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/zhangyu94/humanfile/agents-mdgit clone --depth 1 https://github.com/zhangyu94/humanfileWrote 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/zhangyu94/humanfile/agents-md)<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>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 | $0.00721 | $0.00721 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
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.
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 exampledocs/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 testfrom root or any package - Build: tsdown — run
pnpm buildfrom root or any package - Cross-platform: The implementation is expected to work and to be tested on MacOS/Linux/Windows
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.
- 4d ago First seen · 65 lines · 721 tokens per session scan A 927869ac926a
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.
Other instructions, from other repositories
superpowers-zh CLAUDE.md
Claude Code instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.
spec-kit-zh AGENTS.md
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.
Meta_Kim CLAUDE.md
Claude Code instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.
nopua AGENTS.md
Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.
Atomic-Spec AGENTS.md
Instructions for Chappygo-OS/Atomic-Spec, covering agents.md — adding a new ai agent to atomic spec, about atomic spec and the atomicspec cli, general practices, adding new agent support and current supported agents.
decantr CLAUDE.md
Instructions for decantr-ai/decantr, covering claude.md -- decantr, project, packages, apps and terminology.