agent-context CLAUDE.md

agent-context CLAUDE.md is an instructions file for coding agents from cote-star/agent-context. It costs 97 tokens per session, scanned A, original, MIT.

A set of repository-navigation instructions for coding agents. It tells them which context files to read first, how to find the right task route, and which parts of the code they may search.

In plain words
What is it for?
Use it in a repository that has an `.agent-context` directory and needs a standard startup procedure for agents.
Why use it?
It reduces unnecessary file reading and helps agents follow the repository's established rules before changing code. The input does not describe its implementation beyond these instructions.

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

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-context CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cote-star/agent-context/claude-md.svg)](https://agentmods.dev/instructions/cote-star/agent-context/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cote-star/agent-context/claude-md"><img src="https://agentmods.dev/badge/instructions/cote-star/agent-context/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 This file is loaded in full into every session.
When invoked 97 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 $0.00097 $0.00097
Opus 5 $0.00048 $0.00048
Sonnet 5 $0.00019 $0.00019
Haiku 4.5 $0.00010 $0.00010

Measured 3d ago against content hash 1bac235ea024, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-context 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 9 lines

What it actually says

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.
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. 3d ago First seen · 9 lines · 97 tokens per session scan A 1bac235ea024

Subscribe to this mod's changes

agent-context CLAUDE.md is an instructions file published in the GitHub repository cote-star/agent-context (2 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session, about $0.0005 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

okp AGENTS.md

Instructions for talesofai/okp, covering agents.md — project conventions for okp, tech stack, architecture, api 端点 and data model (postgresql).

talesofai/okp · 1,386 tokens

project-tiny-context-harness AGENTS.md

Instructions for Seven128/project-tiny-context-harness, covering project agent overlay, 本仓库 authoring 例外, minimal context harness protocol, shared engineering quality obligation and default workflow contract.

Seven128/project-tiny-context-harness · 5,179 tokens

structured-context-spec CLAUDE.md

Instructions for tim-mccrimmon/structured-context-spec, covering claude.md, structured context specification (scs) — project context, what this project is, repository structure and tools & development commands.

tim-mccrimmon/structured-context-spec · 1,997 tokens

agent-context-bridge AGENTS.md

Instructions for Yongthyuan/agent-context-bridge, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

Yongthyuan/agent-context-bridge · 649 tokens

beardrive CLAUDE.md

Claude Code instructions for runbear-io/beardrive, covering claude.md, what this is, commands, architecture and invariants — do not break these.

runbear-io/beardrive · 8,200 tokens

plan42 AGENTS.md

AGENTS.md instructions for sh1nj1/plan42, covering agent development guide, documentation language, documentation index and agent operating rules.

sh1nj1/plan42 · 549 tokens