Building agents

38,442 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.

skillassay

5378

rakib-nyc/skillassay

Skill Claude CodeCodex

Audits AI coding-agent context. Measures always-on context-window cost of CLAUDE.md, AGENTS.md and Agent Skills, and reports skills that will not load, stale path references, redundant instructions and duplicate skill names. Use when the user asks to audit, measure or reduce context cost, check whether a skill is…

not rated 2 1mo ago A 93 tokens original Apache-2.0

mcp-code-exec

5379

AlexFischman/mcp-skill-creator-agency

Command Claude CodeCursor needs its repo

Your task is to convert an MCP server into the Code Execution Pattern described in Anthropic's blog post. This pattern enables progressive disclosure of tools, reducing token usage by up to 98% compared to loading all tools upfront.

not rated 2 10mo ago A 0 tokens original MIT

cc-forge

5380

A-Director/cc-forge

Plugin Claude Code

Bundles 15 commands, 4 hooks · 938 tokens together

SDLC framework for Claude Code: Hermes the Conductor, Argus the Monitor, expert personas, structured backlog, dashboard.

not rated 2 3mo ago A tokens not measured

chealth

5381

danielithomas/chealth

Plugin Claude Code

Bundles 1 skill · 22 tokens together

Check CLAUDE.md health against Anthropic best practices.

not rated 2 6mo ago A tokens not measured original MIT

holocron

5382

atuljha23/holocron

Plugin Claude Code

Bundles 11 skills, 24 commands, 14 agents, 6 hooks · 2,057 tokens together

A Jedi council for your codebase: 14 role-specialist agents, 24 domain commands (a11y, perf, QA, security, threat-modeling, SRE, ADR, cost tracking, MCP auditing), 11 skills including token economy, and a SQLite-backed learning crystal that compounds your corrections across sessions.

not rated 2 4mo ago A tokens not measured original MIT

skill-audit

5384

t0ddharris/claude-code-skills

Skill Claude CodeCodex

Audit all available Claude skills across user and project scopes — inventory them, map routing and overlap, score each on efficiency, reliability, clarity, maintainability, learning, currency, and safety, then produce a prioritized report and draft patches. Use when the user asks to audit, review, improve, optimize…

not rated 2 2mo ago A 115 tokens original MIT

analyze-cc-feature

5386

Prajwalsrinvas/claude-code-reverse-engineering

Skill Claude Code

Reverse engineer and analyze a specific feature in Claude Code's source. Use when the user wants to understand how a Claude Code feature works internally, or when asked to analyze Claude Code internals.

not rated 2 2mo ago A 44 tokens original MIT

saas-accelerator

5387

batterfried-philosophy172/Agent-Startup-Skills

Skill Claude CodeCodex

Master orchestrator skill that coordinates a full multi-agent startup pipeline. Triggers on: build SaaS, launch startup, startup accelerator, build product, create MVP, SaaS builder, million dollar startup, build me a business, or using the Startup Factory. Coordinates 8 specialized sub-skills in a gated…

not rated 2 yesterday A 73 tokens copy · 100% MIT

agentic-site-building

5388

divyanshu-iitian/agent-website-design-skills

Skill Codex

Design, implement, or harden an AI website-building agent that turns natural-language requests into scoped code changes with planning, structured edits, deterministic verification, bounded repair, safe previewing, version history, and token-aware model routing.

not rated 2 27d ago A 51 tokens original MIT

orchestrator

5389

noelpuig/claude-explains

Agent Claude Code needs its repo

Coordinates the full video generation pipeline. Use as main session agent for multi-chapter video projects.

not rated 2 3mo ago A 23 tokens original MIT

claude-wayfinder

5390

glitchwerks/claude-wayfinder

Plugin Claude Code

Bundles 5 skills, 6 hooks · 658 tokens together

Helps Claude make deterministic, auditable choices about which agent and skills to use for a given task — replacing prose-scanning agent/skill selection with a typed scoring kernel.

not rated 2 today A tokens not measured original MIT

Aidress-ai/aidress-skill-find-verified-flight-booking-agent

Skill Claude CodeCodex

Find a Verified Flight Booking Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for travel agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

not rated 2 2mo ago A 62 tokens copy · 86% MIT

mcp-server-evaluations

5392

mcp-com-ai/mcp-server-evaluations-skills

Skill Claude Code

Test MCP servers for quality and reliability. Verify tool functionality, test error handling, generate tests, and assess response quality with no dependencies other than curl. Use this when validating MCP server implementations, testing OpenAPI-to-MCP conversions, or assessing API tool quality.

not rated 2 7mo ago A 59 tokens original MIT

evolve-skill

5393

taneltaluri/evolve-skill

Skill Claude CodeCodex

Evolve Skill: measurement-first skill optimizer. Evaluates SKILL.md files against an anchored 9-dimension rubric, validates that the rubric itself is stable (test-retest), optimizes with a hill-climbing loop that only accepts improvements larger than measurement noise, protects against overfitting with train/holdout…

not rated 2 5mo ago A 128 tokens original MIT

moradin

5394

CloseTheLoops/moradin

Plugin Claude Code

Bundles 14 skills · 586 tokens together

The Forge: a guided pipeline from idea to shipped product — calibrated process, verified research, clickable decisions, checked builds, honest kill lines — plus a cross-project memory that compounds. Cross-tool (Claude Code, Cursor, Codex, Gemini, Hermes).

not rated 2 1mo ago A tokens not measured original MIT

lattice

5396

sectersion/lattice

Plugin Claude Code

Bundles 2 skills · 211 tokens together

Skill for talking to the Lattice agent-threading server ("Slack for agents"): register an identity, post/reply to threads, and poll notifications instead of ad-hoc file polling.

not rated 2 12d ago A tokens not measured original MIT

skill-creator

5397

ssdeanx/AI-Skills

Skill Claude CodeCodex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

not rated 2 8mo ago A 45 tokens

skill-check

5399

JckJhns/skill-check

Skill Claude Code

Comprehensive testing and validation of Claude skills. Use this skill whenever the user wants to test, validate, audit, or quality-check a skill — whether they say "test my skill", "check this skill works", "validate my skill", "run skill-check", or anything similar. Also trigger when the user asks things like "does…

not rated 2 4mo ago A 192 tokens original MIT

sparring

5400

nyxandro/sparring-skill

Skill Claude CodeCodex

Use when the user says "sparring", "run sparring with Claude", "do sparring with Claude", "do sparring with GPT-5", "sparring with Codex", "sparring my plan with Claude", "discuss this approach with Codex", "get a second opinion through sparring", "give me the sparring transcript", "read the long sparring answer", or…

not rated 2 3mo ago A 154 tokens

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: