What is Guanlan CLAUDE.md?

Project instructions for Guanlan, a command-line research tool that finds, reads, observes, and archives Chinese-language web sources for AI agents.

Use them when modifying Guanlan’s agent behavior, research tools, workflows, browser evidence handling, tests, benchmarks, or release automation.

They give contributors the project structure, required reference documents, development commands, and quality checks needed to change the system safely.

How shenyangs/Guanlan configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shenyangs/Guanlan. 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/shenyangs/Guanlan/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/shenyangs/Guanlan

Made for: Claude Code.

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/shenyangs/guanlan/claude-md/github.svg)](https://agentmods.dev/instructions/shenyangs/guanlan/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/shenyangs/guanlan/claude-md"><img src="https://agentmods.dev/badge/instructions/shenyangs/guanlan/claude-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/shenyangs/guanlan/claude-md"><img src="https://agentmods.dev/badge/instructions/shenyangs/guanlan/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 867 This file is loaded in full into every session.

When invoked 867 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	$0.00867	$0.00867
Opus 5.5	$0.00347	$0.00347
Sonnet 5.5	$0.00173	$0.00173
Haiku 4.5	$0.00087	$0.00087

Measured 2mo ago against content hash b804ac1f84d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Guanlan CLAUDE.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.

CLAUDE.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project

观澜 / Guanlan — CLI-first, read-first Chinese-web research substrate for AI agents.

Positioning: source router + webpage reader + hotnews/feeds observer + evidence packet builder + local archive/RAG bridge, with explicit authorization boundaries.

License: MIT | Current version: 0.5.10 | Stage: Alpha

Durable Memory Surfaces

Before changing Agent behavior, MCP tools, workflows, browser-assisted evidence, benchmarks, or release automation, reread:

AGENTS.md
docs/agent-playbook.md
docs/agent-usage.md
guanlan/skill/SKILL.md

These files define how downstream agents should actually operate Guanlan.

Development Commands

uv sync --all-extras --dev
uv run guanlan version
uv run ruff check guanlan tests
uv run pytest
scripts/pre_release_status.sh

Release-quality checks:

guanlan quality foundational
guanlan quality coverage
guanlan quality regression
guanlan quality robustness
guanlan quality backend-fixtures
guanlan eval benchmark
scripts/release_gate.sh

Core Structure

guanlan/cli.py — CLI entry point and command dispatch
guanlan/webtools.py — public search/read/research orchestration
guanlan/router.py — local intent routing and source-role planning
guanlan/source_registry.py / guanlan/source_packs.py — source identity, roles, and curated packs
guanlan/browser_assist.py — read-only browser-assisted evidence planning
guanlan/archive.py — local SQLite archive, quality audit, RAG/Wiki export, browser-note ingest
guanlan/hotnews.py / guanlan/feeds.py — hotnews, RSS, and trend observation
guanlan/integrations/mcp_server.py — MCP integration
guanlan/skill/ — packaged Agent skill surfaces
docs/ — public docs and agent playbooks
tests/ — unit, contract, regression, robustness, CLI, MCP, and release smoke tests

Conventions

Python 3.10+.
Commit subjects, changelog entries, and release notes are Chinese-first. Conventional prefixes such as feat: / fix: / docs: are fine.
Keep code identifiers English, user-facing CLI/docs Chinese-first where appropriate.
Do not shrink default result pools or remove agent-facing evidence metadata without an explicit migration note and tests.
Treat route plans, source cards, risk tags, quality reports, trace, and archive metadata as downstream Agent contracts.
Prefer graceful degradation over silent failure: blocked backend, WAF, captcha, dynamic shell, stale cache, partial salvage, and external fetch strategy must be visible.

Read the full file on GitHub · 84 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.

2mo ago First seen · 84 lines · 867 tokens per session scan A b804ac1f84d0

Subscribe to this mod's changes

Guanlan CLAUDE.md is an instructions file published in the GitHub repository shenyangs/Guanlan (57 stars, last pushed 3d ago), licensed MIT. It adds 867 tokens to every session, about $0.0035 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 2026-08-30.

Python Research ai-agent chinese-web cli llm-tools mcp

Guanlan CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Guanlan CLAUDE.mdshenyangs/Guanlan	Instructions file	57	3d ago	MIT	A	867	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Guanlan: Instructions file for Claude Code