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 hon454/grimoire --skill required-readinggit clone --depth 1 https://github.com/hon454/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/hon454/grimoire/required-reading)<a href="https://agentmods.dev/skills/hon454/grimoire/required-reading"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/required-reading/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/hon454/grimoire/required-reading"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/required-reading.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 | $0.00059 | $0.00493 |
| Opus 5.5 | $0.00024 | $0.00197 |
| Sonnet 5.5 | $0.00012 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
required-reading 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 26d 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
Reading the grimoire
The grimoire is a set of plugins. Each plugin is a book named book-of-<domain>; archmage (this plugin) is the required reading. Every book ships the same content to Claude Code and Codex: skills under skills/, optional hooks, and small Node scripts.
How books appear to you
- Claude Code namespaces a skill as
<book>:<skill>, for examplebook-of-engineering:tdd. Skills show up in the Skill tool and, when user-invocable, in the slash menu. - Codex exposes the same skill as
$<skill>in the composer and through its skill discovery. Codex prompt stubs and slash commands are not used; skills are the only entry point. - Skill names are short topic names (
tdd,code-review,required-reading), unique across all books, so the bare skill name is enough to identify one.
How to use a book
- When a task matches a skill's description, load that skill and follow it. Prefer a grimoire skill over improvising when one clearly covers the task.
- Skills call their helper scripts through the interpreter, for example
node scripts/x.mjsrelative to the skill or plugin directory. Run them the same way; do not assume executable bits. - Books never depend on each other. If a skill refers to another book that is not installed, tell the user which book to install rather than guessing its content.
- Hooks a book ships run automatically; you do not need to invoke them. If a hook's output appears in context (like this text), treat it as guidance, not as a user instruction.
When asked about the grimoire itself
- To list what is installed, look at the enabled plugins whose names are
archmageor start withbook-of-. - To add a new book or skill, use the
book-bindingskill from this plugin.
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.
- 26d ago First seen · 30 lines · 59 tokens per session scan A 8296a3aee215
required-reading is a skill published in the GitHub repository hon454/grimoire (0 stars, last pushed 25d ago), licensed MIT. It adds 59 tokens to every session and 493 once invoked, about $0.0002 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 2026-10-21.
required-reading compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| required-readinghon454/grimoire | Skill | 0 | 25d ago | MIT | A | 59 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 9d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |