mcp-yashan: Instructions file for Codex

AGENTS.md

mcp-yashan AGENTS.md is an instructions file for Codex, OpenCode from willorn/mcp-yashan. It costs 535 tokens per session, scanned A, original, MIT.

Project instructions for developing the willorn/mcp-yashan repository, including Chinese responses, debugging rules, and progress updates.

In plain words
What is it for?
Use them while modifying or debugging that repository so changes follow its stated development and response rules.
Why use it?
They set consistent expectations for communication, temporary files, error handling, and decisions about compatibility or fallback behavior.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is willorn/mcp-yashan's own configuration. It tells Codex and OpenCode how to work on mcp-yashan itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-yashan configures →

Reuse

Borrowing it

Nothing to install: this file belongs to willorn/mcp-yashan. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/willorn/mcp-yashan/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/willorn/mcp-yashan

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 mcp-yashan AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/willorn/mcp-yashan/agents-md/github.svg)](https://agentmods.dev/instructions/willorn/mcp-yashan/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/willorn/mcp-yashan/agents-md"><img src="https://agentmods.dev/badge/instructions/willorn/mcp-yashan/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.

agentmods 80×15 button for mcp-yashan AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/willorn/mcp-yashan/agents-md"><img src="https://agentmods.dev/badge/instructions/willorn/mcp-yashan/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 535 This file is loaded in full into every session.
When invoked 535 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00535 $0.00535
Opus 5.5 $0.00214 $0.00214
Sonnet 5.5 $0.00107 $0.00107
Haiku 4.5 $0.00053 $0.00053

Measured 2mo ago against content hash 4e0fad1af6fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-yashan 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 2mo 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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

开发的临时文件可以放到 docs-in-dev 文件夹中,不要提交到 github

Basic Rules

  1. Think in English and answer in Chinese unless the context requires otherwise.
  2. Use ascii for diagrams. Prefer long, fluent natural language paragraphs; use bullet lists only when necessary to maintain readability.
  3. When the user's requirements are ambiguous, always ask for clarification and provide options before proceeding — the user may lack technical expertise and give vague or unrealistic demands.
  4. Never compliment the user or be affirming excessively (like saying "You're absolutely right!" etc). Criticize user's ideas if they actually need to be critiqued.
  5. Avoid getting stuck. After 3 failures when attempting to fix or implement something, stop, note down what's failing, think about the core issue, then continue.
  6. End immediately after the final substantive sentence, with no conversational closers, offers, suggestions, or follow-up questions unless the user explicitly requests clarification.

Debug-First Policy (No Silent Fallbacks)

  • Do not introduce new boundary rules / guardrails / blockers / caps (e.g. max-turns), fallback behaviors, or silent degradation just to make it run.
  • Do not add mock/simulation fake success paths (e.g. returning (mock) ok, templated outputs that bypass real execution, or swallowing errors).
  • Do not write defensive or fallback code; it does not solve the root problem and only increases debugging cost.
  • Prefer full exposure: let failures surface clearly (explicit errors, exceptions, logs, failing tests) so bugs are visible and can be fixed at the root cause.
  • If a boundary rule or fallback is truly necessary (security/safety/privacy, or the user explicitly requests it), it must be:
    • explicit (never silent),
    • documented,
    • easy to disable,
    • and agreed by the user beforehand.

No Backward Compatibility

No backward compatibility unless explicitly requested. Break old formats freely. Prioritize clean architecture and high-quality code over minimizing changed lines.

Read the full file on GitHub · 36 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. 2mo ago First seen · 36 lines · 535 tokens per session scan A 4e0fad1af6fc

Subscribe to this mod's changes

mcp-yashan AGENTS.md is an instructions file published in the GitHub repository willorn/mcp-yashan (3 stars, last pushed 4mo ago), licensed MIT. It adds 535 tokens to every session, about $0.0021 per session on Opus 5.5. 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.

Related

mcp-yashan AGENTS.md compared with instructions from other repositories

mcp-yashan AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-yashan AGENTS.mdwillorn/mcp-yashanInstructions file34mo agoMITA535Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode