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 commands/chrisdbaldwin/masques/doffgit clone --depth 1 https://github.com/ChrisDBaldwin/MasquesWhat 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 | $0.00013 | $0.00551 |
| Opus 5 | $0.00006 | $0.00275 |
| Sonnet 5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
doff 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 2d 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.
What it actually says
Doff Masque Command
Remove the active masque and return to baseline.
Instructions
Step 1: Read Session File
Read .claude/masque.session.yaml to check current state.
Step 2: Check State and Update
If file doesn't exist or active.name is null:
- Report: "No masque is currently active."
- If
previous.nameis set, show: "Last worn: [previous.name]" - Suggest: "Use
/don <name>to adopt a masque." - Stop here.
If active.name has a value (masque is active):
Write updated session file using the Write tool to .claude/masque.session.yaml:
# Auto-managed by masques plugin
active:
name: null
source: null
donned_at: null
previous:
name: <previous-active-name>
source: <previous-active-source>
doffed_at: <current-UTC-timestamp>
Where:
previous.doffed_atis the current UTC timestamp in ISO formatprevious.namepreserves the name of the masque being doffedprevious.sourcepreserves the source for potential re-donning
Step 2b: Clear Spinner Verbs (if applicable)
Check if .claude/settings.local.json exists:
- If the file does not exist, skip this step — there are no spinner verbs to clean up.
- If the file exists but has no
spinnerVerbsfield, skip this step. - If the file exists and contains a
spinnerVerbsfield:- Read the existing settings
- Remove the
spinnerVerbskey - Write the updated JSON (preserving other fields like
permissions) - If the file would be empty or contain only
{}after removal, delete it
This returns the spinner to Claude Code defaults.
Step 3: Confirm
Report: ✓ Doffed [name]. Back to baseline.
Tool Calls Summary
This command requires:
- Read
.claude/masque.session.yaml - Write
.claude/masque.session.yaml(if masque was active) - Read
.claude/settings.local.json(if exists) - Write
.claude/settings.local.json(to remove spinnerVerbs)
Or fewer calls if no masque is active or no settings file exists.
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.
- 2d ago First seen · 72 lines · 13 tokens per session scan A ff7d03317822
doff is a command published in the GitHub repository ChrisDBaldwin/Masques (14 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 551 once invoked, about $0.0001 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 commands, from other repositories
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
review
View your learning progress — quiz scores, weak areas, and what to study next.