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 adrgit 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/adr)<a href="https://agentmods.dev/skills/hon454/grimoire/adr"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/adr/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/adr"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/adr.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 | $0.00081 | $0.01304 |
| Opus 5.5 | $0.00032 | $0.00522 |
| Sonnet 5.5 | $0.00016 | $0.00261 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade A, and why
adr 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture decision records
An ADR records one decision, why it was made, what was rejected and what it costs. It is written once and never edited afterwards; a changed mind gets a new record that supersedes the old one. The value is in recording that a decision was made and why, so the next reader does not "fix" something that was deliberate.
1. Decide whether this deserves a record
Offer an ADR only when all three hold:
- Hard to reverse. Changing your mind later costs real effort.
- Surprising without context. A future reader of the code would ask "why on earth did they do it this way?"
- A real trade-off. There were genuine alternatives and one was picked for specific reasons.
If any is missing, skip it. An easily reversed decision will simply be reversed; an unsurprising one raises no question; a decision with no alternative records nothing beyond "we did the obvious thing". Minor conventions (naming, formatting, defaults) go in the project's contributor guide, not in an ADR.
What qualifies: architectural shape (monorepo, event-sourced writes), integration patterns between parts, technology choices that carry lock-in (database, message bus, auth provider, deployment target), boundary and ownership decisions (the explicit "no"s are as valuable as the "yes"es), deliberate deviations from the obvious path, constraints invisible in the code (compliance, partner contracts), and rejected alternatives whose rejection is not obvious.
When the decision came out of a discussion in the current session, say so and offer to record it. Do not write one silently.
2. Find the decision log
Look, in this order, for an existing log: docs/decisions/, docs/adr/, doc/adr/, adr/, or any directory whose files are named NNNN-*.md with a status in their frontmatter. Match whatever the repository already does: its directory, its numbering, its template (a template.md or README.md in that directory wins over this skill), and its language. If the repository writes its documents in a language other than English, write the ADR in that language.
What ships with it
2 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.
- 26d ago First seen · 69 lines · 81 tokens per session scan A 0bcd98f9e98f
adr is a skill published in the GitHub repository hon454/grimoire (0 stars, last pushed 25d ago), licensed MIT. It adds 81 tokens to every session and 1,304 once invoked, about $0.0003 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.
adr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adrhon454/grimoire | Skill | 0 | 25d ago | MIT | A | 81 | 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 |