Masques CLAUDE.md

Masques CLAUDE.md is an instructions file for coding agents from ChrisDBaldwin/Masques. It costs 3,605 tokens per session, scanned A, original, Apache-2.0.

A design for temporary roles that AI agents can put on and remove, like actors wearing masks. Each role combines a way of thinking, relevant situation details, and descriptive information.

In plain words
What is it for?
Use it to define, apply, and remove temporary agent roles while keeping identity separate from knowledge lookup, credentials, and tool access.
Why use it?
It provides one place to define an agent's temporary identity instead of spreading that setup across prompts, tools, permissions, and background information.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/chrisdbaldwin/masques/claude-md
Clone the repo
git clone --depth 1 https://github.com/ChrisDBaldwin/Masques

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 Masques CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chrisdbaldwin/masques/claude-md.svg)](https://agentmods.dev/instructions/chrisdbaldwin/masques/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chrisdbaldwin/masques/claude-md"><img src="https://agentmods.dev/badge/instructions/chrisdbaldwin/masques/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,605 This file is loaded in full into every session.
When invoked 3,605 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03605 $0.03605
Opus 5 $0.01802 $0.01802
Sonnet 5 $0.00721 $0.00721
Haiku 4.5 $0.00361 $0.00361

Measured 4d ago against content hash ff61d8384471, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Masques 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 4d 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 · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 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.

Project Purpose

Masques applies theater's ancient coordination model to AI agents. Just as actors don costumes, adopt roles, and operate within defined boundaries — then step backstage to become themselves again — agents can temporarily assume identities called masques.

The core problem: today agents get configured through scattered mechanisms (system prompts, MCP servers, credentials, knowledge bases, tool permissions). These are disconnected. A masque unifies cognitive identity into a single "become this" operation — one don, one doff, session over.

Masques is "AssumeRole for Agents." A masque is a temporary cognitive identity bundling lens (how to think), context (situational grounding), and attributes (metadata). It's a representation tool that slaps on top of any agent — don, work, doff.

What Masques Own (and Don't)

Masques own cognitive identity — nothing else. Separation of concerns:

Need Masques Who Handles It
Identity & framing Lens + context Masque itself
Knowledge lookup Declares need MCP servers
Credentials Declares need Vault/credential managers
Tool bundles Declares capability Claude Code MCP config
Performance tracking Declares interest Observability (OTEL)

Masque Schema

Every masque is a YAML file with three required fields and three optional fields. The schema is intentionally minimal.

Required Fields

name: string              # Human-readable identifier (minLength: 1)
version: "x.y.z"          # Semantic version (pinned — upgrading is deliberate, not automatic)
lens: |                    # Cognitive framing — the core of the masque
  How to think, how to work, what to refuse.
  This is intent guidance as prose.

Optional Fields

attributes:               # Flexible key-value metadata (additionalProperties: true)
  domain: string          # Primary domain (e.g., "systems-programming")
  tagline: string         # One-line promise (e.g., "every line should teach")
  style: string           # Working style description
  philosophy: string      # Core philosophy
  # Any additional keys are allowed

context: |                # Situational grounding
  Who you're helping. What they value.
  What's the operational environment.

spinnerVerbs:             # Custom activity indicators
  mode: replace           # replace | append | prepend
  verbs:                  # min 1 item
    - "Masque:Verbing"    # e.g., "Codesmith:Forging"

Read the full file on GitHub · 325 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. 4d ago First seen · 325 lines · 3,605 tokens per session scan A ff61d8384471

Subscribe to this mod's changes

Masques CLAUDE.md is an instructions file published in the GitHub repository ChrisDBaldwin/Masques (14 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,605 tokens to every session, about $0.0180 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 2026-08-30.

Related

Other instructions, from other repositories

gangsta AGENTS.md

Instructions for kucherenko/gangsta, covering contributing to gangsta, what this is, what will not be accepted, skill changes and the laws apply to contributors too.

kucherenko/gangsta · 276 tokens

gangsta GEMINI.md

Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.

kucherenko/gangsta · 29 tokens

magi-workflow CLAUDE.md

Instructions for howar31/magi-workflow, covering what this is, slash commands, subagents, project state model and project document tiers.

howar31/magi-workflow · 626 tokens

agent-skills AGENTS.md

AGENTS.md instructions for racastellanosm/agent-skills, covering agents.md, 1. vision & architectural invariants, 2. repository architecture & layout, 3. harness support & installation paths and 4. scripting & tooling guardrails.

racastellanosm/agent-skills · 2,799 tokens

ai-software-architect AGENTS.md

AGENTS.md instructions for codenamev/ai-software-architect, covering agents.md - ai software architect framework, project overview, framework development setup, repository structure and installation for framework development.

codenamev/ai-software-architect · 3,251 tokens

connectors CLAUDE.md

Claude Code instructions for zapier/connectors: Claude Code loads this file automatically. The canonical AI-agent guidance lives in AGENTS.md so that Claude Code, Codex, Cursor, and any other tool following the AGENTS.md convention read the same content.

zapier/connectors · 60 tokens