cuc-literature-mcp: Instructions file for Codex

AGENTS.md

cuc-literature-mcp AGENTS.md is an instructions file for Codex, OpenCode from SHENAO1/cuc-literature-mcp. It costs 850 tokens per session, scanned B, original, MIT.

Repository instructions for installing, configuring, running, diagnosing, updating, or removing the CUC literature-search MCP server and its related skill. The repository concerns research-paper searches for China’s Communication University.

In plain words
What is it for?
Guiding setup and maintenance of the CUC literature tools, including their installation, operation, updates, troubleshooting, and removal.
Why use it?
They define the required workflow and safety boundaries, including how to handle authentication, preserve existing records, and avoid exposing private browser data.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: reads ~/.codex or $CODEX_HOME, but also the file is AGENTS.md. Also seen: mentions Codex; $skill-name invocation.

This is SHENAO1/cuc-literature-mcp's own configuration. It tells Codex and OpenCode how to work on cuc-literature-mcp 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 cuc-literature-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SHENAO1/cuc-literature-mcp. 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/SHENAO1/cuc-literature-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/SHENAO1/cuc-literature-mcp

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 cuc-literature-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shenao1/cuc-literature-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/shenao1/cuc-literature-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/shenao1/cuc-literature-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/shenao1/cuc-literature-mcp/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 cuc-literature-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shenao1/cuc-literature-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/shenao1/cuc-literature-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 850 This file is loaded in full into every session.
When invoked 850 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00850 $0.00850
Opus 5 $0.00425 $0.00425
Sonnet 5 $0.00170 $0.00170
Haiku 4.5 $0.00085 $0.00085

Measured 11d ago against content hash 266f95afe74c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

cuc-literature-mcp AGENTS.md scanned grade B with 1 finding 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 11d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

5. Run the platform installer with the URL as an argument. Do not hand-edit `~/.codex/config.toml` unless `codex mcp add` is unavailable.
AGENTS.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex repository instructions

This repository contains a local STDIO MCP plus a repository Skill for CUC SCI literature search. When a user asks you to install, configure, run, diagnose, update, or uninstall it, follow these instructions.

Safety boundaries

  • Never read, print, copy, commit, archive, or upload .runtime/chrome-profile, browser cookies, login databases, passwords, session tokens, or verification codes.
  • Never ask the user to send a password, Cookie, or CAPTCHA answer. Open the dedicated visible browser and let the user complete authentication.
  • Never copy or publish output/pdfs; users are responsible for publisher and institutional-license terms.
  • Never set the write target to the formal source sheet 工作表1. The default write target is MCP测试.
  • Do not bypass authentication, CAPTCHA, paywalls, institutional access controls, or attachment limits.
  • Do not edit unrelated root CSV files; they are intentionally ignored.
  • Preserve all other MCP entries in the user's Codex configuration. Installers may replace only the exact cuc-literature entry.

Installation workflow

  1. Read README.md and the platform guide under docs/.
  2. Detect the host platform. Prefer native PowerShell on Windows because this project drives a visible local browser. Use scripts/install.ps1 on Windows and scripts/install.sh on macOS.
  3. Check node --version, npm --version, codex --version, and the availability of Chrome or Edge. Node.js must be 20 or newer.
  4. Ask for exactly one required value if it is not already supplied: a Tencent Sheets URL under https://docs.qq.com/sheet/ for which the user has edit permission. Ask whether to use Chrome or Edge only when it cannot be inferred.
  5. Run the platform installer with the URL as an argument. Do not hand-edit ~/.codex/config.toml unless codex mcp add is unavailable.
  6. Run npm run doctor and codex mcp get cuc-literature. Report concrete failures and use docs/TROUBLESHOOTING.md.
  7. Run npm run login. This is intentionally interactive. Pause while the user completes WOS, IEEE, Tencent Docs, or school SSO login in the dedicated browser, then let them press Enter.
  8. Restart ChatGPT/Codex after MCP registration. Open a new session in this repository so .agents/skills/cuc-literature-search is discovered.
  9. Give the user the exact first-use prompt from README.

Read the full file on GitHub · 56 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. 11d ago First seen · 56 lines · 850 tokens per session scan B 266f95afe74c

Subscribe to this mod's changes

cuc-literature-mcp AGENTS.md is an instructions file published in the GitHub repository SHENAO1/cuc-literature-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 850 tokens to every session, about $0.0042 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens