Borrowing it
Nothing to install: this file belongs to mishahanin/heading-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mishahanin/heading-os/main/AGENTS.mdgit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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.
[](https://agentmods.dev/instructions/mishahanin/heading-os/agents-md)<a href="https://agentmods.dev/instructions/mishahanin/heading-os/agents-md"><img src="https://agentmods.dev/badge/instructions/mishahanin/heading-os/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.03594 | $0.03594 |
| Opus 5 | $0.01797 | $0.01797 |
| Sonnet 5 | $0.00719 | $0.00719 |
| Haiku 4.5 | $0.00359 | $0.00359 |
Grade A, and why
heading-os AGENTS.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 today.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`subprocess(..., shell=True)` / `os.system()`, no `yaml.load()` without How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents (Codex, Cursor, and any AGENTS.md-aware tool)
working in this repository. Claude Code agents should read CLAUDE.md instead
(or in addition) — it is the Claude-Code-specific superset of what is here,
carrying the always-on rules under .claude/rules/ that this file does not
duplicate.
No AGENTS.md existed in this repository before this file; it is new, not a
revision of a prior version.
What this repository is
HEADING OS is an operations engine for an AI executive assistant: a library of skills, always-on rules, automation scripts, and daemons that let an agent act as a strategic assistant across sessions, with Claude Code as the reference agent it is built for. This repository is the engine — code only, no private data, intended to be public. A companion private "data" repository (not part of this repo, and not present in a bare clone) holds the operator's actual contacts, knowledge, outputs, and credentials.
Setup
The canonical toolchain is uv; pyproject.toml
is the source of truth for dependencies and uv.lock pins the resolved set.
uv sync --all-extras --group dev # core + all integration extras + dev tools
cp .env.example .env # fill in only the credentials you use
pre-commit install # arm the commit-time gates (see below)
A plain venv + pip path also works and is kept for tooling that cannot run
uv. requirements.txt is a generated export of the full dependency graph
(uv export --all-extras) for exactly this case — do not hand-edit it.
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt # add requirements-dev.txt for dev tooling
cp .env.example .env
pre-commit install
Running tests
Always invoke the interpreter inside .venv explicitly — .venv/bin/python,
never a bare python — so you are not silently running against a different
interpreter or a machine-wide install that lacks the pinned dependencies.
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.
- today Changed · +2 lines · +30 tokens per session 1559969db404
- 3d ago First seen · 256 lines · 3,564 tokens per session scan A 55654c75f0d4
heading-os AGENTS.md is an instructions file published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,594 tokens to every session, about $0.0180 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.