Borrowing it
Nothing to install: this file belongs to Jartan-LLC/grimoire. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jartan-LLC/grimoire/main/CLAUDE.mdgit clone --depth 1 https://github.com/Jartan-LLC/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/instructions/jartan-llc/grimoire/claude-md)<a href="https://agentmods.dev/instructions/jartan-llc/grimoire/claude-md"><img src="https://agentmods.dev/badge/instructions/jartan-llc/grimoire/claude-md.svg" alt="Measured on agentmods" 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 | $0.00743 | $0.00743 |
| Opus 5 | $0.00371 | $0.00371 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
grimoire CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grimoire
A Claude Code plugin marketplace. Each plugin lives in plugins/<name>/ with a
.claude-plugin/plugin.json manifest and a mirrored entry in
.claude-plugin/marketplace.json.
Rules
Always
- Pure ASCII in every tracked file. No em-dashes, smart quotes, arrows,
box-drawing, accented letters, or other non-ASCII. Use the ASCII equivalents:
--(em-dash),->/<-/<->(arrows),>=<=!=(comparators),x(times),^2(superscript),...(ellipsis), plain'and"(quotes), and|`-for directory trees. Applies to prose, code fences, JSON descriptions, and hook scripts alike. - Read
README.mdandRELEASING.mdbefore changing plugin structure or versioning - Version lives only in
plugin.json; bump it on any content change underplugins/<name>/(marketplace entries carry noversion-- seeRELEASING.md) - Declare a plugin
dependencyfor every cross-plugin skill an agent loads in its frontmatterskills:(a hard, resolve-or-fail load likegitwise:github-conventions); a prosesee plugin:skillpointer is soft and needs none - Update the affected READMEs and skills alongside any change
- Executable code earns tests by one rule -- pure input, silent-wrong output --
and hook entry points earn a process contract;
CONTRIBUTING.mdholds the rule, the runners, the layout and the CI wiring - Reviewer agents tier findings with the
review-severityskill; agents name their lens and reference skills -- they do not restate a skill's rules (agents = role, skills = knowledge; seeclaudivis:claude-config)
Anti-patterns
- Don't restate a referenced skill's rules or examples inside an agent or command -- point to the skill
- Don't speculate about a fix -- investigate first, then propose
- Don't hardcode derived counts in prose -- they drift silently
Ask first
- Changing a plugin's public surface (command/agent/skill names) or a skill's severity mapping
- Deleting files or removing a plugin or feature
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 · 74 lines · 743 tokens per session scan A 53e949242dc0
grimoire CLAUDE.md is an instructions file published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed today), licensed MIT. It adds 743 tokens to every session, about $0.0037 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.