scagent CLAUDE.md

scagent CLAUDE.md is an instructions file for coding agents from miounet11/scagent. It costs 774 tokens per session, scanned A, original, MIT.

Project instructions for scagent, a command-line coding assistant. They describe setup, commands, project folders, security checks, file analysis, fixes, and GitHub pull-request review.

In plain words
What is it for?
Installing and diagnosing scagent, understanding its code structure, scanning files and projects, proposing or applying fixes, and reviewing GitHub pull requests.
Why use it?
They give an agent the repository-specific information needed to install, run, inspect, and maintain the project correctly.

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/miounet11/scagent/claude-md
Clone the repo
git clone --depth 1 https://github.com/miounet11/scagent

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 scagent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/miounet11/scagent/claude-md.svg)](https://agentmods.dev/instructions/miounet11/scagent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/miounet11/scagent/claude-md"><img src="https://agentmods.dev/badge/instructions/miounet11/scagent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 774 This file is loaded in full into every session.
When invoked 774 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 $0.00774 $0.00774
Opus 5 $0.00387 $0.00387
Sonnet 5 $0.00155 $0.00155
Haiku 4.5 $0.00077 $0.00077

Measured 5d ago against content hash 2cea813c5643, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scagent 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 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.

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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 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.

Quick Start

# Install
pip install -e .

# Run
shencha              # Interactive mode
shencha -q           # Quick audit
shencha config       # Setup wizard
shencha doctor       # Check environment

Project Structure (v2.1)

src/
├── cli.py              # 🎯 Main CLI (Rich-based, user-friendly)
├── config.py           # ⚙️ Configuration management
├── errors.py           # ❌ Error handling with friendly messages
├── output.py           # 🎨 Beautiful terminal output (Rich)
├── security.py         # 🔒 Input validation, path protection
│
├── agent/              # 🤖 Core Agent (modular)
│   ├── core.py         # Agent orchestration
│   ├── hooks.py        # Event hooks
│   └── tools/          # MCP Tools
│       ├── analysis.py # analyze_file, scan_project
│       ├── fix.py      # propose_fix, apply_fix
│       ├── expert.py   # expert_*_audit (UI, Arch, Logic)
│       ├── knowledge_tools.py
│       └── github_tools.py
│
├── integrations/       # 🔗 Third-party
│   └── github.py       # GitHub PR review
│
├── cache/              # 💾 Caching
│   └── file_cache.py   # Content-hash based
│
├── utils/              # 🛠️ Utilities
│   ├── async_io.py     # Async file operations
│   └── logger.py       # Unified logging
│
├── knowledge.py        # 📚 Knowledge base
├── reporters.py        # 📊 Report generation
├── frontend_checker.py # TypeScript/ESLint
├── log_analyzer.py     # PM2 log analysis
└── parallel_fixer.py   # Concurrent fixes

Key Commands

# Development
pip install -e ".[dev]"
pytest --cov=src
black src/ && isort src/

# CLI
shencha                    # Interactive audit
shencha ./project -q       # Quick audit
shencha pr owner/repo 123  # PR review
shencha config             # Configuration wizard
shencha doctor             # Environment check

Environment Variables

SHENCHA_API_KEY=<key>      # Required: LLM API key
SHENCHA_LLM_URL=<url>      # Optional: Custom API endpoint
GITHUB_TOKEN=<token>       # Optional: For PR review

Read the full file on GitHub · 93 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 · 93 lines · 774 tokens per session scan A 2cea813c5643

Subscribe to this mod's changes

scagent CLAUDE.md is an instructions file published in the GitHub repository miounet11/scagent (5 stars, last pushed 7mo ago), licensed MIT. It adds 774 tokens to every session, about $0.0039 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.