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 skills add grimoire-rs/grimoire --skill nox-reviewgit clone --depth 1 https://github.com/grimoire-rs/grimoireWrote 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/skills/grimoire-rs/grimoire/nox-review)<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/nox-review"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/nox-review/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/skills/grimoire-rs/grimoire/nox-review"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/nox-review.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 | $0.00086 | $0.03336 |
| Opus 5.5 | $0.00034 | $0.01334 |
| Sonnet 5.5 | $0.00017 | $0.00667 |
| Haiku 4.5 | $0.00009 | $0.00334 |
Grade A, and why
nox-review 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 11d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nox-review — adversarial review under a second harness
What this does
nox reviews a change under an AI harness other than the one that wrote it.
It builds a pair of synthetic commits with every instruction file, hook and
agent-config file removed from the tree, checks the target out into an
ephemeral git worktree it owns, and spawns the reviewing harness there under a
minimal environment. The reviewer sees the change — not the repository's
instructions, and not its hooks.
What the minimal environment does and does not withhold. It is an
allowlist: everything outside it is dropped, credential-shaped names are
dropped on top of that, and nox forwards no credential value of its own. But
the allowlist deliberately carries HOME and each harness's own
config-directory variables, because that is the only way the reviewing harness
authenticates at all — it reaches its own credential store exactly as it does
when you run it yourself. "The reviewer cannot reach my secrets" is not a claim
this makes.
Writes and network reach are held per harness, and how strongly differs.
os is the operating system's, and is established only once nox has probed
that the sandbox really holds; harness is the harness's own primitive,
visible in the resolved argv; attested is self-declared and never probed — a
claim, not evidence. Every run stamps what it established on its containment:
line; weigh the findings against that line rather than against a level you
assumed.
nox changes nothing in the repository under review. It does append one line per
run to a local call log — calls.jsonl under $XDG_STATE_HOME/nox, by default
~/.local/state/nox/ — carrying the timestamp, the harness, the model, the
duration, the outcome, the cost and a count of warnings. Never findings, never
harness output.
Scopes
--scope code-diff reviews a branch diff against a base (--base <ref>), or
the working tree when you pass no --base.
--scope plan-artifact reviews a single file — a plan, an ADR, a spec — named
by --path <file>.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago Changed e16140c95aba
- 20d ago Changed 7fc7b23bcdf6
- 1mo ago First seen · 250 lines · 86 tokens per session scan A ee3c3a3e88c6
nox-review is a skill published in the GitHub repository grimoire-rs/grimoire (14 stars, last pushed 6d ago), licensed Apache-2.0. It adds 86 tokens to every session and 3,336 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-08.
Other skills, from other repositories
pr-review
Review open PRs two ways - default is a per-PR deep review with severity-tagged findings, inline comments, and a verdict; --survey runs a risk-tiered triage digest of what's safe to merge first.
feedback-builder
Point Aeon at a service's /feedback endpoint - pull what agents reported (bugs, missing features), triage and cluster it, then build the best accepted request as a PR for a human to approve.
pr-triage
First-touch triage for external pull requests - verdict, label, and a welcoming comment within minutes of open.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
pr-description
Write or update a GitHub PR description as a short, skimmable list of key points grounded in the diff and real verification. Use when opening a PR or editing its description.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…