agentmods.dev

autoforge: Instructions file for Claude Code

CLAUDE.md

autoforge CLAUDE.md is an instructions file for Claude Code from shigel/autoforge. It costs 713 tokens per session, scanned A, original, MIT.

An autonomous software-development framework written in Python that coordinates AI agents through stages such as surveying, implementing, testing, security review, and approval. It can run inside Claude Code, where the subscription provides authentication.

In plain words
What is it for?
Use it to investigate issues, load SWE-bench tasks, locate relevant code, reproduce failures, apply fixes, run checks, and save patches in the required format.
Why use it?
It organizes broad software tasks into a repeatable process and provides tools for searching, viewing, editing, running commands, and saving patches.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is shigel/autoforge's own configuration. It tells Claude Code how to work on autoforge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything autoforge configures →

not rated 5repo 6mo ago A scan 713 tokens original MIT
View source ↗ shigel/autoforge
Reuse

Borrowing it

Nothing to install: this file belongs to shigel/autoforge. 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/shigel/autoforge/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shigel/autoforge

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.

agentmods badge for autoforge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shigel/autoforge/claude-md/github.svg)](https://agentmods.dev/instructions/shigel/autoforge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shigel/autoforge/claude-md"><img src="https://agentmods.dev/badge/instructions/shigel/autoforge/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for autoforge CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shigel/autoforge/claude-md"><img src="https://agentmods.dev/badge/instructions/shigel/autoforge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 713 This file is loaded in full into every session.
When invoked 713 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00713 $0.00713
Opus 5.5 $0.00285 $0.00285
Sonnet 5.5 $0.00143 $0.00143
Haiku 4.5 $0.00071 $0.00071

Measured 2mo ago against content hash 4ab347c5050e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autoforge 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 2mo 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 · 61 lines

What it actually says

autoforge

自律型AIエージェントによるソフトウェア開発ライフサイクルの完全自動化フレームワーク。

プロジェクト概要

  • 論文: paper/paper.md — アーキテクチャ設計と関連研究
  • 調査: docs/ — OSS調査レポート・競合分析
  • 実装: autoforge/ — Python パッケージ (v0.5)

アーキテクチャ（ハーネスモード）

Claude Code のサブスクリプション内で動作。API key 不要。

Claude Code (推論層 — LLM はサブスクで認証済み)
    │
    ├── autoforge-tools search "pattern"    # コード検索
    ├── autoforge-tools view path           # ファイル閲覧（行番号付き）
    ├── autoforge-tools edit path --old/--new  # 編集（lint検証付き）
    ├── autoforge-tools run-cmd "pytest"    # コマンド実行
    ├── autoforge-tools localize --issue "..." # パターン抽出
    ├── autoforge-tools load-task id        # SWE-benchタスク読み込み
    └── autoforge-tools save-patch id       # パッチ保存（SWE-bench形式）

フルSDLCパイプライン（7エージェント）

Survey → Idea(木探索) → Implement → Test ⟲ → Security(OWASP) ⟲ → Stage → Approval

SWE-bench 競争力スタック

Localizer(3段階) → Reproducer(fail→pass) → ACI(7ツール) → Search Agent → Resolver

ハーネスモードでの Issue 解決手順

  1. タスク読み込み: PYTHONPATH=. python3 -m autoforge.harness.tools load-task INSTANCE_ID --file tasks.jsonl
  2. パターン抽出: PYTHONPATH=. python3 -m autoforge.harness.tools localize --issue "issue text"
  3. コード検索: PYTHONPATH=. python3 -m autoforge.harness.tools search "pattern"
  4. ファイル閲覧: PYTHONPATH=. python3 -m autoforge.harness.tools view path/to/file
  5. 修正: PYTHONPATH=. python3 -m autoforge.harness.tools edit path --old "old" --new "new"
  6. テスト: PYTHONPATH=. python3 -m autoforge.harness.tools run-cmd "pytest"
  7. パッチ保存: PYTHONPATH=. python3 -m autoforge.harness.tools save-patch INSTANCE_ID --patch "diff"

開発ルール

  • Python 3.11+, Pydantic v2, httpx
  • イミュータブルデータ（frozen dataclass / Pydantic model）
  • ファイルは400行以下
  • テスト: PYTHONPATH=. python3 -m pytest tests/ -v

テスト

PYTHONPATH=. python3 -m pytest tests/ -v
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. 2mo ago First seen · 61 lines · 713 tokens per session scan A 4ab347c5050e

Subscribe to this mod's changes

autoforge CLAUDE.md is an instructions file published in the GitHub repository shigel/autoforge (5 stars, last pushed 6mo ago), licensed MIT. It adds 713 tokens to every session, about $0.0029 per session on Opus 5.5. 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.

Building agents
Related

autoforge CLAUDE.md compared with instructions from other repositories

autoforge CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
autoforge CLAUDE.mdshigel/autoforgeInstructions file56mo agoMITA713Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode