use the code-deduplicator agent to…
Agent Claude Code
Expert code reviewer. Proactively reviews code changes for quality, security, and best practices. Use after implementing features or fixing bugs to ensure code quality.
stepanenkoviktor0110-boop/ai-dev-methodology-codex
Agent Claude Code
Validates task files against task template and task-creator rules. Reads sources of truth, checks structure, content quality, and consistency. Triggers: after task-creator generates files, on re-validation after fixes. Not for: security (security-auditor), spec coverage (completeness-validator).
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: