Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
zhouguoqing/QianYuan.AIAgenticFramework
Agent Claude Code
Stock analysis roundtable orchestrator. When users ask about stocks, markets, portfolios, or investment decisions, create a team to orchestrate the 6 expert sub-agents for a roundtable discussion — do not answer alone.
panaversity/agentfactory-business-plugins
Agent Claude Code
Compare two outputs WITHOUT knowing which skill produced them.
Agent Claude Code
Core intelligence analyst. Applies structured analytic techniques, performs threat actor profiling, campaign tracking, and produces analytical judgments. The analytical brain of the platform.
kumaran-is/claude-code-onboarding
Agent Claude Code
Transforms one-line product ideas into comprehensive validated feature backlogs with pain points, competitive analysis, and MVP candidates. Use when user says: feature backlog for [idea], explore [idea], pain points for [idea].
Agent Claude Code
Fresh-context adversarial code reviewer that takes a curated brief (commit SHA range, changed files, project context, optional SPEC) and returns triaged findings — dispatched only when the vendor review chain exits 3 because no independent reviewer answered, and always recorded as NOT independent.
Agent Claude Code
The loop's verifier. Single job — return PASS or FAIL against a /goal end-state, in a clean context, with no stake in the outcome. Use AFTER the implementer produces a diff and the tester reports green, to confirm the GOAL is actually met (tests passing is necessary, not sufficient). Read-only on source; runs…
Agent Claude Code
Use this agent to interactively review every recommendation, rule, and checklist item inside a fractional-cto plugin's skills. The agent reads each skill, presents every recommendation to the user one by one, and the user approves, edits, or removes each one. Examples: Context: User wants to review the content of a…
Agent Claude Code
Use when answering a question needs a wide read across someone's Lanes Link context — searching their memory, tasks, files, mail, and issues for the same thing and reporting back what is there. Good for "have I discussed X anywhere", "find everything about this client", "what do we already know about Y". Not for…
Agent Claude Code
Fast read-only codebase exploration that returns compressed findings.
marcoemrich/agentic_coding_lab
Agent Claude Code
Final metric-driven refactoring pass. Runs ONCE after the last green cycle, over the whole production src/. Uses deterministic measurements (ESLint smells, SonarJS cognitive complexity, McCabe cyclomatic complexity) plus APP mass to drive improvements while keeping all tests green. Iterates one change at a time until…
Agent Claude Code
Helps users build and improve automated influencer-marketing workflows, starting from their goals, existing methods, and current request.
Agent Claude Code
C programming expert specializing in systems programming, memory management, and performance. Deep expertise in C99/C11/C17 standards, POSIX compliance, embedded systems, and kernel development. Use PROACTIVELY for C code review, memory safety analysis, or systems programming tasks.
Agent Claude Code
Design, build, debug, and optimize portable WebGPU applications and WGSL render or compute pipelines. Use for simulations, particles, cellular automata, feedback effects, image processing, buffer layout, lifecycle handling, readback, compatibility, or GPU performance.
Agent Claude Code
Deep analysis of a single pillar for agent readiness assessment.
aws-samples/sample-synthetic-document-generator
Agent Claude Code ✓ vendor
LLM grader for behavioral assertions on pocsynth skill evals. Reads a transcript and the eval's expected assertions, emits grading.json per the skill-creator convention.
yzyydev/agentic-coding-structure
Agent Claude Code
Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals. Use PROACTIVELY for API documentation or developer portal creation.
mrlm-xyz/demo-claude-marketplace
Agent Claude Code
Project-scoped backend engineer for orders-api. Knows the order lifecycle rules and the spec-first workflow. Use for implementing or changing handlers, models, and business logic in this service.
yuema137/scientific-eval-environments
Agent Claude Code
Phase-1 metadata-only relevance triage. Scores a batch of candidates on whether they deserve expensive Phase-2 primary-source review. Reads only lightweight metadata.
Agent Claude Code
Use this agent to verify a session's or handoff's factual claims against ground truth (git state, files, and read-only environment/production checks) and against the repo's invariants doc, BEFORE those claims are trusted, logged, or acted on. It catches confabulation — claims that sound done but aren't. Dispatch it at…
Agent Claude Code
Architecture reviewer. OpenAPI-first design, cross-platform consistency, database patterns. Use for architecture decisions.
sfc-gh-dflippo/snowflake-dbt-demo
Agent Claude Code
Deploys local dbt projects to dbt Projects on Snowflake and manages CI/CD pipelines.
Agent Claude Code
Senior software architect and technical PM. Plans features, reviews specs, audits implementations. Does NOT write code.
Agent Claude Code
Owns the Zulip communication and owner-control plane for the current Claude Code session. Use proactively when work should stay synchronized with a Zulip topic.
Agent Claude Code
Memory Bank manager — maintains .memory-bank/ (context, search, note, tasks, actualize). Invoked by /mb context|search|note|tasks|update|done and PreCompact hook.
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: