Building agents

38,215 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.

semaphore-mcp

1227

cloin/semaphore-mcp

MCP server Claude CodeCodexCursor +2

Model Context Protocol (MCP) server for SemaphoreUI automation. Runs locally from the semaphore-mcp Python package.

not rated 80 +1 24d ago A tokens not measured AGPL-3.0

claude-harness

1229

panayiotism/claude-harness

Plugin Claude Code

Bundles 6 skills, 1 agent, 8 hooks · 382 tokens together

Long-running agent harness with 5-layer memory architecture, GitHub integration via gh CLI, autonomous batch processing with a dedicated implementer subagent, Agent Teams with ATDD, quality-gate hooks, and 6 Agent Skills.

not rated 79 1mo ago A tokens not measured original MIT

sverklo-explore

1230

sverklo/sverklo

Agent Claude Code

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

not rated 79 1mo ago A 96 tokens original MIT

setup-wizard

1231

JKHeadley/instar

Skill Claude Code

Interactive conversational setup wizard for instar. Walks users through initial configuration and identity bootstrapping conversationally.

not rated 79 yesterday A ✓ AI review SkillSpector: warn 26 tokens original MIT

skill-optimizer

1232

fastxyz/skill-optimizer

Plugin Claude Code

Bundles 2 skills · 75 tokens together

Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs.

not rated 79 +2 3mo ago A tokens not measured original MIT

gf-agent-contributor

1233

brucemcpherson/gas-fakes

Skill Claude CodeCodex needs its repo

Guide for creating or contributing modular knowledge to the gfagent skill. Use this when a user wants to teach gfagent a new trick or document an Apps Script parity oddity.

not rated 79 2d ago A SkillSpector: pass 40 tokens original MIT

mastra-skills

1234

mastra-ai/skills

Plugin Claude Code

Bundles 2 skills · 137 tokens together

Mastra framework and Factory supervisor skills with progressive disclosure for development, API inspection, troubleshooting, and operations.

not rated 79 +1 changed 4d ago A tokens not measured

meta-harness

1236

001TMF/harness-forge

Skill Claude CodeCodex

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto…

not rated 78 3mo ago A 217 tokens original MIT

npc-mind

1238

LudicDynamics/WorldLines

Agent Claude Code

A private-mind agent for one named character at a time. It reacts only from that character’s personal point of view and must be given the character’s ID.

not rated 78 +5 3d ago A 101 tokens

agy

1239

simplybychris/antigravity-plugin-cc

Plugin Claude Code

Bundles 1 skill, 7 commands, 1 agent · 225 tokens together

Use the Google Antigravity CLI (agy) from inside Claude Code — slash commands /agy:setup, /agy:ask, /agy:delegate, /agy:research, /agy:review, /agy:image, /agy:help. Supports per-call model selection via --model.

not rated 78 3mo ago A tokens not measured original MIT

agent-council

1240

magnus919/agent-skills

Skill Claude CodeCodex

Run a structured multi-agent debate by spawning a panel of expert agents on any question, with convergence-aware iteration and typed synthesis output via the agent-council CLI. Use when a decision has genuine tradeoffs, high stakes, or hidden assumptions worth adversarial collaboration, or when confidence diagnostics…

not rated 78 +3 3d ago A SkillSpector: warn 129 tokens original MIT

skillsmith-agent

1241

smith-horn/skillsmith

Skill Claude CodeCodex

Delegate your agent-skill lifecycle: keep skills current, audit and clean up your inventory, and vet skills before you install them. The Skillsmith Agent diagnoses in full for free, proposes a batched fix plan, and changes files only with your per-changeset approval, with one-step undo. Triggers: "ask the Skillsmith…

not rated 78 changed 2d ago A 100 tokens

core

1242

crafter-station/skill-kit

Skill Claude CodeCodex

Canonical skillkit workflow served by the installed CLI. Read before auditing skill packs or analyzing skill usage, context cost, conflicts, coverage, and token burn.

not rated 77 +1 changed 9d ago A 33 tokens

dominion-flow

1243

ThierryN/fire-flow

Plugin Claude Code

Bundles 5 skills, 51 commands, 13 agents · 1,298 tokens together

Research-backed orchestration for Claude Code. Structured workflow from idea to production with parallel execution, session memory, 70-point validation, autonomous mode, and adversarial review. 51 commands, 15 agents across 7 departments.

not rated 77 1mo ago A tokens not measured original MIT

skill-creation

1244

emanueleielo/ciana-parrot

Skill Claude CodeCodex

Guide for creating, updating, and managing skills. Use when: you need to extend your capabilities with a new skill, or the user asks you to create one. Skills are persistent Markdown instruction modules auto-discovered at runtime.

not rated 77 4mo ago A 49 tokens original MIT

agent-starter

1245

sneg55/agent-starter

Plugin Claude Code

Bundles 8 skills, 5 hooks · 303 tokens together

Skills, hooks, templates, and engineering guides for bootstrapping AI-agent-friendly projects, with a per-project self-improvement loop.

not rated 77 +1 changed 10d ago A tokens not measured original MIT

cc-workflow-ai-editor

1246

bottobot/touchdesigner-mcp-server

Skill Claude CodeCodex

AI workflow editor for CC Workflow Studio. Create and edit visual AI agent workflows through interactive conversation using MCP tools (getworkflowschema, getcurrentworkflow, applyworkflow). Use when the user wants to create a new workflow, modify an existing workflow, or edit the workflow canvas in CC Workflow Studio…

not rated 77 25d ago A SkillSpector: pass 74 tokens original MIT

orbit

1247

simota/agent-skills

Skill Claude CodeCodex

Running autonomous loops for nexus-autoloop. Generates script sets from goals, designs operation contracts, audits live loops, and recovers state — runners that complete reliably.

not rated 77 +1 changed today A SkillSpector: warn 35 tokens original MIT

rolecraft

1248

rolecraft-sh/rolecraft

Skill Claude CodeCodex

Install AI agent skills as roles & behaviors from any source — local folder, GitHub, GitLab, SSH git URL. Zero-dependency CLI with 87 agent targets (27 verified).

not rated 77 2d ago A 41 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: