argus CLAUDE.md

argus CLAUDE.md is an instructions file for coding agents from Khamel83/argus. It costs 326 tokens per session, scanned A, original, MIT.

A short guide for working on Argus with Claude Code and other AI coding agents. It points agents to the main project instructions and records Argus-specific development rules.

In plain words
What is it for?
Use it when developing, testing, documenting, or releasing changes in the Argus repository, including work involving its MCP server.
Why use it?
It prevents agents from using the wrong Python version or commands and reminds them to update user-facing documentation and release notes when behavior changes.

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/khamel83/argus/claude-md
Clone the repo
git clone --depth 1 https://github.com/Khamel83/argus

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 argus CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/khamel83/argus/claude-md.svg)](https://agentmods.dev/instructions/khamel83/argus/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/khamel83/argus/claude-md"><img src="https://agentmods.dev/badge/instructions/khamel83/argus/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 326 This file is loaded in full into every session.
When invoked 326 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 $0.00326 $0.00326
Opus 5 $0.00163 $0.00163
Sonnet 5 $0.00065 $0.00065
Haiku 4.5 $0.00033 $0.00033

Measured 4d ago against content hash facde6e32167, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

argus 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 4d 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.

CLAUDE.md · 24 lines

What it actually says

Claude Code — Argus

What this file is for: Claude Code's entry point into this repo. The canonical guide for any AI coding agent (Claude Code, Codex, Cursor, Copilot, OpenCode) lives in AGENTS.md — Claude Code reads both, but the content lives there. Keep this file short.

See AGENTS.md for project conventions, architecture, key commands, provider tiers, configuration, and the rules contributors must follow.

Claude-Code-specific notes

  • The MCP server in this repo is argus — you can use it directly from Claude Code via argus mcp serve (stdio) or by configuring a remote HTTP transport. See the Integration → MCP section of README.md.
  • The repo is pinned to Python 3.12 for development. Use uv run pytest ..., not the system interpreter. See CONTRIBUTING.md.
  • Local-only operator artifacts (e.g. 1shot/, docs/sessions/, .janitor/, .claude/) are gitignored. Don't write into them as part of a PR.
  • When changing user-facing behavior, update README, .env.example, and CHANGELOG (under [Unreleased]). Do not bump the version in pyproject.toml or server.json — releases are cut separately. See docs/releasing.md.
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. 4d ago First seen · 24 lines · 326 tokens per session scan A facde6e32167

Subscribe to this mod's changes

argus CLAUDE.md is an instructions file published in the GitHub repository Khamel83/argus (4 stars, last pushed yesterday), licensed MIT. It adds 326 tokens to every session, about $0.0016 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.