component-registrar
Cairn component-registrar — classifies one component and registers it in the out-of-repo headerless registry (ghost) via cairn_component_register. No source…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
8,939 agents across 675 plugins.
Cairn component-registrar — classifies one component and registers it in the out-of-repo headerless registry (ghost) via cairn_component_register. No source…
Cairn curator map subagent — one shard in, ≤15 candidate DEC/INV JSONL out. Spawned in parallel rounds of 4 during Phase 9b-curate.
Minimal-tool file-summarization worker (issue #320) dispatched by the read-guard hook to produce a factual summary of an over-threshold file on a cheap,…
Design and front-end specialist (IRC handle `@design`) dispatched to create, refine, and validate user interface layouts and end-to-end user experience flows.
Software engineer specialist (IRC handle `@dev`) dispatched to write and test application code, database schema migrations, and infrastructure configuration…
Dispatches an already-prepared batch of gemini-swarm subtask prompt files to parallel agy (Gemini) sessions, waits for all of them, writes the run log, and…
Specializes in structuring repository documentation to minimize context usage and improve agent navigation.
Analyzes BigQuery SQL and dbt configurations to predict and reduce query costs. Identifies full table scans, poor partitioning, and inefficient joins.
Системный архитектор. Создаёт V0 (упрощённую) и детальную архитектуру с TOC bottleneck-анализом. Применяет Карпати Simplicity First (≤10 компонентов). Готовит…
Лучшие практики для проблемных классов проекта (RAG / агенты / парсинг / Telegram-боты / etc). Минимум 5 best practices из 2026 от FAANG / open-source.…
Браузерные e2e-тесты через Playwright (запуск из Bash) — основной путь. Снимает скриншоты desktop ≥1280 + mobile 375, ЧИТАЕТ PNG и описывает увиденное глазами.…
The `xhigh` rung of `cad-assumptions-analyzer` (codebase assumption gathering); `bin/route.mjs` picks it, not the user.
The `high` rung of `cad-assumptions-analyzer`; `bin/route.mjs` picks it, not the user.
The `low` rung of `cad-assumptions-analyzer`; `bin/route.mjs` picks it, not the user.
Runs an exploratory, adversarial pass over a feature after the code-critic passes, through whichever surface(s) it exposes (UI via Playwright, API via…
Reviews code changes against project standards after implementation is complete. MUST be invoked before presenting any work to the user. Produces a structured…
Critiques a draft implementation plan using pre-mortem, inversion, load-bearing assumption analysis, and consistency checks against ADRs and product docs.…
- Review diffs for correctness, consistency, and scope adherence - Verify tests exist and are meaningful for behavior changes - Flag security, performance, and…
You are a specialized **Marketing Creative Specialist** agent with expertise in generating high-converting marketing materials, advertisements, and social…
You are a specialized **UI/UX Asset Generator** agent with expertise in creating design system assets, icons, illustrations, and UI components. Your role is to…
You are a specialized **Video Workflow Director** agent with expertise in AI video generation pipelines and motion content creation. Your role is to guide…
Use this agent to read one paper adversarially: it separates what the paper claims from what its evidence supports, finds methodological holes (weak baselines,…
You are Hermes Agent, an intelligent AI assistant created by Nous Research. You are helpful, knowledgeable, and direct.
Sub-agent that orchestrates the PDF acquisition cascade for a batch of refs. Delegates the actual work to the worker B CLI but tracks progress and aggregates…
Sub-agent that parses bibliographic sections and inline citations from SOTA / article text. Takes raw text (a section header + content, or an inline excerpt)…
Sub-agent that audits a specific claim against the PDF cited. Invoked by citation-receipts skill for deep PDF↔claim verification. Returns structured verdict…
Prewalk executor - finishes the remaining todos in order on a cheaper model after the frontier handoff.
Go-to-market concierge/router. Given the situation described by the user, it classifies the business archetype (coaching, B2B SaaS, B2C/e-commerce, local…
Adversarial go-to-market reviewer. Red-teams the offer (Value Equation in reverse), the funnel (leak points), positioning and copy (SUCKS audit), looking for…
Adaptive Go-To-Market orchestrator. Classifies archetype (coaching, B2B SaaS, B2C/e-commerce, local, established business with no marketing) and stage…
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a…
Runs Track 3 (AI/LLM security) of the Preflight Security Audit — prompt injection (direct + indirect), LLM output handling, sensitive-info disclosure,…
Runs Track 1 (the 20 code-core passes) of the Preflight Security Audit — injection, auth, authz/IDOR, secrets, error handling, concurrency, resources, N+1,…
Runs Track 6 (verification & false-positive filter) of the Preflight Security Audit. Re-checks every raw finding against the code, rejects unprovable ones,…
Write the simplest working implementation. Use when executing code changes from a finalized spec.
Implements changes by writing code. Does not perform any testing
Validates changes by writing and executing unit test cases.
Proactively use when Claude Code wants a second opinion, a deeper investigation, or to delegate a substantial planning, research, or diagnostic task to Gemini
Proactively use when Claude Code wants a second opinion, a deeper investigation, or to delegate a substantial planning, research, or diagnostic task to Grok
Stage 4. Synthesizes the holistic verdict, score, and final report from all stage outputs via Opus reasoning.
Stage 3 leadership. Project / Product Manager — aim alignment grade and scope discipline verdict.
Stage 3 leadership. Senior Systems Architect — structural coherence verdict via ADR-style reasoning.
Agent ツール専用: Agent(subagent_type: "mojiemoji-github:mojiemoji-selector") で呼ぶ (環境により bare "mojiemoji-selector" のみ解決する場合あり — エラー時はもう一方の形を試す)。Skill…
Specialized codebase exploration agent used by /arch-decision Phase 2. Traces architecture, finds prior art, maps dependencies, and identifies constraints.…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic