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 grim-usagegit 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/grim-usage)<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/grim-usage"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/grim-usage/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/grim-usage"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/grim-usage.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 | $0.00154 | $0.03427 |
| Opus 5.5 | $0.00062 | $0.01371 |
| Sonnet 5.5 | $0.00031 | $0.00685 |
| Haiku 4.5 | $0.00015 | $0.00343 |
Grade A, and why
grim-usage 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grim Usage
Grimoire (binary: grim) is a package manager for AI-agent configuration.
It distributes six artifact kinds — skills, rules, agents,
MCP servers, hooks, and bundles — through any standard OCI
registry (GHCR, Docker Hub, a private Distribution), with lockfile-pinned
installs into a growing fleet of AI clients plus a vendor-neutral agents
target. The current names are listed in
references/registries.md; the
set grows every minor release, so read it there rather than assuming. An
MCP server artifact installs by registering an entry in each client's
native MCP config file (never as a file of its own); uninstall removes
only that entry, never the file.
Not every client can host every kind: a skill is the one kind every client hosts, but a rule needs a per-file scoping surface, an agent needs a shipped file format, and an MCP server needs a config file grim can splice — and many clients lack one or more of those. Where a client cannot faithfully host a kind, grim warns and skips it, writing zero files. Most of the fleet declines rules, but agents are hosted by a majority of clients (12 of the 18 supported clients), and the skills-only clients mostly write no MCP config either — except Cline (global scope only), Droid, and Warp. The authoritative per-client support matrix is the [Client Compatibility][clients] docs page — trust it over this summary, and check it rather than assuming.
Hooks are experimental and off by default. The kind publishes, resolves, locks, installs, and reports today; arming is gated twice:
options.experimental.hooksmust be true (falseunless you set it, config-only — no environment variable overrides it) and the workspace must have consented (grim hook allow,grim add, or an accepted prompt; global scope is always consented).grim installandgrim updatenever grant consent. So adding a hook gives you a declaration, a lock pin, and a materialized payload tree, and nothing fires until both gates clear.grim hook listis the surface for inspecting what you have. Full picture: references/consume.md; a hook that stays silent: references/troubleshooting.md.
Two consequences of that shape are worth knowing before your first
install. When nothing is detected, grim targets the generic agents
client — one copy into the shared .agents/skills pool — rather than
writing a directory for every client it knows about; a lock holding only
rules, agents, or MCP servers then has nowhere to go and exits 78. And
a client that reads that shared pool can be moved into it deliberately with
options.vendors.<name>.shared_skills. Both in
references/registries.md.
What ships with it
7 files 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.
- 2d ago Changed · +18 lines · +23 tokens per session 8e0a4e99fa33
- 7d ago Changed · +1 lines 440c944f011e
- 21d ago Changed · +17 lines · +7 tokens per session aec6b6594666
- 28d ago Changed · +2 lines · +2 tokens per session 473f413e2d97
- 29d ago Changed 8b8b4a41b69c
- 1mo ago Changed · +1 lines 75a8ddab194e
- 1mo ago First seen · 168 lines · 122 tokens per session scan A baa9510b0474
grim-usage is a skill published in the GitHub repository grimoire-rs/grimoire (14 stars, last pushed today), licensed Apache-2.0. It adds 154 tokens to every session and 3,427 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
vuln-scanner
Audit trending repos for real security vulnerabilities and disclose responsibly - scan and route findings (PVR / dependency PR), re-submit queued advisories, and send armed email disclosures.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
autoresearch
Evolve a skill by generating variations, evaluating them, and updating the best version.