embabel-agent CLAUDE.md

Repository instructions for working on embabel-agent and its documentation. They define required rules, coding style, test-first development, build checks, documentation updates, and limits on Git actions.

In plain words
What is it for?
They are for making enhancements or bug fixes, writing tests before implementation, building the relevant Maven project, running focused tests, and updating affected documentation.
Why use it?
They give a coding agent the project's working rules so changes follow local expectations and are checked before they are presented as finished.

Instructions file

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/embabel/embabel-agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/embabel/embabel-agent
Per session 504 This file is loaded in full into every session.
When invoked 504 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 $0.00504 $0.00504
Opus 5 $0.00252 $0.00252
Sonnet 5 $0.00101 $0.00101
Haiku 4.5 $0.00050 $0.00050

Measured yesterday against content hash 0634cd7a776a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

embabel-agent 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 yesterday.

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.

CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 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.

Important

  • ALL instructions within this document MUST BE FOLLOWED, these are not optional unless explicitly stated.
  • ASK FOR CLARIFICATION If you are uncertain of anything within the document.
  • DO NOT edit more code than you have to.
  • DO NOT WASTE TOKENS, be succinct and concise.

Coding Style

IMPORTANT: Adhere to coding style in .embabel/coding-style.md for coding style guidance.

Working Approach

NEVER execute git commit or push. You may use git tools for history, diffing or staging only.

ALWAYS work test first. When making an enhancement or fixing a bug, write failing tests first, then implement the feature or fix the bug to make the tests pass.

IMPORTANT: You should build the most relevant project (closest pom.xml) with Maven before presenting finished changes. Run the individual tests you have changed or that are most relevant.

If any change impacts usage of the project, update relevant documentation files.

Advice for Documentation in embabel-agent-docs

When working on documentation in the embabel-agent-docs module, follow these guidelines:

Use Asciidoctor syntax for writing documentation.

When asked to edit a particular .adoc file, look for a parallel file with a name prefixed with a . for instructions.

For example, if you are asked to edit tools.adoc, look for .tools.adoc for specific instructions about how to go about it. Thus you will be given a combination of user instructions such as ("edit tools.adoc to cover the FooBar tool in FooBar.kt"). You will follow the user instruction but bear in mind the instructions in any .tools.adoc file. If there is no ..adoc file, follow the general instructions in this document.

When writing documentation, ensure that you cover the following general instructions:

NEVER make up code unless asked. Code examples must come from the following repositories:

Read the full file on GitHub · 56 lines

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. yesterday First seen · 56 lines · 504 tokens per session scan A 0634cd7a776a

Subscribe to this mod's changes

embabel-agent CLAUDE.md is an instructions file published in the GitHub repository embabel/embabel-agent (4,407 stars, last pushed yesterday), licensed Apache-2.0. It adds 504 tokens to every session, about $0.0025 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.