37,042 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
A Chinese-language workflow for exploring requirements, writing implementation plans, and carrying out repeated build-test-commit cycles. TDD means developing with tests as a guide; the description mentions this as part of its loop.
Shiien/research-closure-harness
Skill Claude CodeCodex
Enforce a claim-to-evidence-to-decision workflow for research projects. Use when planning experiments, implementing research code, analyzing results, changing scope, or preparing weekly updates.
Cursor rule Cursor needs its repo
Update plans before PRs; small focused commits; one plan per PR; pre-PR quality gates (API).
Skill Claude CodeCodex
Use when starting Phase 1 of the Beam workflow, or when a new repository needs a plan.md before any scaffolding, AGENTS.md, or technical spec work begins.
Skill Codex
Plan or revise experience-design readiness for a UI-bearing SDD Change. Use /sdd-design --plan after Change planning to converge unresolved flow, responsive, component/state, accessibility, or visual direction before implementation, and /sdd-design --revise when candidate-bound implementation, review, comparison, or…
Skill Claude Code
Checklist for adding a new public module or sub-package to console-toolkit.
Rito-w/claude-code-best-practice-zh
Command Claude Code
Execute phased implementation with validation gates.
Plugin Claude Code
Bundles 1 skill · 0 tokens together
Discipline rules for long-running agent tasks — recurring loops and run-until-done goals. Checkpoint to .loopgoal/state.json, isolate each iteration in a fresh subagent, and write an explicit exit condition.
SylvainChabaud/spec-to-code-factory
Skill Claude Code
Phase MODEL - Génère specs + ADR + rules.
impactcrew/dont-be-a-sloperator
Skill Claude Code
Structured 4-phase workflow for non-trivial tasks. Enforces Understand, Plan, Execute, Verify phases with quality gates.
q0821/cross-exchange-arbitrage-bot
Command Claude Code
Generate a custom checklist for the current feature based on user requirements.
Plugin Claude Code
Bundles 19 skills, 6 agents · 1,109 tokens together
Lightweight development workflow with plan/run/fresh pattern, git workflow integration, PR feedback, and autonomous execution. Optimized for efficiency - minimal hooks, on-demand skills, direct execution.
gongxuanzhang/shengsheng-skill
Skill Claude CodeCodex
A guided discussion for analysing review feedback after a proposal has been assessed. It helps separate useful, unclear, or unreasonable comments before producing a revised proposal or response.
Agent Claude Code
An agent named pfc from the HanLi-Chainsea/han-agents project. Its description identifies it as a task coordinator and mentions databases, responsibilities, execution modes, and workflows.
evgeny-birch/spec-driven-development-skill
Skill Claude Code
Use this skill when the user wants to create, update, or decompose a product specification. A spec is a triplet of documents — epic.md (what and why), tasks.md (work breakdown), plan.md (execution order). Project-agnostic; drop this skill folder into any repo. Invoke when the user says things like "let's write a…
Skill Claude CodeCodex
Use when a plan, spec, design doc, brainstorm, or walkthrough needs review before anyone implements it — especially when it may be over-engineered, over-abstracted, or scoped past a lean MVP. Triggers include "review this plan", "is this over-engineered", "is this too much for an MVP", "sanity check this design"…
Skill Codex
use this skill when coordinating complex multi-step or multi-agent work through an autonomous durable kanban dispatch protocol. use it when a user gives only an idea and expects the model to infer product requirements, ux flows, architecture, task decomposition, implementation, review, trace logs, and final results…
Plugin Claude Code
Bundles 4 skills · 64 tokens together
ALMAS-inspired autonomous multi-agent SDLC framework. From task to production.
Skill Claude CodeCodex
Establish disk-backed repository context by reading ASI documentation entrypoints and recording a scoped context digest. Produces onboarding artifacts only (no kickoff, no plan, no execution).
Plugin Claude Code
Bundles 21 skills · 1,617 tokens together
Opinionated workflow skills. Hard gates, not suggestions. Spec through blueprint, implementation, verification, and shipping -- the skills refuse to let you skip steps.
kesslerio/coding-agent-openclaw-skill
Skill Claude Code
Implementation/review workflow for approved plans. Route ACP-first, then CLI fallback. Use after explicit APPROVE.
Skill Codex
A skill that turns a request, product requirements document, Feishu or Lark document, competitor analysis, notes, or vague product idea into a concise Markdown product requirements document. A PRD explains what should be built and can guide a coding agent.
Plugin Claude Code
Bundles 1 skill, 5 commands · 151 tokens together
Adaptive clinical interview — binary yes/no questions before coding, outputs PLAN.md. Differential diagnosis for software requirements.
Plugin Claude Code
Bundles 3 commands, 1 agent · 270 tokens together
Advisor Strategy for Claude Code — use Opus-level thinking from Sonnet/Haiku sessions at critical decision points, without switching models.
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: