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/otavia-projects/otavia/claude-mdgit clone --depth 1 https://github.com/otavia-projects/otaviaWrote 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/otavia-projects/otavia/claude-md)<a href="https://agentmods.dev/instructions/otavia-projects/otavia/claude-md"><img src="https://agentmods.dev/badge/instructions/otavia-projects/otavia/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 | $0.02205 | $0.02205 |
| Opus 5 | $0.01103 | $0.01103 |
| Sonnet 5 | $0.00441 | $0.00441 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
otavia 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 — 170 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.
Coding Agent Rules — MUST follow strictly
Context Loading
- Load module CLAUDE.md files on demand. Do NOT read all module CLAUDE.md files upfront. Use the Context Loading Guide below to determine which modules are relevant, then read only those.
- Read large source files incrementally. Many files exceed 500 lines (e.g.
AbstractChannel.scala,AdaptiveBufferImpl.scala,ActorThread.scala). First extract method/field signatures (via Grep, LSP, or other available tools), then read specific line ranges as needed. Do NOT read entire large files in one call.
Before Implementing
- Study existing similar code first. This project follows consistent patterns. You MUST find the closest existing implementation (e.g. new codec -> study codec-http) and follow its structure before writing any code.
- Clarify before coding. For each task, identify the success criteria upfront — expected behavior, test cases, compilation. If you are unsure about requirements, approach, or which pattern to follow, ask the user. Never silently guess or assume. If something feels wrong or ambiguous, push back — do not paper over confusion with code.
While Implementing
- Minimal, surgical changes. Write the minimum code that solves the problem — no speculative features, no abstractions for single-use code, no error handling for impossible scenarios. Touch ONLY what you must — every changed line MUST trace directly to the user's request. If your implementation can be reduced to fewer lines while preserving correctness, rewrite it. If you notice unrelated dead code, mention it — do NOT delete it unless explicitly asked.
- Comments focus on code itself. Scaladoc and inline comments MUST describe what the code does, its preconditions, and its effects. Do NOT include design rationale, decision history, comparison with alternatives, or meta-commentary about why something was written a certain way.
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 · 170 lines · 2,205 tokens per session scan A fe97d2d3401f
otavia CLAUDE.md is an instructions file published in the GitHub repository otavia-projects/otavia (55 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 2,205 tokens to every session, about $0.0110 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
tachyon AGENTS.md
AGENTS.md instructions for kpavlov/tachyon, covering tachyon mcp — agent guide, style, project, fast commands and parts.
tachyon GEMINI.md
Gemini CLI instructions for kpavlov/tachyon: In repositories indexed by CodeGraph (a .codegraph/ directory exists at the repo root), reach for it BEFORE grep/find or reading files when you need to understand or locate code.
hird AGENTS.md
AGENTS.md instructions for no-materials/hird, covering agents.md, north star, non-negotiables (definition of done), before implementing a ticket and rust workspace expectations.
skillsets AGENTS.md
Instructions for oghie/skillsets, covering skillsets and skills.
skillsets GEMINI.md
Instructions for oghie/skillsets: This extension bundles a collection of model-agnostic engineering and research skills.
penpot-aio AGENTS.md
AGENTS.md instructions for JSONbored/penpot-aio, covering agents.md, intent, source of truth, runtime contract and validation.