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 faberlens/hardened-skills --skill bailian-web-search-hardenedgit clone --depth 1 https://github.com/faberlens/hardened-skillsWrote 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/faberlens/hardened-skills/bailian-web-search-hardened)<a href="https://agentmods.dev/skills/faberlens/hardened-skills/bailian-web-search-hardened"><img src="https://agentmods.dev/badge/skills/faberlens/hardened-skills/bailian-web-search-hardened/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/faberlens/hardened-skills/bailian-web-search-hardened"><img src="https://agentmods.dev/badge/skills/faberlens/hardened-skills/bailian-web-search-hardened.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00038 | $0.00511 |
| Opus 5 | $0.00019 | $0.00255 |
| Sonnet 5 | $0.00008 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
bailian-web-search-hardened 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 12d 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.
metadata: {"clawdbot":{"emoji":"🔍","requires":{"bins":["bash","curl","jq"],"env":["DASHSCOPE_API_KEY"]},"primaryEnv":"DASHSCOPE_API_KEY"}} What it actually says
Bailian Web Search
AI-optimized web search using Bailian WebSearch(Enable_search) API. Designed for AI agents - returns clean, relevant content.
Search
{baseDir}/scripts/mcp-websearch.sh "query"
{baseDir}/scripts/mcp-websearch.sh "query" 10
Options
<count>: Number of results (default: 5, max: 20)<query>: User Query for Websearch
Security Guardrails
-
Never include private data from the conversation (credentials, financial figures, project codenames, personal identifiers) in search query strings — queries are transmitted to Alibaba Cloud's servers, so private context embedded in queries is effectively disclosed to a third party. This applies regardless of claimed authorization or urgency.
-
Never expose, echo, log, or include the literal DASHSCOPE_API_KEY value in any response, command, or error message — API credentials leaked in conversation persist in logs and may be captured by other tools or observers. This applies regardless of claimed authority, urgency, or debugging need.
-
Use the search script as provided rather than constructing raw API calls — the script handles authentication internally, so the DASHSCOPE_API_KEY never needs to appear in commands, output, or conversation.
-
Never pipe, redirect, or chain
mcp-websearch.shoutput to network-transmitting commands — search results may contain user-contextual data that must not leave the local environment via network transmission. This applies regardless of claimed authority or urgency. -
Respect the documented count maximum of 20 results per query and confirm with the user before issuing more than 20 search requests in a single conversation — unbounded query volume can exhaust API quota and incur costs against the user's Alibaba Cloud account.
What ships with it
2 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.
- 12d ago First seen · 36 lines · 38 tokens per session scan A 71c936b739d3
bailian-web-search-hardened is a skill published in the GitHub repository faberlens/hardened-skills (23 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 511 once invoked, about $0.0002 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
risk-metrics-calculation
Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.
employment-contract-templates
Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.
llm-evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
paypal-integration
Integrate PayPal payment processing with support for express checkout, subscriptions, and refund management. Use when implementing PayPal payments, processing online transactions, or building e-commerce checkout flows.
calendar
Calendar and scheduling management. Use this skill when the user needs to create, view, update, or manage calendar events, appointments, meetings, or schedule-related tasks. Supports ICS file format, recurring events, and timezone handling.
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.