Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add hon454/grimoire/plugin install archmageWrote 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/book-binding)<a href="https://agentmods.dev/skills/hon454/grimoire/book-binding"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/book-binding/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/book-binding"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/book-binding.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 | $0.00057 | $0.01038 |
| Opus 5.5 | $0.00023 | $0.00415 |
| Sonnet 5.5 | $0.00011 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
book-binding 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Binding a book
A book is one plugin directory under plugins/ in the grimoire repository. This skill applies inside a checkout of that repository. If you are not in one, tell the user and stop.
1. Scaffold
From the repository root:
node tools/grimoire.mjs new-book book-of-<domain> --description "<one sentence>" [--category "<Codex category>"] [--skill <skill-name>]
The tool creates VERSION (0.1.0), CHANGELOG.md, both manifests, a README.md, and, with --skill, a first skill with its agents/openai.yaml sidecar. It then regenerates both marketplace files. Only archmage may omit the book-of- prefix.
2. Write skills
Each skill lives in skills/<name>/SKILL.md plus skills/<name>/agents/openai.yaml.
- Name the skill after its topic with the shortest name that identifies it (
tdd,adr,code-review). A domain term beats a description of it; a gerund (reviewing-pull-requests) is fine when a verb is needed. Names are kebab-case, at most 4 words, contain no article (a,an,the), and must be unique across every book;checkenforces all four. - Frontmatter may use only
name,description,metadata,license,allowed-tools. Put anything else undermetadata.namemust equal the directory name. - Write the
descriptionas a trigger: "Use when ..." followed by what the skill does. Both harnesses pick skills by this text. - Reference helper scripts through the interpreter (
node scripts/x.mjs), never by bare path. - Do not link to files in other books or outside the plugin root.
- The sidecar needs
interface.display_name,interface.short_description, andpolicy.allow_implicit_invocation(false for skills the user must invoke explicitly).
3. Add a hook (optional)
Put hooks/hooks.json at the plugin root and set "hooks": "./hooks/hooks.json" in .codex-plugin/plugin.json. Use only events both harnesses support (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop, PreCompact, SessionEnd). Write matchers with Claude's tool names (Bash, Edit|Write, Agent); Codex aliases them. Commands look like node "${CLAUDE_PLUGIN_ROOT}/scripts/x.mjs". Scripts are dependency-free Node 20+, read the JSON payload from stdin, and must exit 0 with no output on any internal failure.
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 · 66 lines · 57 tokens per session scan A fc3aaafcabe6
book-binding is a skill published in the GitHub repository hon454/grimoire (0 stars, last pushed 25d ago), licensed MIT. It adds 57 tokens to every session and 1,038 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.
book-binding compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| book-bindinghon454/grimoire | Skill | 0 | 25d ago | MIT | A | 57 | 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 |