Borrowing it
Nothing to install: this file belongs to sunyuzheng/lizheng-open-context. 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/sunyuzheng/lizheng-open-context/main/AGENTS.mdgit clone --depth 1 https://github.com/sunyuzheng/lizheng-open-contextWrote 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/sunyuzheng/lizheng-open-context/agents-md)<a href="https://agentmods.dev/instructions/sunyuzheng/lizheng-open-context/agents-md"><img src="https://agentmods.dev/badge/instructions/sunyuzheng/lizheng-open-context/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.
<a href="https://agentmods.dev/instructions/sunyuzheng/lizheng-open-context/agents-md"><img src="https://agentmods.dev/badge/instructions/sunyuzheng/lizheng-open-context/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00477 | $0.00477 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
lizheng-open-context 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 12d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
This repository is a source-grounded public context pack, not a persona simulator.
When answering from this repository
- Retrieve before answering.
- Distinguish a direct source, a synthesis across sources, and your own inference.
- Cite the original title, date, URL, and video timestamp when available.
- Prefer the current thesis for durable positioning; preserve dated posts, comments, and videos as dated views.
- If sources disagree, show the change or tension. Do not silently blend them.
- Recommend only sources that materially help the question, and explain why each one fits.
- Do not claim that an answer is what Yuzheng "would say" unless it is a direct, current quotation.
- Do not turn heuristics, book frameworks, or working lenses into diagnoses, universal laws, guarantees, or rigid instructions.
Privacy and rights
- Use only committed material in this repository and its source URLs.
- Never import private messages, other members' posts or comments, member profiles, personal data, credentials, unpublished drafts, internal operations, or commercial secrets.
- Full-text Superlinear posts and comments must be authored by
YZ｜立正. Explicit author authorization covers the committed first-party text even when the original Circle space required membership; it does not cover surrounding member content. - Community comments must be originally public replies on included public Yuzheng-authored posts and pass
config/community-comment-policy.json; retain the canonical comment link but remove member mention names, contact data, inline links, third-party quotations, and private or sensitive-personal context. - Do not add full guest-interview transcripts without documented permission and an explicit rights classification.
- A first-party video transcript must also appear in
config/video-transcript-allowlist.txt; absence from guest metadata is not approval. - Use the committed author-owned 真本事 framework reference. Do not import the publisher's layout, illustrations, scans, or third-party material unless rights are separately documented.
- Run
python3 scripts/validate_release.pybefore proposing a public release.
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.
- 12d ago First seen · 30 lines · 477 tokens per session scan A 13b88b03bd50
lizheng-open-context AGENTS.md is an instructions file published in the GitHub repository sunyuzheng/lizheng-open-context (107 stars, last pushed 12d ago), licensed MIT. It adds 477 tokens to every session, about $0.0024 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
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.
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).
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.
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).