humanfile AGENTS.md

humanfile AGENTS.md is an instructions file for Codex, OpenCode from zhangyu94/humanfile. It costs 721 tokens per session, scanned A, original, MIT.

A repository guide for coding agents that explains the project structure, important documents, architecture, and editing rules. It also describes humanfile, a tool where file ownership is declared in .human files.

In plain words
What is it for?
Use it to orient an agent in the humanfile repository, find design documents and implementation plans, and follow its coding and documentation conventions.
Why use it?
It gives an agent a map of the codebase and tells it to get approval before changing files owned by someone else. This helps prevent edits that ignore project conventions or ownership boundaries.

Instructions file for CodexOpenCode

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/zhangyu94/humanfile/agents-md
Clone the repo
git clone --depth 1 https://github.com/zhangyu94/humanfile

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 humanfile AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zhangyu94/humanfile/agents-md.svg)](https://agentmods.dev/instructions/zhangyu94/humanfile/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zhangyu94/humanfile/agents-md"><img src="https://agentmods.dev/badge/instructions/zhangyu94/humanfile/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 721 This file is loaded in full into every session.
When invoked 721 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00721 $0.00721
Opus 5 $0.00360 $0.00360
Sonnet 5 $0.00144 $0.00144
Haiku 4.5 $0.00072 $0.00072

Measured 4d ago against content hash 927869ac926a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

humanfile 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 4d 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the entry point for AI coding agents working in this repository. It serves as a map — not an encyclopedia. Follow the pointers below to find deeper context.

Repository Overview

humanfile lets developers declare which files they take responsibility for via .human files. Agents learn to obtain explicit approval before editing, treat these files as source of truth, and respect ownership boundaries. The project ships a core library + CLI, a GitHub Action, and agent guidance for multiple platforms.

Architecture

See ARCHITECTURE.md for the package layout, dependency graph, and module responsibilities.

Documentation Map

All long-form documentation lives in docs/:

Path Contents
docs/design/ Design decisions, core beliefs
docs/plans/active/ Current implementation plans
docs/plans/completed/ Archived completed plans
docs/specs/ Product specifications and requirements
docs/references/ External reference material
docs/RELEASE.md Internal release/shipping runbook
docs/DESIGN.md High-level design philosophy
docs/PLANS.md Plans index and status

Placement rule:

  • docs/references/ is only for information derived from outside this repository.
  • Internal operational guides (for example release/shipping steps) belong in docs/ (for example docs/RELEASE.md).

Key Conventions

  • Language: TypeScript (ESM-first, dual CJS build for the core library)
  • Package manager: pnpm with workspaces
  • Monorepo layout: packages/core (lib + CLI + configs), packages/action
  • Tests: Vitest — run pnpm test from root or any package
  • Build: tsdown — run pnpm build from root or any package
  • Cross-platform: The implementation is expected to work and to be tested on MacOS/Linux/Windows

Read the full file on GitHub · 65 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. 4d ago First seen · 65 lines · 721 tokens per session scan A 927869ac926a

Subscribe to this mod's changes

humanfile AGENTS.md is an instructions file published in the GitHub repository zhangyu94/humanfile (10 stars, last pushed 4mo ago), licensed MIT. It adds 721 tokens to every session, about $0.0036 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.