What is Aha-Loop CLAUDE.md?

Project instructions for Aha Loop, an autonomous development system that plans, researches, oversees, and logs software work. It explains how to initialize the system in an existing project and start a run.

Use them when starting Aha Loop on a new or external project, building a project vision, or working with its workspace and orchestration scripts.

They give agents the project context and the commands needed to keep Aha Loop’s files in the right workspace location.

Aha-Loop CLAUDE.md — Instructions file by YougLin-dev

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/youglin-dev/aha-loop/claude-md

Clone the repo

git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop

Per session 2,343 This file is loaded in full into every session.

When invoked 2,343 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.02343	$0.02343
Opus 5	$0.01171	$0.01171
Sonnet 5	$0.00469	$0.00469
Haiku 4.5	$0.00234	$0.00234

Measured 2d ago against content hash 623ecaa099a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Aha-Loop CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://crates.io/api/v1/crates/tokio" | jq '.crate.max_stable_version'

CLAUDE.md · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aha Loop - Claude Code Instructions

Project Overview

This is the Aha Loop project - a fully autonomous AI development system that extends Ralph with planning, research, and oversight capabilities.

Aha Loop Autonomous Development System

This project uses Aha Loop, a fully autonomous AI development system with:

Interactive vision building
Parallel exploration via git worktrees
Full observability and thought logging
Automatic skill creation and maintenance
Unlimited resource access
God Committee - Independent oversight layer with supreme authority

Starting a New Project

Workspace Mode (Recommended for External Projects)

Aha Loop can operate on any project without copying files. All Aha Loop data is stored in .aha-loop/ within your project:

# Initialize workspace in your project
/path/to/aha-loop/scripts/aha-loop/orchestrator.sh --init-workspace /path/to/your-project

# Run Aha Loop on your project
/path/to/aha-loop/scripts/aha-loop/orchestrator.sh --workspace /path/to/your-project --build-vision

# Or set environment variable
export AHA_LOOP_WORKSPACE=/path/to/your-project
/path/to/aha-loop/scripts/aha-loop/orchestrator.sh --build-vision

# Or run from within your project (auto-detects .aha-loop/)
cd /path/to/your-project
/path/to/aha-loop/scripts/aha-loop/orchestrator.sh --build-vision

Workspace Directory Structure:

your-project/
├── .aha-loop/           # All Aha Loop files here
│   ├── config.json
│   ├── prd.json
│   ├── progress.txt
│   ├── project.vision.md
│   ├── project.roadmap.json
│   ├── research/
│   ├── exploration/
│   ├── knowledge/
│   ├── logs/
│   └── .god/
├── src/                 # Your code (untouched)
└── ...

Interactive Vision Building (Recommended)

./scripts/aha-loop/orchestrator.sh --build-vision

You'll be guided through questions to build a complete vision.

Manual Vision

cp scripts/aha-loop/templates/project.vision.template.md project.vision.md
# Edit the file
./scripts/aha-loop/orchestrator.sh --tool claude

Read the full file on GitHub · 355 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.

2d ago First seen · 355 lines · 2,343 tokens per session scan A 623ecaa099a0

Subscribe to this mod's changes

Aha-Loop CLAUDE.md is an instructions file published in the GitHub repository YougLin-dev/Aha-Loop (181 stars, last pushed 7mo ago), licensed MIT. It adds 2,343 tokens to every session, about $0.0117 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

Aha-Loop CLAUDE.md