agentmods.dev

code-hacker: Instructions file for Codex

AGENTS.md

code-hacker AGENTS.md is an instructions file for Codex, OpenCode from hackerlibs/code-hacker. It costs 1,222 tokens per session, scanned A, original, MIT.

Always-on working instructions for a coding-agent repository, covering its goals, important files, architecture, and default development habits.

In plain words
What is it for?
Use them as a starting guide when working on the repository's Python configuration, server scripts, MCP services, agent definitions, or development commands.
Why use it?
They encourage small reviewable changes, repeatable workflows, and checking the source of truth before changing servers, ports, endpoints, or tools.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

This is hackerlibs/code-hacker's own configuration. It tells Codex and OpenCode how to work on code-hacker 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 code-hacker configures →

not rated 55repo yesterday A scan 1,222 tokens original MIT
View source ↗ hackerlibs/code-hacker
Reuse

Borrowing it

Nothing to install: this file belongs to hackerlibs/code-hacker. 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/hackerlibs/code-hacker/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/hackerlibs/code-hacker

Made for: Codex, OpenCode.

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 code-hacker AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hackerlibs/code-hacker/agents-md/github.svg)](https://agentmods.dev/instructions/hackerlibs/code-hacker/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hackerlibs/code-hacker/agents-md"><img src="https://agentmods.dev/badge/instructions/hackerlibs/code-hacker/agents-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 code-hacker AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hackerlibs/code-hacker/agents-md"><img src="https://agentmods.dev/badge/instructions/hackerlibs/code-hacker/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,222 This file is loaded in full into every session.
When invoked 1,222 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 $0.01222 $0.01222
Opus 5.5 $0.00489 $0.00489
Sonnet 5.5 $0.00244 $0.00244
Haiku 4.5 $0.00122 $0.00122

Measured 2mo ago against content hash 03e647921130, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-hacker 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 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.

AGENTS.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — How to work in this repo (for coding agents + humans)

This file is the repo's always-on working agreement. If you are an agent, follow it by default unless a task explicitly overrides it.

North Star

  • Make small, reviewable changes. Prefer tiny diffs that are easy to reason about.
  • Keep workflows repeatable. If a step matters, document it or script it.
  • Don't leak secrets. Never commit credentials, tokens, API keys, or .env files.

Read Before You Act

Before changing anything, locate the source of truth:

  1. Docs / run commands
    • README.md
    • start_servers.sh (server lifecycle management)
  2. Build configuration
    • pyproject.toml (Python deps + build config)
    • subagents.yaml (DeepAgent subagent definitions)
  3. Agent definitions
    • code-hacker.agent.md (VS Code Custom Agent system prompt + tool bindings)

If a task involves server ports, MCP endpoints, or tool names, read the relevant source file first and avoid "guess changes".

Repo Map (high level)

This section is a convenience only. If it gets out of date, trust the repo tree.

  • filesystem.py — MCP Server 1: File CRUD, search, command exec (port 8001)
  • git_tools.py — MCP Server 2: Git operations (port 8002)
  • code_intel.py — MCP Server 3: AST analysis, symbols, dependency graph (port 8003)
  • memory_store.py — MCP Server 4: Persistent memory + scratchpad + QA experience (port 8004)
  • code_review.py — MCP Server 5: Code quality review + health score + ydiff structural diff (port 8005)
  • multi_project.py — MCP Server 6: Multi-project workspace (port 8007)
  • lib/ — Internal engines (ydiff AST diff)
  • web_app.py — DeepAgent web interface (FastAPI + WebSocket)
  • tui_app.py — Claude Code-style TUI (Rich + prompt_toolkit)
  • subagents.yaml — 4 subagent definitions
  • static/ — Hacker-style web terminal UI
  • tests/ — LLM-powered integration test scenarios
  • start_servers.sh — Start/stop/status/restart all 6 MCP servers
  • codehacker/ — Package directory

Read the full file on GitHub · 111 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. 2mo ago First seen · 111 lines · 1,222 tokens per session scan A 03e647921130

Subscribe to this mod's changes

code-hacker AGENTS.md is an instructions file published in the GitHub repository hackerlibs/code-hacker (55 stars, last pushed yesterday), licensed MIT. It adds 1,222 tokens to every session, about $0.0049 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 2026-08-30.

LLMaicodergptprompt-engineeringvscode-extension
Related

Other instructions, from other repositories

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 · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens