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.
npx agentmods add instructions/chrisdbaldwin/masques/claude-mdgit clone --depth 1 https://github.com/ChrisDBaldwin/MasquesWrote 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.
[](https://agentmods.dev/instructions/chrisdbaldwin/masques/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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"
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.
- 4d ago First seen · 325 lines · 3,605 tokens per session scan A ff61d8384471
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.
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.
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.
magi-workflow CLAUDE.md
Instructions for howar31/magi-workflow, covering what this is, slash commands, subagents, project state model and project document tiers.
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.
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.
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.