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 MemTensor/skills-vote --skill curlsearchgit clone --depth 1 https://github.com/MemTensor/skills-voteWrote 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/memtensor/skills-vote/curlsearch)<a href="https://agentmods.dev/skills/memtensor/skills-vote/curlsearch"><img src="https://agentmods.dev/badge/skills/memtensor/skills-vote/curlsearch/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/memtensor/skills-vote/curlsearch"><img src="https://agentmods.dev/badge/skills/memtensor/skills-vote/curlsearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00584 |
| Opus 5.5 | $0.00022 | $0.00234 |
| Sonnet 5.5 | $0.00011 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
curl-search 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 1mo 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.
name: curl-search What it actually says
Curl Search Skill
Web search using curl + multiple search engines. This skill provides a lightweight alternative when dedicated search APIs are unavailable.
Supported Search Engines
| Engine | Alias | Description |
|---|---|---|
| Baidu | bd | Fast for China, default option |
| g | Requires proxy/VPN in China | |
| Bing | b | Microsoft Bing |
| DuckDuckGo | ddg | Privacy-focused search |
Usage Examples
Search for OpenClaw tutorial
Google search AI development
Find Python tutorials with bing
Requirements
- curl - Command-line HTTP client
- python3 - For URL encoding
Security Features
This skill includes several security enhancements:
1. Input Sanitization
Removes dangerous shell metacharacters that could be exploited:
sanitize_input() {
local input="$1"
echo "$input" | sed 's/[^a-zA-Z0-9 \_\-\.\~\x{4e00}-\x{9fff}]//g'
}
2. Command Injection Protection
- Validates search engine selection
- Restricts max results to 1-50
- Checks for empty input after sanitization
3. URL Encoding
Uses Python's urllib.parse with safe='' parameter to properly encode special characters.
Installation
# Install via ClawHub
clawhub install curl-search
# Or manually
cd your-skills-dir
tar -xzf curl-search.tar.gz
Configuration
Set default search engine:
export SEARCH_ENGINE=google
Set max results:
export MAX_RESULTS=5
Limitations
- Search results come from public search engines
- May be blocked by anti-scraping measures
- Google requires proxy/VPN in China
Version History
- 2.0.0 - Security enhancements added
- Input sanitization
- Command injection protection
- URL encoding improvements
- 1.0.0 - Initial release
What ships with it
1 file 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.
- 1mo ago First seen · 105 lines · 55 tokens per session scan A 4635715b0f11
curl-search is a skill published in the GitHub repository MemTensor/skills-vote (305 stars, last pushed 22d ago), licensed MIT. It adds 55 tokens to every session and 584 once invoked, about $0.0002 per session on Opus 5.5. 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
agentsop-llm-tool-idempotency
Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the tool must promise…
agentsop-map-reduce-fanout
Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in parallel, then combine". Activates when the coder agent is about to process N items with N LM calls (per-doc summarize, per-query retrieve, per-candidate rank, parallel tool fan-out). Encodes…
agentsop-prompt-history-inspect
Tool skill — the first move in any LM-debugging session: dump the actual rendered prompt the framework sent to the model, before changing anything else. Activate when an LM call produced an unexpected output (wrong answer, schema violation, refusal, truncation, cost spike, latency spike, infinite loop, "model got…
LEAP
LEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.
agentsop-bounded-loop
Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every team relearns expensively: the LM in the loop is NEVER a reliable terminator. Termination must be provided by an…
agentsop-code-execution-decision
Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent step that does…