Outfit: Instructions file for Claude Code

CLAUDE.md

Outfit CLAUDE.md is an instructions file for Claude Code from MyceliumInc/Outfit. It costs 1,250 tokens per session, scanned A, original, MIT.

Repository instructions for working on Outfit, a tool that turns an agent's identity, abilities, and permissions into rules enforced by its runtime.

In plain words
What is it for?
Use them when building, testing, developing, or changing Outfit, including its command-line tool, registry, and enforcement flow.
Why use it?
They give an agent the project background, correct commands, architecture, and testing requirements needed to make safe changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is MyceliumInc/Outfit's own configuration. It tells Claude Code how to work on Outfit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Outfit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MyceliumInc/Outfit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MyceliumInc/Outfit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MyceliumInc/Outfit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Outfit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/myceliuminc/outfit/claude-md.svg)](https://agentmods.dev/instructions/myceliuminc/outfit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/myceliuminc/outfit/claude-md"><img src="https://agentmods.dev/badge/instructions/myceliuminc/outfit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,250 This file is loaded in full into every session.
When invoked 1,250 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01250 $0.01250
Opus 5 $0.00625 $0.00625
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured 8d ago against content hash b18b97b4bb1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Outfit CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

Outfit turns an agent persona into a contract the runtime enforces, not a prompt it can ignore. An outfit is one declarative YAML/JSON file (identity + capabilities + permissions

  • optional integrations/skills). The package is the @myceliuminc/outfit npm CLI/library.

The public marketplace is outfits.mycelium.markets (the sibling OutfitMarket repo): a Supabase-backed registry of downloadable outfits. It is distinct from the bundled examples/ and the GitHub registry/index.json. outfit add <name> resolves a bare name against the GitHub registry first, then falls back to the marketplace at outfits.mycelium.markets/api/outfit/<name>, which serves the canonical *.outfit.yaml.

Commands

npm run build      # tsc -> dist/ (+ .d.ts), then chmods dist/cli/index.js
npm test           # runs `pretest` (build) then `node --test` over test/
npm run dev        # tsc -w

Tests import from compiled dist/, not src/. Always build before running a single test file:

npm run build && node --test test/scope.test.mjs   # one suite

CI runs npm ci && npm run build && npm test on Node 18, 20, 22. Minimum is Node 18.

Architecture

The codebase is small (~1800 LOC of TS) and split into four layers under src/, mirrored by dist/ and the public barrel src/index.ts:

  • src/spec/ — the portable core. schema.ts (zod) defines the outfit document; ontology.ts is the closed set of capability ids (shell.exec, fs.read/write/list, http.fetch, web.search), each with a ScopeKind (shell/fs/net) and JSON input schema; index.ts is the loader/validator/discovery (loadOutfit, validateSemantics, discoverOutfits, resolveOutfit).
  • src/gateway/ — the enforcement engine. server.ts builds an MCP server that IS the agent's whole tool-world: each capability becomes a gateway tool; each integration is a child MCP server launched and proxied (only allow-listed tools exposed). capabilities.ts holds the per-capability HANDLERS (each scope-checks before acting) and sanitizedEnv. scope.ts holds the three enforcers — assertShellAllowed, assertPathAllowed, assertUrlAllowed — and is the security-critical file.
  • src/adapters/ — per-runtime compilers. Each Adapter has a conformance matrix (routeViaGateway, denyNative, hooks, slashCommands, integrations) and a compile() that emits runtime config. claude-code.ts writes .mcp.json (registers the gateway), .claude/settings.json (denies NATIVE_TOOLS, allows mcp__outfit-<name>__*), and a delimited persona block in CLAUDE.md. openai-agents.ts is experimental. Register new adapters in ADAPTERS in index.ts.
  • src/cli/ — the outfit command (index.ts) and doctor.ts (preflight that checks whether a target's conformance can satisfy the outfit). The use/doff lifecycle is CLI-only; everything else is also exported as a library.

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 84 lines · 1,250 tokens per session scan A b18b97b4bb1f

Subscribe to this mod's changes

Outfit CLAUDE.md is an instructions file published in the GitHub repository MyceliumInc/Outfit (7 stars, last pushed 1mo ago), licensed MIT. It adds 1,250 tokens to every session, about $0.0063 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens