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/ranxi2001/zero2agent/agents-mdgit clone --depth 1 https://github.com/ranxi2001/zero2AgentWhat 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 | $0.01535 | $0.01535 |
| Opus 5 | $0.00767 | $0.00767 |
| Sonnet 5 | $0.00307 | $0.00307 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
zero2Agent 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 2d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zero2Agent Repository Guide
Purpose
This repository owns the zero2Agent tutorial site at
https://onefly.top/zero2Agent/. It is a Chinese-language, engineering-focused
learning path for developers building, evaluating, and interviewing for AI
Agent systems.
Keep repository changes focused on one coherent content, navigation, design, or publishing outcome. Preserve unrelated user edits and check the worktree before and after every task.
Start Every Task
- Run
git status --short --branchand identify the exact files in scope. - Read the relevant repository Skill under
.agents/skills/before editing. - Inspect the current module index, neighboring articles, and
_data/nav.yml; examples or article counts in a Skill may be older than the repository. - For facts about fast-moving tools, APIs, models, prices, or projects, verify them against current primary sources and distinguish fact from inference.
- Keep generated output, credentials, browser profiles, and scraped raw data out of Git.
Source Of Truth
_data/nav.ymldrives the article header navigation, sidebar, and previous/ next pager through_layouts/default.html.- Each module directory owns its landing
index.mdand article directories. - An article lives at
<module>/<NN>-<slug>/index.md. index.htmlowns the homepage module cards, headline metrics, and primary entry links.README.mdowns the public repository overview, module table, totals, and local-run instructions._config.ymlowns the Jekyll URL, base path, included content, and plugins._layouts/default.htmlandassets/own the shared article shell and client behavior. Avoid article-specific fixes in shared code unless the behavior is intentionally site-wide..github/workflows/jekyll-gh-pages.ymlis the production build and deploy contract. A push tomainpublishes the site.
When these sources disagree, use executable site behavior and current files as evidence, then update every affected summary or count in the same change.
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.
- 2d ago First seen · 153 lines · 1,535 tokens per session scan A e0ec979185cc
zero2Agent AGENTS.md is an instructions file published in the GitHub repository ranxi2001/zero2Agent (367 stars, last pushed 2d ago), licensed MIT. It adds 1,535 tokens to every session, about $0.0077 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 2026-08-30.
Other instructions, from other repositories
vant AGENTS.md
Instructions for dhaupin/vant, covering agents.md — vant agent guide, what is vant?, your job, brain router interface and middleware chain.
fast-agent AGENTS.md
Instructions for evalstate/fast-agent, covering fast-agent contributor notes and architectural orientation.
kungfu CLAUDE.md
Instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before working in this repository. It routes both product use and contribution work to the repository sources of truth, including the requirement that development and build tasks enter through Shifu.
kungfu copilot-instructions.md
Instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
yoagent CLAUDE.md
Instructions for yologdev/yoagent, covering claude.md, project overview, build & development commands, architecture and core loop pattern.
skein-js AGENTS.md
Instructions for skein-js/skein-js, covering agents.md, what skein-js is, read first, golden rules and this is an nx monorepo (pnpm) — use nx.