agentmods.dev

Ghost-Agent CLAUDE.md

Repository instructions for Ghost-Agent, an autonomous development loop that repeatedly runs Claude Code and monitors its progress. They describe its shell scripts, library components, response parsing, and compatibility behavior.

In plain words
What is it for?
Use it when changing the Ralph loop, monitoring dashboard, setup process, document importer, library code, or command-line response handling.
Why use it?
They explain how the loop is organized and which scripts handle development, monitoring, setup, file creation, and document imports.

Instructions file

747 +2 7d ago A scan 6,216 tokens original MIT
View the source file CryptoDmitry/Ghost-Agent
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/cryptodmitry/ghost-agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/CryptoDmitry/Ghost-Agent
Per session 6,216 This file is loaded in full into every session.
When invoked 6,216 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 $0.06216 $0.06216
Opus 5 $0.03108 $0.03108
Sonnet 5 $0.01243 $0.01243
Haiku 4.5 $0.00622 $0.00622

Measured 2d ago against content hash da1de293306c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Ghost-Agent 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 2d 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 · 629 lines

How it starts

The opening of the file, as written. The whole thing — 629 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.

Repository Overview

This is the Ralph for Claude Code repository - an autonomous AI development loop system that enables continuous development cycles with intelligent exit detection and rate limiting.

Version: v0.9.8 | Tests: 276 passing (100% pass rate) | CI/CD: GitHub Actions

Core Architecture

The system consists of four main bash scripts and a modular library system:

Main Scripts

  1. ralph_loop.sh - The main autonomous loop that executes Claude Code repeatedly
  2. ralph_monitor.sh - Live monitoring dashboard for tracking loop status
  3. setup.sh - Project initialization script for new Ralph projects
  4. create_files.sh - Bootstrap script that creates the entire Ralph system
  5. ralph_import.sh - PRD/specification import tool that converts documents to Ralph format
    • Uses modern Claude Code CLI with --output-format json for structured responses
    • Implements detect_response_format() and parse_conversion_response() for JSON parsing
    • Backward compatible with older CLI versions (automatic text fallback)

Library Components (lib/)

The system uses a modular architecture with reusable components in the lib/ directory:

  1. lib/circuit_breaker.sh - Circuit breaker pattern implementation

    • Prevents runaway loops by detecting stagnation
    • Three states: CLOSED (normal), HALF_OPEN (monitoring), OPEN (halted)
    • Configurable thresholds for no-progress and error detection
    • Automatic state transitions and recovery

  2. lib/response_analyzer.sh - Intelligent response analysis

    • Analyzes Claude Code output for completion signals
    • JSON output format detection and parsing (with text fallback)
    • Supports both flat JSON format and Claude CLI format (result, sessionId, metadata)
    • Extracts structured fields: status, exit_signal, work_type, files_modified
    • Session management: store_session_id(), get_last_session_id(), should_resume_session()
    • Automatic session persistence to .claude_session_id file with 24-hour expiration
    • Session lifecycle: get_session_id(), reset_session(), log_session_transition(), init_session_tracking()
    • Session history tracked in .ralph_session_history (last 50 transitions)
    • Session auto-reset on: circuit breaker open, manual interrupt, project completion
    • Detects test-only loops and stuck error patterns
    • Two-stage error filtering to eliminate false positives
    • Multi-line error matching for accurate stuck loop detection
    • Confidence scoring for exit decisions

Read the full file on GitHub · 629 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. 2d ago First seen · 629 lines · 6,216 tokens per session scan A da1de293306c

Subscribe to this mod's changes

Ghost-Agent CLAUDE.md is an instructions file published in the GitHub repository CryptoDmitry/Ghost-Agent (747 stars, last pushed 7d ago), licensed MIT. It adds 6,216 tokens to every session, about $0.0311 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 2026-08-30.

Building agentsagent-control-roomai-agentai-agentsai-agents-frameworkclaude-codeclaude-code-cli
Related

Other instructions, from other repositories

ai-agents-for-beginners AGENTS.md

Instructions for microsoft/ai-agents-for-beginners, covering agents.md, project overview, setup commands, prerequisites and initial setup.

microsoft/ai-agents-for-beginners · 2,488 tokens

ralph-orchestrator AGENTS.md

Instructions for mikeyobrien/ralph-orchestrator, covering claude.md, build & test, web dashboard, architecture and key files.

mikeyobrien/ralph-orchestrator · 2,870 tokens

CrestApps.AgentSkills AGENTS.md

Instructions for CrestApps/CrestApps.AgentSkills, covering agent instructions, skill roots, skill structure, content conventions and adding a new skill.

CrestApps/CrestApps.AgentSkills · 359 tokens

ralph-orchestrator CLAUDE.md

Instructions for mikeyobrien/ralph-orchestrator, a project described as: An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration.

mikeyobrien/ralph-orchestrator · 3 tokens

langgraph AGENTS.md

AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.

langchain-ai/langgraph · 477 tokens

airi copilot-instructions.md

Copilot instructions for moeru-ai/airi, covering copilot repository instructions, general rules, validation and output format.

moeru-ai/airi · 229 tokens