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 strategy framework for finding new markets where competition matters less. It helps compare what customers value and redesign the balance of benefits and costs.
Plugin Claude Code
Bundles 39 skills, 47 commands, 39 agents, 2 hooks · 2,721 tokens together
AI Development Methodology: 6 phase gates from discovery to ship, 28 skills, 39 review sub-agents, and WHY-first enforcement hooks. Stops code being written before the problem is understood.
Skill Claude Code
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.
arcayne/agentic-delivery-playbook
Plugin Claude Code
Bundles 3 skills, 5 agents · 260 tokens together
Direct/Controlled delivery kernel for Claude Code: explicit-invoke skill plus Sonnet worker, Opus reviewer, and read-only explorer agents.
Skill Claude CodeCodex
Guide a human operator through a multi-step operation (production change, migration, backfill, load or outage test, incident fix) as a live runbook canvas in Katashiro — the human runs every command; you write the runbook, point at the next step, check each pasted output against what was expected, and keep the…
Skill Claude CodeCodex
Run a subagent-first structured improve-verify loop in OpenCode. Activate with /autoresearch or specialized modes like /autoresearch:plan, /autoresearch:debug, /autoresearch:fix, /autoresearch:learn, /autoresearch:predict, /autoresearch:scenario, /autoresearch:security, /autoresearch:ship. Supports recursive…
Plugin Claude Code
Bundles 3 commands · 75 tokens together
Turn a plan into GitHub milestones + issues — from your repo, an existing MD file, or a rough idea. Always previews and asks before it creates anything.
Plugin Claude Code
Bundles 1 skill, 1 command, 14 agents · 560 tokens together
A user-friendly adaptive second-opinion skill for Claude Code. For important decisions, plans, strategies, proposals, architecture, and recommendations: frame the real goal, verify decision-critical evidence, pressure-test the biggest risk, compare alternatives, and stop when more reasoning will not change the action.
Skill Claude CodeCodex
Plan a project by breaking goals into concrete tasks with priorities and deadlines. Use when the user says "let's plan", "break this down", "I need to figure out how to", "help me plan", or when starting a new project.
Skill Claude CodeCodex
Execute tasks in the active plan under .plan/active/. Writes concrete Output and Handoff for each task and archives the plan once terminal.
Plugin Claude Code
Bundles 6 skills · 342 tokens together
Skills for discovering and closing knowledge gaps across the dev lifecycle, from Thariq's 'Know Your Unknowns'.
GreatMark/fable-field-guide-skills
Plugin Claude Code
Bundles 9 skills, 2 hooks · 1,389 tokens together
Eight agent skills plus a field-guide router for finding your unknowns before, during, and after implementation, derived from Thariq's 'A Field Guide to Fable: Finding Your Unknowns'.
Skill Codex
Create a new source-grounded decision brief in Feishu/Lark, Word/docx, Markdown or self-contained HTML; default to source format. Include a reader-fit Pyramid opening, one editable or auditable visual covering at least 80% of value-weighted non-appendix claims, and a key-question table. Use for 3080-brief, 3080 brief…
omril321/claude-plan-visualizer
Plugin Claude Code
Bundles 1 agent · 88 tokens together
Generates self-contained HTML visualizations from markdown implementation plans showing BEFORE/AFTER architecture, diff-marked components, key decisions, and risks.
Plugin Claude Code
Bundles 2 skills, 4 commands, 6 agents, 4 hooks, 2 MCP servers · 1,027 tokens together
Claude Context First — a context-first, spec-driven, wave-parallel development workflow. Keeps CLAUDE.md/.claude specs continuously fresh and grounds every design decision in best practices fetched from Context7 and Microsoft Learn.
Plugin Claude Code
Bundles 5 skills · 347 tokens together
Thin state layer for agent-driven development. A feature is a brief plus a git branch; status (planned, in-progress, verified, landed) is derived from git, never stored. Five skills: yolo-brief, yolo-status, yolo-next, yolo-verify, yolo-init.
RDEL-Group/compound-knowledge-work
Plugin Claude Code
Bundles 5 skills, 7 agents, 1 hook · 625 tokens together
Compound Knowledge Work — phased execution with compounding institutional knowledge for RFPs, training, SOPs, strategy docs, and any knowledge work.
alphaparkinc/mirofish-ai-skill
Skill Claude CodeCodex
Scenario Prediction Engine — Orchestrates AI-driven scenario simulation and forecasting using Mirofish's graph-building pipeline to predict outcomes, model ripple effects, and generate structured insight reports.
alphaparkinc/genpark-accio-csuite-manager
Skill Claude CodeCodex
Multi-Agent C-Suite Orchestrator. Manages a team of specialized AI agents (CMO, CTO, CFO, etc.) for cohesive business strategy.
Agent Claude Code
MUST BE USED PROACTIVELY. Universal read-only explorer agent. Combines jrag graph navigation (call chains, service boundaries, routes, impact analysis, FQN resolution) with broad file-system search (grep, glob, excerpt reading). Use for any exploration task: locating code, tracing dependencies, finding patterns…
Skill Claude CodeCodex
Explain an approach or build approved work.
rgranet/project-coding-companion-skill
Skill Claude CodeCodex
ALWAYS invoke this skill before starting ANY coding task. This skill evaluates the user's coding prompt for completeness, coaches them to clarify vague requests before any code is written, then guides implementation through a structured workflow. You MUST consult this skill whenever the user mentions code, a…
MCP server Claude CodeCodexCursor +2
Deterministic tech stack recommendations, audits, and project estimates. No hallucinations. Runs locally from the @stacksfinder/mcp-server npm package. Needs 1 environment variable to run.
dmitryprg-ai/cursor-develop-autorules
Cursor rule Cursor
A Cursor rule defining a step-by-step process for judging task complexity, planning the work, and carrying it out.
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: