grimoire AGENTS.md

A repository instruction file that defines how coding agents should work in the grimoire project. It covers the project's purpose, maintenance rules, commits, branches, manifests, and pull requests.

In plain words
What is it for?
Use it when making changes in the grimoire repository, especially when naming skills, preparing commits or branches, validating JSON manifests, or creating pull requests.
Why use it?
It gives agents one shared set of project-specific rules, reducing inconsistent changes and overlooked review or validation steps.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/hon454/grimoire/agents-md
Clone the repo
git clone --depth 1 https://github.com/hon454/grimoire

Made for: Codex, OpenCode.

Per session 298 This file is loaded in full into every session.
When invoked 298 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00298 $0.00298
Opus 5 $0.00149 $0.00149
Sonnet 5 $0.00060 $0.00060
Haiku 4.5 $0.00030 $0.00030

Measured 2d ago against content hash 5b30a598a4fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grimoire AGENTS.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 2d 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.

AGENTS.md · 33 lines

What it actually says

Grimoire Agent Protocol

This file is the source of truth for Codex agents working in this repository.

Repository Intent

Grimoire is a personal Codex harnessing repository for reusable skills, one primary plugin, hooks, workflow instructions, and tool integrations. Keep the repository practical and source-owned.

Working Rules

  • Prefer small, readable skills over broad catch-all instructions.
  • Keep skill names stable and literal so Codex can trigger them predictably.
  • Do not add roadmap lists or promised future spells until there is a real skill to commit.
  • Use Conventional Commits for commit messages.
  • Choose commit and pull request scopes by the smallest durable responsibility affected by the change, not by the broadest package, repository area, or file path.
  • Use branch names that expose the Conventional Commit type.
  • Verify JSON manifests before committing.

Pull Requests

Before creating or updating a pull request:

  • Read .github/pull_request_template.md.
  • Use the template's current section structure for the PR body.
  • Use a Conventional Commit-style pull request title.
  • Choose the pull request title scope by the smallest durable responsibility affected by the change.
  • Fill in applicable template content with concrete details.
  • Delete template prompts and inapplicable checklist items instead of leaving placeholders behind.

Maintenance Policy

Read docs/maintaining-grimoire.md before changing skills, plugin manifests, repository instructions, hooks, sidecar metadata, publishing checks, or README content.

Changes

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.

  1. 2d ago First seen · 33 lines · 298 tokens per session scan A 5b30a598a4fa

Subscribe to this mod's changes

grimoire AGENTS.md is an instructions file published in the GitHub repository hon454/grimoire (2 stars, last pushed 14d ago), licensed MIT. It adds 298 tokens to every session, about $0.0015 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.

Related

Other instructions, from other repositories