Building agents commands

CyrilLeMat/temper-skills

Command Claude Code

Temper a skill.md into a test suite + deterministic decision tree via the adversarial subagent loop (a directory gets the ranked library audit).

arsenelupin14/THEMIS

Command Claude Code

Use the Themis protocol from this repository.

ldilov/harness-forge

Command Claude Code

Use when an agent should autonomously escalate a hard task into a recursive session, prefer Typed RLM first, and only fall back to bounded structured analysis when needed.

jazz-max/ruflo-hub

Command Claude Code

Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.

SiluPanda/codex-agent-loop

Command Claude CodeCodex

Run a bounded, Claude-Code-style coding loop with onboarding helpers like --doctor, --demo, and shorthand budgets like 10m.

crcresearch/llm-wiki-memory-template

Command Claude Code

Consult federated agent(s) via the agent-comms ask primitive (clone-and-invoke).

SpillwaveSolutions/grading-claude-agents-md-agentic-skill

Command Claude Code

Grade CLAUDE.md and AGENTS.md files against best practices.

clarsbyte/washedmcp

Command Claude Code

Install an MCP server with automatic API key prompting.

The-Artificer-of-Ciphers-LLC/skills-from-the-artificer

Command Claude Code

Engineering Workflow Directive — Feature Implementation & Integrations. Implements a feature-request epic or single feature issue, Memtrace-first. Graph-backed research, recorded-decision + known-defect gauntlets, epic detection with seam-validated multi-PR decomposition (stacked or Fleet-parallel), then a…

natea/fitfinder

Command Claude Code

Structure Claude Code's approach to complex development tasks for maximum efficiency.

MarieLynneBlock/arcanum-artifex

Command Claude CodeGitHub Copilot

Review one agent for standalone packaging, instruction quality, contradictory guidance, resource correctness, and current best practices.

mrgnfndr-dr/mind-clone

Command Claude Code

Ask a mind-clone of an author — advice, or their likely view on a topic.

obeone/claude-skills

Command Claude Code needs its repo

Edit the project autoMode block in plain language. The agent interprets the request, builds a proposal, runs critique + hash gate, and writes atomically to .claude/settings.local.json.

MohamedAbdallah-14/awesome-claude-hooks

Command Claude Code

Scaffold a new hook conforming to the awesome-claude-hooks contract.

erniker/understudy

Command Claude Code

Explain what understudy is, its capabilities, available roles, commands, and how to use the team.

sarkarsaurabh27/agent-loop-learning

Command Claude Code

Goal: execute on issues found. Apply concrete, benchmark-backed improvements to the agent in this repo.

airmcp-com/mcp-standards

Command Claude Code

Continuously improve coordination through neural network learning.

davet47/hashloom

Command Claude Code

Draft hashloom contracts (status: inferred) for the feature's stable seams and register them for gating.

codeverbojan/claude-code-kickstart

Command Claude Code

Analyze the codebase and extract real patterns into patterns.md.

fentas/cuite

Command Claude Code

Team-based parallel execution with agent teams coordination.

Ertinox7711/SGRR-AGI-V2

Command Claude Code

Analyze your real sessions + project folders and propose concrete, prioritized upgrades to the SGRR AGI V2 rig — report only, applies nothing.

hackermanishackerman/claude-skills-vault

Command Claude Code

Production-grade feature planning with dual-AI validation (Claude + Gemini).

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.

dawiddutoit/custom-claude

Command Claude Code

Guided end-to-end plugin creation workflow with component design, implementation, and validation.