808 tagged agentic-coding, measured the same way as everything else here.
Browse within: agentic-workflow 132agentic-engineering 82ai-workflows 80ai-coding-agent 72Multi-Agent 71claude-code-skills 67ai-coding-assistant 63agent-orchestration 62claude-code-subagents 57gemini-cli 48github-copilot 47gofer 47cline 44ai-code-review 36
Agent
Product-vision guardian — audits work against the project's stated direction, detects drift (feature creep / architecture / priority), asks A/B/C clarifying questions, keeps vision docs current, and recommends which other agents to run. NOT a code reviewer; a direction validator. Run at the start of major features…
Agent
Accessibility audit of an implemented UI surface — assistive-tech labels, hit-target size, contrast ratios, text scaling, reduced-motion. Read-only; produces an S/A/B/C/D/F per-dimension report where a missing label or sub-threshold hit target blocks ship regardless of visual grade. Run after a screen is…
Agent
Review a diff with no memory of writing it. Use before merging, or when asked to check work. Reports findings only; it cannot edit.
CassetteTapeCrackle/claude-starters
Agent
Use to survey existing solutions before building — what exists, how they solve it, their strengths/gaps/pricing, and where an opening is. Read-only research; cites sources.
CassetteTapeCrackle/claude-starters
Agent
Use to audit a project's dependencies — pinned versions, committed lockfiles, and known-vulnerability exposure — across ecosystems (Cargo, npm/pnpm, pip/uv, go modules, etc.). Read-only; it reports, it does not modify.
CassetteTapeCrackle/claude-starters
Agent
Use to scaffold a new language/stack starter for the claude-starters system. Follows the repo's existing pattern (CLAUDE.md + manifest.json + content test), producing lean, agent-friendly rules rather than dogma.
Agent
Blind adversarial reviewer dispatched by fable-review — attacks a real artifact through one named lens and returns findings. Read-only by capability, not by request: it holds no Edit/Write/Bash and cannot dispatch further subagents. Not for general work; the dispatcher supplies the lens and the scope.
martin-francois/symphony-trello
Agent
The order of work for any task: what to read first, how to scope a change, how to verify, and how to commit and open pull requests. Topic-specific rules live in the pages linked under References.
martin-francois/symphony-trello
Agent
Agent "maintaining-agent-docs" from martin-francois/symphony-trello, covering maintaining agent docs, progressive disclosure contract, what may be added to agents.md (allowlist), what must not be added to agents.md (denylist) and where to put new guidance (decision tree).
martin-francois/symphony-trello
Agent
This file is the source of truth for the structure and maintenance approach.
Agent
MyACE project-specific orchestrator. Extends the global orchestrator with MyACE-specific subagents, commands, and conventions for the three-component architecture (backend FastAPI, frontend React/Vite, CLI Typer).
Agent
Curates what goes into an agent's context window across a long-running or multi-agent task — deciding what stays, what gets summarized, and what gets dropped.
Agent
Designs and iterates on prompts, system instructions, and agent/skill copy — owns defining what "better" means for a change before making it, not after.
Agent
Dispatch a clinical-safety lens over any health, wellness, or medical output before it reaches a user - when the founder says "is this safe to tell a patient", "check this health claim", "what is the harm if we are wrong here", or is shipping anything that touches a dose, a symptom, a diagnosis, or a clinical…
Agent
Dispatch a sceptical-customer lens to play the buyer who has heard every pitch and refuses to be flattered - when the founder says "would anyone buy this", "they said they loved it", "everyone I interviewed is interested", "pressure-test my pitch", or is about to build off interview enthusiasm. Plays the buyer who has…
Agent
Dispatch a moat lens to interrogate whether anything actually compounds - when the founder says "is my data a moat", "what stops a giant cloning this", "we collect a lot of data", "is this defensible", "design my data flywheel", or is about to call a data lake a moat. Applies store-the-proprietary…
Agent Claude Code
Tracks, validates, and monitors assumptions throughout the pipeline, flagging disproven assumptions that require spec revision.
Agent Claude Code
Analyzes pipeline logs to generate business-facing metrics including velocity, cost per feature, quality trends, and scope creep indicators.
Agent Claude Code
Cross-references spec, plan, and tasks to verify alignment before implementation.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Master0fFate/parallax-claudecode
Agent
Independently audits one completed Horizon worker attempt against its acceptance criteria and observed receipt. Use only after Horizon observes the worker receipt.
Master0fFate/parallax-claudecode
Agent
Use for large, multi-feature goals that benefit from durable planning, delegated implementation, autonomous decisions, retry-bounded evaluation, and a final audit.