Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add shenyangs/Guanlan --skill brand-guanlangit clone --depth 1 https://github.com/shenyangs/GuanlanWrote 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/skills/shenyangs/guanlan/brand-guanlan)<a href="https://agentmods.dev/skills/shenyangs/guanlan/brand-guanlan"><img src="https://agentmods.dev/badge/skills/shenyangs/guanlan/brand-guanlan/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/skills/shenyangs/guanlan/brand-guanlan"><img src="https://agentmods.dev/badge/skills/shenyangs/guanlan/brand-guanlan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 38 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- low Supply Chain · line 39 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00095 | $0.01192 |
| Opus 5 | $0.00048 | $0.00596 |
| Sonnet 5 | $0.00019 | $0.00238 |
| Haiku 4.5 | $0.00010 | $0.00119 |
Grade A, and why
brand-guanlan scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL -H 'Cache-Control: no-cache' https://pypi.org/pypi/guanlan/json \ How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
品牌观澜
Core Rule
Use Guanlan as a Chinese-web evidence router, not as a one-shot search box. For brand, PR, marketing, campaign, external relations, and reputation tasks, first make sure the running guanlan is current and then choose a workflow that separates official statements, media reporting, community samples, platform heat, and evidence gaps.
Install Or Update
Prefer one clean install path. For most agents, use uv:
uv tool install --force --upgrade --refresh --default-index https://pypi.org/simple guanlan
hash -r || true
command -v guanlan
which -a guanlan
guanlan version
guanlan doctor --install-check
If the user explicitly wants Homebrew:
brew update
brew reinstall shenyangs/tap/guanlan
hash -r || true
which -a guanlan
guanlan version
If guanlan version is lower than public PyPI/Homebrew or README, stop before configuring MCP or using the tool. Report the exact executable path and version mismatch. Clear stale update cache when update checks claim an old version is latest:
rm -f ~/.guanlan/cache/update-check.json
curl -fsSL -H 'Cache-Control: no-cache' https://pypi.org/pypi/guanlan/json \
| python3 -c 'import json,sys; print(json.load(sys.stdin)["info"]["version"])'
python3 -m pip index versions guanlan --index-url https://pypi.org/simple
For a repeatable full install/update smoke, run:
bash scripts/install_or_update_guanlan.sh
Read references/install-update.md when a user reports version drift, stale PyPI, Homebrew lag, multiple guanlan paths, or a screenshot saying an old version is latest.
Post-Update Smoke
After any install or update, run:
guanlan capabilities
guanlan doctor --install-check
guanlan doctor --trace
guanlan search "人工智能 政策" --profile china --limit 5 --trace
guanlan hotnews today --limit 5 --trends
Treat --limit 5 as smoke only. For real communications research, rerun with --limit 80.
Workflow Selection
Use this fast routing:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 99 lines · 95 tokens per session scan A ff9272140737
brand-guanlan is a skill published in the GitHub repository shenyangs/Guanlan (55 stars, last pushed 11d ago), licensed MIT. It adds 95 tokens to every session and 1,192 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…
generate-image
Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics…
gpt-image-gen
MUST read before generating images. Prompt-crafting guide for gpt-image-2.5 covering tool routing (native imagegeneration server tool vs the generateimage tool), model and quality selection, prompt structure, exact text rendering, reference-image editing, transparent assets, output formats, and multi-turn refinement.
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
coding-agent-extension-worker
Implements a single feature in the pi-mono todotools builtin extension work. Use for refactoring, continuation runtime, config resolver, prompt builder, test authoring, golden snapshots, CHANGELOG entries, and harness helpers. Does NOT do manual tmux QA.