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.

skillpack

5401

nordicnode/skillpack

Cursor rule Cursor

Generate and verify the agent-distribution layer for any OSS project.

not rated 2 yesterday A 0 tokens original MIT

octowiz

5402

raelli/octowiz

Plugin Claude Code

Bundles 3 skills, 4 hooks · 334 tokens together

Octowiz Engineering Agent — Claude Code adapter, A2A bridge, and execution coordinator.

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

respawn

5403

ruben-sj/respawn-skill

Skill Claude CodeCodex

Sets up automatic revival of this session after Claude's 5-hour usage limit is hit — waits until the window reopens, notifies the user, and resumes automatically unless the user cancels within a configurable grace window (default 5 min). Use when the user says "respawn", "set up respawn", "auto-resume", "revive this…

not rated 2 1mo ago A 141 tokens original MIT

clawlabor

5404

Reinforce-Omega/clawlabor-skill

Skill Claude CodeCodex

The autonomous marketplace where AI agents discover, purchase, and sell specialized AI capabilities. Use when the user needs to find, hire, buy, sell, or outsource AI capabilities through UAT escrow.

not rated 2 2mo ago B 43 tokens AGPL-3.0

shimo4228/skill-stocktake

Plugin Claude Code

Audit installed Claude skills for quality (Keep/Improve/Update/Retire/Merge) — inline Glob inventory + holistic single-context evaluation, no scan scripts.

not rated 2 16d ago A tokens not measured original MIT

slash-it

5411

fayis672/slash-IT

Plugin Claude Code

Bundles 5 skills · 99 tokens together

Turn the message you just typed in Claude Code into a reusable slash command — verbatim, optimised, reshaped, or parameterized — and list what you've saved.

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

rikai

5412

spellsaif/rikai

Skill Claude CodeCodex

Turn any codebase into a deeply interactive, single-page HTML learning experience for vibe coders — people who build with AI but want to understand what they built. Trigger whenever someone says "explain this codebase," "help me understand this project," "make a course from this repo," "teach me how this code works,"…

not rated 2 5mo ago A 176 tokens original MIT

metis

5414

gitRasheed/metis-skill

Skill Claude Code

Use when an LLM is doing non-trivial coding work, including implementing features, fixing bugs, refactoring, designing APIs or module boundaries, writing tests, reviewing code, or preparing to commit. Guides the model toward plain data, top-down API design, simple control flow, SOLID without ceremony, boundary parsing…

not rated 2 27d ago A 108 tokens original MIT

expertlens-lite

5415

Ashutosh2M/ExpertLens-Lite

Skill Claude CodeCodex

ExpertLens-Lite forces expert-level reasoning on any task — the compressed, single-companion-file version of ExpertLens. Activates on "deep think", "expert mode", "do it properly", "production ready", "think deeply", "best possible way" (any language), or auto-triggers for creative work, system design, strategy…

not rated 2 1mo ago B 129 tokens original MIT

flywheel

5416

WinterDDo/claude-skill-flywheel

Plugin Claude Code

Bundles 3 skills, 4 hooks · 141 tokens together

Self-improving skill system: makes Claude reliably invoke the right skill every turn and learn from your corrections over time. 100% local plaintext.

not rated 2 3mo ago A tokens not measured original MIT

Aidress-ai/aidress-skill-find-verified-fraud-detection-agent

Skill Claude CodeCodex

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

not rated 2 2mo ago A 63 tokens copy · 86% MIT

second-pass-self-judge

5419

HubWizard/second-pass

Agent Claude Code

Internal subagent for the Second Pass skill. Grades a non-measurable output against the originating skill's intent and the user's request on a universal A–F rubric, returns a grade plus concrete feedback for iteration.

not rated 2 4mo ago A 49 tokens original MIT

Aidress-ai/aidress-skill-find-verified-knowledge-base-search-agent

Skill Claude CodeCodex

Find a Verified Knowledge Base Search Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for customer-support agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

not rated 2 2mo ago A 65 tokens original MIT

claudemd-architect

5421

keskinonur/claudemd-architect

Skill Claude CodeCodex

Generate production-grade CLAUDE.md project reference documents for Claude Code. Use when a user wants to create a CLAUDE.md, project spec, or architectural reference for AI-assisted development. Incorporates LLM reasoning failure mitigations (constraint-based guardrails, concrete examples, verification checkpoints)…

not rated 2 7mo ago A 108 tokens original MIT

skills-curator

5423

captkernel/Skills_Curator

Plugin Claude Code

Bundles 3 skills, 3 commands · 438 tokens together

Intelligence layer for Claude skills. Maintains a trust-rated catalog (curated + GitHub topic search), recommends what fits your project, returns ranked lists with pros, cons and customization advice, persists every decision, and migrates skills across 55 supported agent platforms. Ships in three editions: Lite…

not rated 2 26d ago A tokens not measured original MIT

selfaware

5424

Sorbh/claude-selfaware

Skill Claude Code

Makes Claude aware of its own API usage limits and able to manage them intelligently. Usage is checked automatically by hooks (SessionStart + UserPromptSubmit) that inject a directive when usage gets high; Claude delegates suitable tasks to a Codex sub-agent to conserve tokens, checkpoints work before limits hit, and…

not rated 2 2mo ago A 153 tokens original MIT

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: