Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
rongxinzy/claude-code-best-practice-zh
Agent Claude Code
A requirements-analysis agent that turns an informal feature request into structured goals, requirements, constraints, risks, and questions. It prepares this information for later planning.
PratikHotchandani22/claude-ollama-agents
Agent Claude Code
Use this agent for ALL code writing tasks: generating new code, fixing bugs, refactoring existing code, and implementing features. Delegates actual code generation to a local Ollama model (zero Claude token cost for the heavy lifting). Use whenever more than 5 lines of code need to be written or modified.
Agent Claude Code
Self-improvement sub-agent for the portable workflow harness. Reads the corpus (commands/, agents/, harness/, hooks/) before editing, makes exactly one targeted change per invocation, never touches preferences.md, commits its edit in the harness repo (and pushes harness main when committing on main, keeping the public…
Agent Claude Code
Decides a single pipeline gate during an autonomous run — /autopilot, or /sprint adjudicating its gate queue (autonomy.gates set to assisted or auto). Reads the gate's evidence packet and returns one verdict — APPROVE, REWORK, or HALT — with a confidence score and cited evidence. Read-only on source; writes only its…
Agent Claude CodeCursor
Reviews PRDs against approved product decisions, supporting evidence, and downstream delivery needs. Use after PRD drafting or when PRD review is requested.
Agent Claude Code
Execution agent. Checks consumers before changing. Builds and verifies per task. Follows existing patterns exactly.
Agent Claude Code
Google Cloud Platform infrastructure specialist for cloud-native applications. When to use: (1) When designing GCP architecture for web/mobile backend services (2) When provisioning infrastructure with Terraform or gcloud CLI (3) When setting up CI/CD pipelines with Cloud Build (4) When configuring networking…
Mohamed-El-Sharqawy/agent-tutor
Agent Claude Code
Creates precise, Obsidian-compatible Mermaid diagrams for learning notes. Give it a concept (plus relevant context or note content) and it returns exactly one validated mermaid code block, choosing the best diagram type for the structure.
Agent Claude Code
Python's creator and Benevolent Dictator For Life (1991–2018), now BDFL emeritus and a member of the Steering Council. Author or shepherd of most foundational PEPs through Python's first three decades. Currently focused on the faster-cpython project at Microsoft.
sjarmak/coding-agent-workflows
Agent Claude Code
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Agent Claude Code
stub for the scaffolded example.
nvdigitalsolutions/mcp-ai-wpoos
Agent Claude Code
Scaffolds and edits NV oOS tool classes under includes/tools/ (Base) and addons/pro/includes/tools/ (Pro), respecting the Base-vs-Pro split and the registry pattern.
MatrixFounder/Agentic-development
Agent Claude Code
Perform full OWASP security audit (Top 10, taint analysis, dependency CVE check, smart-contract patterns, LLM-specific attacks) on code changes or a target directory. Spawn for pre-merge or pre-release audits. Distinct from critic-security which is the lightweight parallel critic for /vdd-multi.
YujxZJCN/teaching-skills-codex
Agent Claude Code
Custodian of coursepassport.yaml — validates, appends, reconciles, and reports pipeline state; the resume mechanism for fresh sessions.
Agent Claude Code
Guardian of redbar's design and the 7 rules in AGENTS.md. Invoke BEFORE changes that risk an invariant (a new effect boundary, a new public field, the way a language is added, an output format), to review architectural drift, to write or review specs in docs/superpowers/specs/, and when a design decision must be made…
Agent Claude Code
Per-node coordination role the node identity DELEGATES to. Holds node context, claims work in the register BEFORE edits, and spawns delivery agents to execute. Not the default session -- claude-pmoves launches the node identity itself with full tools; PMOVESDEFAULTAGENT=node-steward still runs this role as the main…
w00fx/spec-anchored-agentic-development
Agent Claude Code
Authoring general-code review and cleanup agent. Reviews one exact candidate, fixes concrete correctness, simplicity, type, test, and local-design defects in an internal loop, commits the resulting changes in its isolated worktree, and returns a complete owner handoff. It is a hardener, not an approval gate.
Agent Claude Code needs its repo
Audits the agent system itself — agent definitions, skill files, routing, command flows, and session artifacts — to find weaknesses (token waste, duplicate load paths, stale references, role-boundary drift, dead skills, portability hazards) and emit a prioritized improvement report. Run after any change under…
indranilbanerjee/neels-plugins
Agent Claude Code
Adapts social media copy per platform — character limits, hashtags, CTAs, tone shifts, and bilingual formatting. Handles cross-posting adaptation.
Agent Claude Code
Reads a finished piece cold before it's published (an essay, a word study, an etymology post, a Bible study, a quote-heavy post) and checks every original-language form, gloss, reconstructed root, quotation and reference against a real source. It reports what passes, what fails and what it couldn't check. It never…
Agent Claude Code
Independent UI review of a pull request's proof recordings. Receives only screenshots and extracted video frames (contact sheets plus full-size frames) and optional reference screens, never the code or the runner's notes, and returns a defect list with severity, frame and what is wrong. The pinqloq task runner calls…
Agent Claude Code
Independent reviewer of rendered Power BI report pages. Reads only the page screenshots (PNG), the request or spec, and the PBIR folder, then returns PASS or FAIL per page and per visual against a fixed checklist. Use after every screenshot step of the PBIR edit loop (pbi-report-layer-pbir), or whenever someone asks…
Agent Claude Code
Goldfish reviewer (vibe-goldfish): checks every claim a document makes about the existing code against the actual code. Read-only, zero context.
Agent Claude Code
A backend implementation agent for building approved non-interface components such as APIs, services, databases, workers, command-line tools, and libraries.
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: