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-authoringgit 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-authoring)<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/grim-authoring"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/grim-authoring.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.03035 |
| Opus 5 | $0.00069 | $0.01517 |
| Sonnet 5 | $0.00028 | $0.00607 |
| Haiku 4.5 | $0.00014 | $0.00303 |
Grade A, and why
grim-authoring 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 7d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grim Artifact Authoring
Grim publishes five artifact kinds to OCI registries. Each has its own
source shape, frontmatter schema, and validation gates. This root file
holds the invariants that apply to every kind; per-kind depth lives in
references/, loaded via the routing table below.
The Five Kinds
grim build and grim release infer the kind from the path — except
agents (always --kind agent, or they silently pack as rules) and MCP
servers (always --kind mcp, or the .toml is treated as a bundle).
| Kind | Source shape | Inference | Installs as |
|---|---|---|---|
| Skill | Directory with a SKILL.md index |
directory → skill | Directory tree under the client's skills/ dir |
| Rule | Single .md file |
.md → rule |
rules/<name>.md, per-client transform |
| Rule + support dir | <name>.md + sibling <name>/ dir |
sibling dir auto-discovered | Index file + rules/<name>/… side by side |
| Agent | Single .md, frontmatter required |
never — --kind agent mandatory |
One agent file per client, per-client render |
| MCP server | .toml descriptor with a [server] table |
never — --kind mcp mandatory |
Entry in each client's MCP config file, per-client render |
| Bundle | .toml member list |
.toml → bundle |
Never materializes — expands to its members |
Which Clients Host Which Kind
Grim installs into a growing set of clients, and not every client can host every kind — decide this before you author, because it changes what you write. Treat the [enforced matrix][clients] as authoritative; the summary below is a planning aid that the next client can age:
- Skills are the universal kind — no client declines them, which is why a skill is the portable choice. One scope caveat: OpenClaw is global-scope-only, so a project install for it writes nothing.
- Rules are native for Claude Code, Copilot, Cursor, and Kiro; degraded for OpenCode and Junie (the file installs and grim restates the scope as prose in the body, but nothing enforces it); and declined by everyone else — grim warns, skips, and writes no file. Most of the fleet cannot scope instructions: when the audience is broad, a skill reaches clients a rule never will.
- Agents install for Claude Code, OpenCode, Copilot, Codex, Cursor, Gemini, and Antigravity. Every other client declines them.
- MCP servers register for the clients that ship a config file grim
can splice — Claude, OpenCode, Copilot, Codex, Cursor, Kiro, Junie,
Gemini, Zed, Amp, and Antigravity. Only Claude accepts the
wstransport and the[server.oauth]block; every other client skips such a descriptor with a warning. The skills-only clients (and the vendor-neutralagentstarget) write no MCP config at all.
What ships with it
9 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.
- references/agent-spec.md 7.3 KB
- references/bootstrap-existing-repo.md 6.4 KB
- references/bundle-spec.md 5.9 KB
- references/mcp-spec.md 7.9 KB
- references/release-checklist.md 14 KB
- references/rule-spec.md 8.6 KB
- references/skill-spec.md 9.1 KB
- references/updating.md 3.1 KB
- references/vendor-metadata.md 7.6 KB
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.
- 7d ago First seen · 210 lines · 138 tokens per session scan A 0d4fecc7b115
grim-authoring is a skill published in the GitHub repository grimoire-rs/grimoire (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 138 tokens to every session and 3,035 once invoked, about $0.0007 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 skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
projection-patterns
Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.