What is everything-analysis-agent AGENTS.md?

Repository instructions for an analysis-agent project that stores skills, plugins, and integrations. They define communication, coding, error-handling, documentation, and file-organization rules for agents working in the repository.

Use them when changing agent assets, skills, plugins, integrations, Python code, or project documentation so the work follows the repository's local rules.

They give coding agents project-specific expectations that may not be obvious from the source code. This reduces inconsistent language, style, error handling, and documentation decisions.

How yellowbee686/everything-analysis-agent configures Codex and OpenCo

Reuse

Borrowing it

Nothing to install: this file belongs to yellowbee686/everything-analysis-agent. 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/yellowbee686/everything-analysis-agent/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/yellowbee686/everything-analysis-agent

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/yellowbee686/everything-analysis-agent/agents-md/github.svg)](https://agentmods.dev/instructions/yellowbee686/everything-analysis-agent/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/yellowbee686/everything-analysis-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/yellowbee686/everything-analysis-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/yellowbee686/everything-analysis-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/yellowbee686/everything-analysis-agent/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 443 This file is loaded in full into every session.

When invoked 443 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.

Model	Per session	Once invoked
Fable 5.1	$0.00443	$0.00443
Opus 5.5	$0.00177	$0.00177
Sonnet 5.5	$0.00089	$0.00089
Haiku 4.5	$0.00044	$0.00044

Measured 2mo ago against content hash ca4369015436, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

everything-analysis-agent 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 · 44 lines

What it actually says

AGENTS.md

System Rules

Read this file and the relevant skill or submodule AGENTS.md before making changes.
Communicate with users in Chinese.
Write code, comments, docstrings, and command-facing text in English unless a domain term requires Chinese.
Python code must include type annotations.
Prefer readable, pythonic code.
Follow fail-fast behavior. When compatibility handling is needed, log with logger.error and return a clear error result instead of raising from user-facing helpers.
Prefer built-in collection types such as list and dict over List and Dict.

Repository Purpose

This repository stores analysis-agent assets such as skills, plugins, and MCP integrations.

Docs

Research and design notes live under docs/.
When the target reader is Chinese, docs/ research notes may be written in Chinese.
Include the investigation date and source references for comparative or external research notes.
QMD setup and usage notes live in docs/qmd_usage.md.

Skills

Skills live under skills/<skill-name>/.
Each skill must include SKILL.md with name and description frontmatter.
Keep SKILL.md concise. Put detailed workflows, tool maps, and setup notes in references/.
Put deterministic helper commands in scripts/.
Validate changed skills with:

python3 /Users/bytedance/.codex/skills/.system/skill-creator/scripts/quick_validate.py skills/<skill-name>

If the default python3 does not have PyYAML, use any project virtual environment that provides yaml.

CBETA MCP Submodule

mcp_servers/CbetaMCP is a git submodule pinned to a known commit.
Do not commit virtual environments, caches, logs, or generated Python bytecode from the submodule.
The default local MCP endpoint is http://localhost:18765/mcp/.
Start the CBETA MCP server only when a live CBETA query requires it. Check the endpoint first, then start it on demand.

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.

2mo ago First seen · 44 lines · 443 tokens per session scan A ca4369015436

Subscribe to this mod's changes

everything-analysis-agent AGENTS.md is an instructions file published in the GitHub repository yellowbee686/everything-analysis-agent (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 443 tokens to every session, about $0.0018 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.

Building agents

everything-analysis-agent AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
everything-analysis-agent AGENTS.mdyellowbee686/everything-analysis-agent	Instructions file	2	6mo ago	Apache-2.0	A	443	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

everything-analysis-agent: Instructions file for Codex