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
The lane agent pinned to Haiku 5.5 (Alex, 2026-10-08): low effort: file inventories, narrow validation, formatting-only and repetitive checks. A bounded implementation lane in the LangWatch coordinator/lane workflow. Use when spawning work that has a manifest under .claude/manifests/ - the lane edits only its owned…
brycewang-stanford/Auto-Empirical-Research-Skills
Agent Claude Code
Performs iterative QA review of executed scripts. Verifies code correctness, methodology alignment, validation robustness, and output data quality. Creates parallel QA inspection scripts. Invoked by orchestrator after each Stage 5-8 script execution. Also performs QA review of profiling scripts during Data Onboarding…
Agent Claude Code
Use when requirements, an approved design, or a root cause are clear and one scoped, complete implementation is authorized. Do not use for unresolved exploration, product decisions, diagnosis-only work, or review-only requests.
Agent Claude Code ✓ vendor
Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.
Agent Claude Code
Multi-stage pipeline to validate vulnerability findings are real, reachable, and exploitable.
Agent Claude Code
Feature planning, design documentation, AND integration planning.
Pimzino/claude-code-spec-workflow
Agent Claude Code
Design validation specialist. Use PROACTIVELY to validate design documents for technical soundness, completeness, and alignment before user review.
Agent Claude Code ✓ vendor
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
Agent Claude Code
Use this agent to audit qsv code changes for performance regressions and optimization opportunities — wasteful allocations/clones, inefficient iterator and I/O patterns, in-loop regex compilation, and missed parallelism. It reports findings with impact estimates and suggested alternatives but does NOT apply fixes.…
foryourhealth111-pixel/Vibe-Skills
Agent Claude Code needs its repo
Automation scripts and agent helpers for the Digital Brain. Use these scripts for recurring tasks, summaries, and maintenance.
Agent Claude Code
Create custom steering documents for specialized project contexts.
tradermonty/claude-trading-skills
Agent Claude Code
Use this agent when you need to create a comprehensive weekly trading strategy blog post for part-time traders and investors. Examples include:\n\n \nContext: User has just finished generating market analysis reports and wants to compile them into a weekly blog post.\nuser…
wesammustafa/Claude-Code-Everything-You-Need-to-Know
Agent Claude Code
Lists the functions in this project that no test calls, with the file each one is in. Use when the user asks what is untested or where tests are missing.
Agent Claude Code
Clean-room tester that runs one realistic task using only an installed skill as documentation, then reports what it did. Invoked by the /skills:validate command; do not delegate ordinary work to it.
Agent Claude Code
Manages Professor Synapse's shared, agent-tagged memory: recall, capture, cleanup, and filtering by agent.
Agent Claude Code
Core operating contract shared by all DeepScientist quest turns.
KhazP/vibe-coding-prompt-template
Agent Claude Code
Reviews diffs for bugs, regressions, missing tests, and safety issues.
Agent Claude Code
Identifies the breaking changes between two versions of the SAME stack (e.g. .NET Framework 4.8 → .NET 8, Java 8 → 17/21, Spring Boot 2 → 3) that actually bite a given codebase, and drives the ecosystem's migration tooling. Use for same-stack uplifts, where code is preserved and tweaked — not rewritten from intent.…
Agent Claude Code needs its repo ✓ vendor
Full-stack Azure AI Foundry application scaffolder for React + FastAPI + azd projects.
Agent Claude Code
AIOX Data Engineer autônomo. Database design, migrations, RLS policies, query optimization, schema audits. Usa task files reais do AIOX.
Agent Claude Code
Read-only architecture and code-review agent with severity-rated findings and status verdicts.
jeremylongshore/tons-of-skills-marketplace
Agent Claude Code
Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write race, audit epic dependency graphs for cycles and orphans, catch closures whose title overstates what shipped, flag open beads carrying no disposition or a disproven premise, and reconcile bd against its GitHub…
Agent Claude Code
Use for design-system/redesign work on Compozy UI surfaces (web/, packages/ui, packages/site) — implementing approved design specs, prototype-to-production passes, visual polish, and token or component restyles. Execution only; spawn it with an approved scope, never to produce plans.
Agent Claude Code
Stage 5 of the GLM chain. Writes the shot list against the curriculum and dossier. Camera grammar is setcameraorientation / movecamera only. Reference images are visual seeds, never teaching sources.
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: