What is argus-claude CLAUDE.md?

Repository instructions for Argus, a Claude Code plugin that uses several AI agents to review code quality and software architecture. They describe the project layout, agent responsibilities, shared content, data formats, and review pipeline.

Use them when changing Argus commands, agents, shared instructions, schemas, validators, or the process that combines review findings into a report.

They give contributors a common map of a multi-agent code-review project, reducing the risk of putting logic in the wrong place or breaking the data passed between agents.

How josstei/argus-claude configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to josstei/argus-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/josstei/argus-claude/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/josstei/argus-claude

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/josstei/argus-claude/claude-md.svg)](https://agentmods.dev/instructions/josstei/argus-claude/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/josstei/argus-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/josstei/argus-claude/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,406 This file is loaded in full into every session.

When invoked 1,406 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01406	$0.01406
Opus 5	$0.00703	$0.00703
Sonnet 5	$0.00281	$0.00281
Haiku 4.5	$0.00141	$0.00141

Measured 8d ago against content hash d48edd88e1b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

argus-claude 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 8d 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 · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 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.

Project Overview

Argus is a Claude Code plugin for multi-agent code quality and architecture review with cross-validation from multiple LLM providers. Named after Argus Panoptes, the all-seeing giant of Greek mythology.

Architecture

Separation of Concerns

commands/ - Entry points only (skills that Claude Code exposes as /argus:*). Orchestration logic lives in commands/review.md.
agents/ - Individual agent definitions, each with a single responsibility.
agents/_shared/ - Reusable content fragments included via  markers.
schemas/ - JSON schemas that define the data contracts between agents.

Multi-Agent Pipeline

Orchestrator (commands/review.md)
  → Analysis Phase: up to 9 agents run in parallel per phase grouping
  → Validation Phase: 5 validators verify findings with evidence
  → External Phase (optional): Codex/Gemini CLI cross-validation
  → Consolidation: merges, deduplicates, scores, generates report

Phase-to-Agent Mapping

Phase	Analysis Agents	Validator	Depth Required
1: Architecture	01-architecture, 02-separation	1a-architecture	quick+
2: Hygiene	03-dead-code, 04-dependencies	2a-hygiene	quick+
3: Naming	05-naming	3a-naming	standard+
4: Quality	06-di-patterns, 07-error-handling, 08-lifecycle	4a-quality	standard+
5: Optimization	09-optimization	5a-optimization	thorough

Data Flow Between Agents

Analysis agents → finding.json schema → Validation agents → validation-result.json schema → Consolidation → report.json schema

finding.json: Individual issue with id, file, line, violation, severity, description, recommendation (required), plus optional currentPattern, optimalPattern, migrationPath, codeSnippet
validation-result.json: Links back to originalFindingId with validationStatus (CONFIRMED/REJECTED/MODIFIED/IMPROVABLE/NEEDS_REVIEW) and required evidence object
report.json: Final consolidated output with healthScore (0-100 per domain), verifiedFindings, implementationPlan (phased by severity), and optional patternEvolutionRoadmap

Read the full file on GitHub · 116 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.

8d ago First seen · 116 lines · 1,406 tokens per session scan A d48edd88e1b7

Subscribe to this mod's changes

argus-claude CLAUDE.md is an instructions file published in the GitHub repository josstei/argus-claude (6 stars, last pushed 7mo ago), licensed MIT. It adds 1,406 tokens to every session, about $0.0070 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.

Claude Code Code review ai-agents ai-tooling architecture-review claude claude-code-plugin

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

argus-claude: Instructions file for Claude Code