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.
npx agentmods add instructions/shigel/autoforge/agents-mdgit clone --depth 1 https://github.com/shigel/autoforgeWhat 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 | $0.00534 | $0.00534 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
autoforge AGENTS.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 yesterday.
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.
What it actually says
autoforge — Agent Instructions
This file provides instructions for AI coding agents (Codex CLI, Claude Code, etc.) working on this repository.
Overview
autoforge is an autonomous SDLC framework. You have access to harness tools via bash commands.
Available Tools
# Search codebase for patterns
PYTHONPATH=. python3 -m autoforge.harness.tools search "pattern" --dir autoforge/
# View file with line numbers
PYTHONPATH=. python3 -m autoforge.harness.tools view path/to/file.py --start 1 --end 50
# Edit file (with Python syntax validation)
PYTHONPATH=. python3 -m autoforge.harness.tools edit path/to/file.py --old "old code" --new "new code"
# Run shell command
PYTHONPATH=. python3 -m autoforge.harness.tools run-cmd "pytest tests/ -v"
# List directory
PYTHONPATH=. python3 -m autoforge.harness.tools list-dir autoforge/agents
# Extract search patterns from issue text
PYTHONPATH=. python3 -m autoforge.harness.tools localize --issue "bug description"
# Analyze a repository and propose goals
PYTHONPATH=. python3 -m autoforge.harness.init --dir /path/to/repo
Issue Resolution Workflow
- Read the issue description
localize --issue "..."to extract search patternssearch "pattern"to find relevant filesview path/to/file.pyto read the codeedit path/to/file.py --old "..." --new "..."to fix the bugrun-cmd "pytest tests/"to verify the fix
Development Rules
- Python 3.11+, Pydantic v2, httpx
- Immutable data (frozen dataclass / Pydantic model)
- Files under 400 lines
- Run tests:
PYTHONPATH=. python3 -m pytest tests/ -v
Project Structure
autoforge/
├── agents/ # 7 SDLC agents + resolver stack
├── core/ # PipelineRunner, LLMClient, Config, Memory, Hooks
├── schemas/ # Pydantic schemas for structured artifact passing
├── tools/ # ACI toolkit, arXiv/GitHub API clients
├── harness/ # Agent harness mode (init, tools, solve)
└── bench/ # SWE-bench evaluation pipeline
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.
- yesterday First seen · 61 lines · 534 tokens per session scan A fedbe5e9dc7f
autoforge AGENTS.md is an instructions file published in the GitHub repository shigel/autoforge (5 stars, last pushed 4mo ago), licensed MIT. It adds 534 tokens to every session, about $0.0027 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.
Other instructions, from other repositories
recharts AGENTS.md
Instructions for recharts/recharts: This is Recharts repository. Recharts is a React-based charting library. The goal is to provide a simple, declarative, and composable way to build charts. We value consistency, usability, and performance. Accessibility is important.
openscreen AGENTS.md
Instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
spec-kit-zh AGENTS.md
Instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
ai-content-kb CLAUDE.md
Instructions for mrbear1024/ai-content-kb, covering knowledge base operating rules, repository roles, provenance, safe editing and ai output lifecycle.