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 agentmods add skills/skillscatalog/registry/skill-searchnpx skills add SkillsCatalog/registry --skill skill-searchgit clone --depth 1 https://github.com/SkillsCatalog/registryWrote 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/skillscatalog/registry/skill-search)<a href="https://agentmods.dev/skills/skillscatalog/registry/skill-search"><img src="https://agentmods.dev/badge/skills/skillscatalog/registry/skill-search.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00549 |
| Opus 5 | $0.00010 | $0.00275 |
| Sonnet 5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
skill-search 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 5d 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.
What it actually says
Instructions
Use this skill to search the skillscatalog.ai catalog for skills.
Prerequisites
Skill Key - Get your key at https://skillscatalog.ai/settings/skill-keys
How to Use
Search for skills:
Search the catalog for PDF tools
Get skill details:
python3 search_catalog.py --get anthropic/document-skills
List skills by vendor:
python3 search_catalog.py --vendor anthropic
Output
Found 5 skills matching "pdf tools":
1. anthropic/document-skills
Create and manipulate PDF documents
Grade: A | Vendor: Anthropic
2. jeffrschneider/pdf-tools
PDF conversion and extraction
Grade: B | Vendor: jeffrschneider
3. acme/office-suite
Office document processing including PDF
Grade: A | Vendor: Acme Corp
JSON Output
python3 search_catalog.py "pdf tools" --json
Returns:
{
"query": "pdf tools",
"count": 5,
"results": [
{
"vendorKey": "anthropic",
"skillKey": "document-skills",
"skillName": "Document Skills",
"description": "Create and manipulate PDF documents",
"rank": 0.95
}
]
}
Examples
Basic search:
User: Find skills for creating spreadsheets
Agent: Searching catalog for "spreadsheets"...
Found 3 skills:
1. anthropic/document-skills - Excel and spreadsheet creation
2. datatools/xlsx-generator - Generate XLSX files
3. office/sheets - Google Sheets integration
Get skill details:
User: Get details for anthropic/document-skills
Agent: Fetching skill details...
anthropic/document-skills
Description: Create and manipulate PDF documents
Version: 1.2.0
Safety Grade: A
Vendor: Anthropic
Limitations
- Requires internet connection
- Search results limited to public catalog
- Private org catalogs require org membership
Dependencies
- Python 3.9+
- requests library
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.
- 5d ago First seen · 117 lines · 19 tokens per session scan A a58adfb365ca
skill-search is a skill published in the GitHub repository SkillsCatalog/registry (1 stars, last pushed 8mo ago), licensed MIT. It adds 19 tokens to every session and 549 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
bilibili_search
Search for videos on Bilibili using keyword queries generated from user interests.
skill-router
Find the right skill in the PCL standard library and compose several when a task spans domains. Use when the user asks which skill applies, cannot find a capability, wants to know what the library covers, is starting a task that spans several domains, or when the task involves choosing between overlapping skills…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Uses reskill as the package manager.
dataset-discovery
Multi-source ML dataset discovery.
atlan-mcp
MCP server for interacting with Atlan services including asset search, updates, and lineage traversal for comprehensive data governance and discovery.
explorer
Quickly search and navigate the codebase - Use when you need to quickly find files, search for patterns, or locate specific code without deep analysis.