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.
git clone --depth 1 https://github.com/noirdoc-ai/mask-claude-pluginWrote 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/commands/noirdoc-ai/mask-claude-plugin/noirdoc-allow)<a href="https://agentmods.dev/commands/noirdoc-ai/mask-claude-plugin/noirdoc-allow"><img src="https://agentmods.dev/badge/commands/noirdoc-ai/mask-claude-plugin/noirdoc-allow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/noirdoc-ai/mask-claude-plugin/noirdoc-allow"><img src="https://agentmods.dev/badge/commands/noirdoc-ai/mask-claude-plugin/noirdoc-allow.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.00510 |
| Opus 5 | $0.00009 | $0.00255 |
| Sonnet 5 | $0.00004 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
noirdoc-allow 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.
What it actually says
Adding $ARGUMENTS to the noirdoc.guard.allowlist in .noirdoc/config.toml disables the guardrail for that path.
The guard hook denies any in-session edit of .noirdoc/config.toml (Edit/Write/Bash) — otherwise a prompt-injected turn could disable the guard on its own. Allowlisting therefore happens out of band.
Steps:
-
Confirm with the user in plain language:
"Adding
$ARGUMENTSto the allowlist means the guard hook will let Claude read that path without redaction. Only do this for files you're sure contain no personal data. Proceed?" -
If the user confirms, use the
Readtool on.noirdoc/config.tomlto show them the currentallowlist. Then tell them to edit the file themselves — in a regular terminal, in their editor, or with the snippet below — and append$ARGUMENTSto the array:[noirdoc.guard] allowlist = [ # …existing entries… "$ARGUMENTS", ]Example one-liner they can paste into a terminal (skips if already present):
python3 -c ' import tomllib, pathlib p = pathlib.Path(".noirdoc/config.toml") c = tomllib.loads(p.read_text()) a = c.setdefault("noirdoc", {}).setdefault("guard", {}).setdefault("allowlist", []) if "$ARGUMENTS" not in a: a.append("$ARGUMENTS") # round-trip via a minimal TOML rewrite — adjust by hand if you keep comments lines = p.read_text().splitlines() # ...edit by hand if the file has comments you want to keep 'In practice the cleanest path is: open
.noirdoc/config.tomlin your editor and add the line by hand. -
After they confirm they've made the change, run
/noirdoc-statusto verify the new allowlist is in effect.
If the user does not confirm, or .noirdoc/config.toml doesn't exist (run /noirdoc-setup first), stop without taking any action.
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.
- 8d ago First seen · 47 lines · 18 tokens per session scan A f16c7a90ccdd
noirdoc-allow is a command published in the GitHub repository noirdoc-ai/mask-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 510 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 2026-08-31.
Other commands, from other repositories
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.
verify-math
Verify a self-authored mathematical result end to end by routing claims across adversarial review, numerical falsification, symbolic or CAS checks, and Lean, then aggregating one report. Use when a theorem, proposition, conjecture, or paper-wide mathematical argument needs the appropriate combination of verification…
synthesise-reviews
Deduplicate and reconcile multiple completed review reports into one prioritised revision plan with conflicts and dependencies made explicit. Use when parallel reviewers have returned findings that need a single action sequence. Not for running the reviews; use $review-cluster.
triage
Triage ServiceNow incidents — list open incidents, assess priority, investigate a specific INC, or analyze trends.