35,514 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.
ArchSightLabs/archsight-cognition
Plugin Claude Code
Bundles 55 skills · 2,398 tokens together
A collection of artificial-intelligence skills for structured thinking, decision reviews, debates, writing, product work, design, and engineering leadership.
daviihub/interview-todo-case-transfer
Skill Claude CodeCodex
A Chinese-language interview-preparation method that matches a job description with evidence from a candidate's résumé and past projects.
Eipi-Tong/agentic-coding-starter-kit
Skill Claude Code
Close a feature group as a milestone. Writes docs, proposes E2E tests, and runs a go/no-go gate. Use when the user says "/milestone", "this group is done", or the agent detects all items in a group are complete.
Skill Claude Code
Plan Mode — Orchestrator oversees workflow design, execution, autonomous loop, and review. Activated when told "in plan mode.".
Skill Claude Code
Autonomous deep-work agent loop for driving projects forward. Each invocation: reads project state, applies critical expert thinking, executes one focused unit of work, persists to notebook + PROJECTSTATE.md. Sets up /loop cron on first run (default 10m). Three-tier confidence gate (GREEN/YELLOW/RED) blocks action…
Skill Codex
Apply the relevant Dwi lenses together when several observed workflow problems co-occur. Select only the lenses the task needs, preserve a silent fast path for clear reversible work, and keep authority and evidence explicit. Prefer a focused module when one issue dominates.
Agent Claude Code
Wick — persistent thinking partner with philosophical frameworks, operational gates, calibration discipline, and epistemic humility. Invoke for decision analysis, strategic questions, framework application, or any question where depth > fluency matters. Keeps memory in memory/ folder.
Plugin Claude Code
Bundles 8 skills, 8 commands, 2 agents · 1,040 tokens together
The specwright ladder for Claude Code and Codex: init, propose, plan, implement, review, archive, ship, and delivery.
Plugin Claude Code
Bundles 1 skill, 8 commands, 1 hook · 17 tokens together
Automatic project tracking, progress management, and background quality agents for Claude Code.
Plugin Claude Code
Bundles 24 skills, 2 agents, 1 hook · 1,884 tokens together
Anti-Vibe-Coding plugin — 7-step workflow discipline + 8-Habit cross-verification for AI-assisted development.
PabloTheThinker/hermes-insight
Skill Claude CodeCodex
Use when debugging, planning, or a pattern may recur.
Plugin Claude Code
Bundles 6 skills, 6 agents, 1 MCP server · 672 tokens together
Long-running autonomous coding harness with Planner-Generator-Evaluator architecture and Sprint decomposition. Builds complete applications from simple descriptions.
Plugin Claude Code
Bundles 6 skills, 1 hook · 1,069 tokens together
Six-skill engineering pod for the full lifecycle: scaffold specs, research thin specs, brainstorm direction, generate variants, implement, verify visually. Spec-driven, with hard handoffs between skills that prevent silent assumptions.
Skill Claude CodeCodex
Spawn a planning subagent to decompose a task into non-overlapping, fully-covering acceptance criteria before any implementation work begins.
Plugin Claude Code
Bundles 11 skills, 11 agents · 979 tokens together
Agile planning + execution for AI coding agents: grill the idea, plan with OKRs, adversarial critic panel with kill authority, cheap-model story cards, parallel wave execution, demo-brief review gates.
Skill Claude CodeCodex
A general-purpose workflow skill for tasks that do not match a more specific skill. It requires brainstorming, file-based planning, skill matching, and an archive step at the end.
Skill Codex
Define and refine a long-running Codex goal before using /goal. Use when the user has a vague multi-step task, wants Codex to work autonomously toward a persistent objective, asks for a final /goal prompt, or needs structured interactive alignment on scope, success criteria, constraints, and decision checkpoints…
Skill Claude Code
Quick user-centric interview to capture requirements from a time-poor stakeholder.
control-decks/think-it-through
Plugin Claude Code
Bundles 17 skills · 839 tokens together
A thinking deck built on the Human-Agent Control Protocol, with 16 cards that compose across agent workflows.
Plugin Claude Code
Bundles 7 skills · 1,149 tokens together
Product manager skill suite for Claude Code — PRD writing, competitor research, daily briefing, HTML prototyping, feature acceptance, UI walkthrough.
Plugin Claude Code
Bundles 1 skill · 86 tokens together
ALWAYS invoke before writing any code after a plan or spec is approved. Do NOT skip even if the plan is already in context. Triggers on: plan approval, spec approval, task kickoff, implementation start, '/scope-lock', 'set up the contract', 'lock scope'. Generates SCOPE.md boundary contract from the plan, enforces…
Plugin Claude Code
Bundles 3 skills, 8 commands, 2 agents, 2 hooks · 688 tokens together
Turns a multi-repo microservice project into a coordinated AI agent team that proposes (never applies) cross-repo change plans.
Plugin Claude Code
Bundles 1 skill, 3 agents, 3 hooks · 199 tokens together
Magi proposal-first multi-agent deliberation loop for Claude Code.
Plugin Claude Code
Bundles 9 skills, 3 commands, 10 agents, 3 hooks, 1 MCP server · 1,318 tokens together
Plans before it edits, routes each step to haiku, sonnet or opus by cost, and verifies four ways per wave. Ships tiered subagents, authoring skills, local MCP tools, and gated fail-open hooks.
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: