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 agentmods add instructions/etiennechollet/ontomics/claude-mdgit clone --depth 1 https://github.com/EtienneChollet/ontomicsWrote 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/etiennechollet/ontomics/claude-md)<a href="https://agentmods.dev/instructions/etiennechollet/ontomics/claude-md"><img src="https://agentmods.dev/badge/instructions/etiennechollet/ontomics/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 | $0.02562 | $0.02562 |
| Opus 5 | $0.01281 | $0.01281 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
Grade A, and why
ontomics 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 5d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
ABSOLUTE RULE — No AI attribution
NEVER mention Claude Code, Anthropic, ChatGPT, Codex, OpenAI, or any AI tool in commits, PRs, issues, comments, or any git artifact. No "Co-Authored-By", no "Generated with", no AI attribution of any kind. This applies to all text that enters the git history or appears on GitHub.
ABSOLUTE RULE — Worktree workflow
ALL source code and test changes MUST go through a worktree branch and PR. Never commit implementation work directly to main. NEVER edit a single file before the worktree exists.
The worktree MUST be created BEFORE any files are edited. This is the very first action for any implementation task. No exceptions. Do not edit on main and stash/move retroactively.
Worktree location: ./worktrees/per-<issue-number>-<issue-name> (e.g., worktrees/per-42-testbed-thread-cap). NEVER place worktrees outside the project root (e.g., ../).
Workflow:
- Create a feature branch:
epc28/<description>(associate with a Linear issue when one exists) - Create the worktree:
git worktree add -b epc28/<name> worktrees/per-<issue>-<name> main - Work ONLY inside that worktree — all edits, tests, and commits happen there
- Create a PR from the feature branch to main
- Merge to main only after review/validation
Direct commits to main are only acceptable for version bumps and release automation (cargo-release).
ABSOLUTE RULE — Embeddings must stay enabled
NEVER disable embeddings (embeddings.enabled = false) in any .ontomics/config.toml for any codebase without explicit permission from the user. Embeddings are a core part of the pipeline — disabling them silently degrades concept discovery, clustering, and suggest_name quality.
ABSOLUTE RULE — Tests are sacred
NEVER modify, delete, weaken, skip, or rewrite any test without explicit permission from the user. This is the single most important rule in this project. No exceptions.
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.
- 5d ago First seen · 147 lines · 2,562 tokens per session scan A 082a0e3bc3fb
ontomics CLAUDE.md is an instructions file published in the GitHub repository EtienneChollet/ontomics (41 stars, last pushed 4mo ago), licensed MIT. It adds 2,562 tokens to every session, about $0.0128 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 2026-08-30.
Other instructions, from other repositories
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
ai-auto-work CLAUDE.md
Claude Code instructions for chaohong-ai/ai-auto-work, covering gamemaker - ai native 游戏创作平台, 项目简介, ai 工作目录约定 and 按需加载（不默认装载）.
catalyst AGENTS.md
AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.
lerim AGENTS.md
AGENTS.md instructions for nablo-io/lerim, covering lerim, summary, current architecture, trace format and parsing and how to query existing context.
better-codebase CLAUDE.md
Claude Code instructions for NicolasYusim/better-codebase: Read and follow AGENTS.md when developing this repository.
AIWiki CLAUDE.md
Claude Code instructions for XuebinMa/AIWiki, covering claude.md — aiwiki 项目记忆, 这是什么, 每次动手前必读（按顺序）, 写作 / 翻译用 skill（不要手搓流程） and 保持连贯的硬规则（防止跨会话的风格 / 内容漂移）.