agent-chorus CLAUDE.md

agent-chorus CLAUDE.md is an instructions file for Claude Code from cote-star/agent-chorus. It costs 1,924 tokens per session, scanned B, original, MIT.

Repository instructions for Agent Chorus, including a context pack: a set of files that explains the project, its rules, and where relevant code lives. Agents must read selected context files before opening source code.

In plain words
What is it for?
Use them to start tasks, answer architecture questions, follow project rules, and maintain the context pack.
Why use it?
They help an agent understand the repository in a controlled order and avoid searching or editing unrelated files.

Instructions file for Claude Code

Written for Claude Code: SessionEnd hook event. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

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/cote-star/agent-chorus/claude-md
Clone the repo
git clone --depth 1 https://github.com/cote-star/agent-chorus

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-chorus CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cote-star/agent-chorus/claude-md.svg)](https://agentmods.dev/instructions/cote-star/agent-chorus/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cote-star/agent-chorus/claude-md"><img src="https://agentmods.dev/badge/instructions/cote-star/agent-chorus/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,924 This file is loaded in full into every session.
When invoked 1,924 The same file — it is already loaded in full.
Security scan B 1 finding. 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 5.1 $0.01924 $0.01924
Opus 5 $0.00962 $0.00962
Sonnet 5 $0.00385 $0.00385
Haiku 4.5 $0.00192 $0.00192

Measured 5d ago against content hash 18c9ed67a32a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

agent-chorus CLAUDE.md scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Install by adding to `~/.claude/settings.json`:
CLAUDE.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BEFORE starting any task, read these 3 files in order:

  1. .agent-context/current/00_START_HERE.md
  2. .agent-context/current/30_BEHAVIORAL_INVARIANTS.md
  3. .agent-context/current/20_CODE_MAP.md Do NOT open repo source files until steps 1-3 are complete. Then open only files .agent-context identifies as relevant to your task.

Context Pack

BEFORE starting any task, read the context pack in this order:

  1. .agent-context/current/00_START_HERE.md — entrypoint, routing, stop rules
  2. .agent-context/current/30_BEHAVIORAL_INVARIANTS.md — change checklists, file families, what NOT to do
  3. .agent-context/current/20_CODE_MAP.md — navigation index, tracing flows

Read these three files BEFORE opening any repo source files. Then open only the files the pack identifies as relevant.

For architecture questions, also read 10_SYSTEM_OVERVIEW.md. For test/deploy questions, also read 40_OPERATIONS_AND_RELEASE.md.

Claude Code Instructions

Naming convention: Use chorus agent-context ... commands. Legacy npm wrappers (npm run agent-context:*) are still available in this repo.

Context Pack

When asked to understand this repository (or any "what does this repo do?" intent):

  1. Read .agent-context/current/00_START_HERE.md first.
  2. Follow the read order defined in that file (10_SYSTEM_OVERVIEW.md, then 30_BEHAVIORAL_INVARIANTS.md, then 20_CODE_MAP.md, then 40_OPERATIONS_AND_RELEASE.md).
  3. Only open project files when the context pack identifies a specific target.

If the context pack is missing, run:

chorus agent-context init
# ...fill in template sections...
chorus agent-context seal

If the context pack is stale (already initialized), run:

chorus agent-context seal

Context Pack Maintenance

After making changes to source files, check whether .agent-context/current/ needs updating. If the changes affect architecture, commands, behavioral invariants, or the code map, run:

Read the full file on GitHub · 201 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. 5d ago First seen · 201 lines · 1,924 tokens per session scan B 18c9ed67a32a

Subscribe to this mod's changes

agent-chorus CLAUDE.md is an instructions file published in the GitHub repository cote-star/agent-chorus (13 stars, last pushed 2mo ago), licensed MIT. It adds 1,924 tokens to every session, about $0.0096 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.