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/listgit 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 | $0.00007 | $0.00792 |
| Opus 5 | $0.00003 | $0.00396 |
| Sonnet 5 | $0.00001 | $0.00158 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
list 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Masque List Command
Display all available masques that can be donned.
Instructions
-
List masques via the
masques-cliCLI — the one authoritative catalog shared by this plugin and the Masques MCP server (PRD v1.2 M7). Do not read the manifests directly; the CLI merges private over bundled for you.Locate the CLI (
$MASQUE): usemasques-cliif onPATH(installed viauv tool install "${CLAUDE_PLUGIN_ROOT}/services/mcp"), otherwiseuv run --project "${CLAUDE_PLUGIN_ROOT}/services/mcp" masques-cli.$MASQUE list --json -
Each entry has
name,version,domain,tagline,has_rubric, andsource(privateorshared). The CLI has already merged the two locations — private wins on a name collision; there is nothing to dedupe.(If the CLI is unavailable, fall back to reading the manifests at
${MASQUES_HOME:-~/.masques}/manifest.yamland${CLAUDE_PLUGIN_ROOT}/personas/manifest.yaml.) -
Check for active masque:
- Read
.claude/masque.session.yamlif it exists - Extract
active.namefrom the YAML - This determines which masque to mark as "(active)"
- If the file doesn't exist or
active.nameis null, no masque is active
- Read
-
Format as a table:
Available Masques: Name Version Domain Source ────────────────────────────────────────────────────────────────────
★ Mirror 0.1.0 masque-creation shared ← start here Nash 0.1.0 architecture [private] Codesmith 0.1.0 systems-programming shared (active) Chartwright 0.1.0 frontend-analytics shared
- Mark the active masque with `(active)` if one is donned
- Show `[private]` for masques from the private manifest
- Show `shared` for masques from the shared manifest
- Always show Mirror first with ★ marker and "← start here" hint (it's the meta-masque for creating others)
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 · 88 lines · 7 tokens per session scan A 634dd244e5c7
list is a command published in the GitHub repository ChrisDBaldwin/Masques (14 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 792 once invoked, about $0.0000 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
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
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
think-expand-options
Break past the obvious option set by reframing the problem, transforming the seed with SCAMPER, and reversing its foundational assumptions, then shortlisting candidates.