Find the best CLAUDE.md, AGENTS.md and Claude skills

One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Worked for most · soon

autonomous-ai Hiding risky files

autonomous-aiSkill

build-a-toy

autonomous-ai/autonomous-workshop/.claude/skills/build-a-toy/SKILL.md

Build a toy from a Design Contract until it conforms - run `workshop wish` as round 0, detect every nonconformance against the contract, and run `workshop fix` rounds until none remain, publishing only the conforming build. Can run unattended - one session launches, watches and diagnoses every attempt, fixes Contract Contradictions at the root and relaunches, resuming from the ledger alone. Use after `design-a-toy` produces a contract, when an existing toy drifted from its contract, or to run or resume a toy's unattended loop.

2124d agoReviewMount

autonomous-aiSkill

design-a-toy

autonomous-ai/autonomous-workshop/.claude/skills/design-a-toy/SKILL.md

Design any physical Workshop toy - a vehicle, a jointed robot, a bone dragon, a puzzle, a game - with an Inventor before any run starts - grill the idea into a frozen spec, draft the Design Contract, generate one reference image per unique geometry plus the assembly, reconcile them with the contract feature by feature, check that everything they show can be printed and that any mechanism can move, then get the human's one visual review before handing off to `build-a-toy`. Use when starting a new toy, or when a previous run drifted from what you wanted.

2124d agoReviewMount

autonomous-aiAGENTS.md

autonomous-workshop / harness

autonomous-ai/autonomous-workshop/harness/AGENTS.md

You are Codex running in a Harness workspace for Workshop: describe a 3D object, get a validated, printable STEP part or assembly. This file is the whole workflow for that; it is the Make stage of Autonomous Workshop on its own, with no Inventor, Wish packet, host gate or shop. - CADSKILLROOT and WORKSHOPPYTHON are set in your environment. Every CAD command is "$WORKSHOPPYTHON" "$CADSKILLROOT/scripts/<tool>". Where a skill says CADSKILLROOT="$(workshop skills path)/cad", skip that line — the variable is already…

2124d agoReviewMount

CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.

CLAUDE.md or AGENTS.md?

CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.

What is a skill?

A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.