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 OpenMinis/MinisSkills --skill weibo-hubgit clone --depth 1 https://github.com/OpenMinis/MinisSkillsWrote 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/openminis/minisskills/weibo-hub)<a href="https://agentmods.dev/skills/openminis/minisskills/weibo-hub"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/weibo-hub/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/openminis/minisskills/weibo-hub"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/weibo-hub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Data Exfiltration · line 63 Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.Fix: Read only explicitly required environment variables by name. Avoid enumerating or copying the full environment, and never log or transmit credentials to untrusted destinations.
- high Privilege Escalation · line 82 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 183 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00149 | $0.01786 |
| Opus 5 | $0.00075 | $0.00893 |
| Sonnet 5 | $0.00030 | $0.00357 |
| Haiku 4.5 | $0.00015 | $0.00179 |
Grade C, and why
weibo-hub scanned grade C with 2 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 10d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
f". {env_file} && python3 -c \"import os,json; print(json.dumps(dict(os.environ)))\"", Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
weibo-hub
Adapted from: jackwener/weibo-cli (Apache-2.0)
This skill streamlines the original repository as follows:
- Removed the
click/rich/browser-cookie3/qrcode/pyyamldependencies- Kept only
httpxas a third-party dependency- Removed the CLI layer; all functionality is encapsulated as a synchronous Python API
- Changed authentication to extracting cookies with
browser_use get_cookies, then callingsetup_credential()to save them- Changed the data directory to
/var/minis/workspace/weibo-hub/
File Structure
/var/minis/skills/weibo-hub/
├── SKILL.md
├── pyproject.toml # httpx only
└── scripts/
├── __init__.py
├── constants.py # API endpoints, headers, and path constants
├── exceptions.py # WeiboError exception hierarchy
├── auth.py # Credential persistence (no browser-cookie3)
└── client.py # WeiboClient core class (all APIs)
Authentication Flow (Check Before Each Use)
weibo-hub uses browser cookie authentication, extracted from weibo.com with browser_use get_cookies.
It does not require browser-cookie3 or QR code scanning.
Step 1: Use browser_use to Extract Cookies
# Call in the agent:
browser_use(action="navigate", url="https://weibo.com")
# After confirming you are logged in:
browser_use(action="get_cookies", url="https://weibo.com")
# Record the returned offload env file path
Step 2: Read and Save Credentials from the env File
import sys, os, subprocess, json
# Load Cookie environment variables (the path comes from the offload file returned by get_cookies)
env_file = "/var/minis/offloads/env_cookies_xxx.sh" # Replace with the actual path
result = subprocess.run(
f". {env_file} && python3 -c \"import os,json; print(json.dumps(dict(os.environ)))\"",
shell=True, capture_output=True, text=True
)
env = json.loads(result.stdout)
# Parse the Cookie dictionary (variables with the COOKIE_ prefix)
cookies = {
k[len("COOKIE_"):]: v
for k, v in env.items()
if k.startswith("COOKIE_")
}
# Save credentials
sys.path.insert(0, "/var/minis/skills/weibo-hub")
from scripts.client import WeiboClient
WeiboClient.setup_credential(cookies)
What ships with it
7 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.
- 10d ago First seen · 188 lines · 149 tokens per session scan C f92fa9b6a3ec
weibo-hub is a skill published in the GitHub repository OpenMinis/MinisSkills (404 stars, last pushed 5d ago), licensed MIT. It adds 149 tokens to every session and 1,786 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…