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/0oooooooo0/skillless/skill-searchnpx skills add 0oooooooo0/skillless --skill skill-searchgit clone --depth 1 https://github.com/0oooooooo0/skilllessWhat 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 | $0.00000 | $0.00509 |
| Opus 5 | $0.00000 | $0.00254 |
| Sonnet 5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: skill-search
Search for Claude Code skills across multiple sources.
user-invocable: false description: Searches for relevant skills across local installation, skills.sh directory, and GitHub. Called by other skills or commands. allowed-tools: [Read, Glob, Grep, Bash, WebSearch]
Instructions
When called with a search query, search these 3 sources and return consolidated results.
Source 1: Local Installed Skills
Search already-installed skills:
Glob: ~/.claude/skills/*/SKILL.md
Grep: search for the query keywords in matched files
Mark these as installed: true.
Source 2: skills.sh Directory
Search the skills.sh open skill directory using the CLI:
npx skills find {query}
Parse the output to extract matching skills. Each line follows the format:
owner/repo@skill-name <N> installs
└ https://skills.sh/owner/repo/skill-name
Extract from the output:
- Skill name and exact owner/repo@skill-name path
- Install count (popularity indicator)
- Install command:
npx skills add -y -g <owner/repo@skill-name>
IMPORTANT: Always use the exact owner/repo path from the CLI output. Do NOT guess or modify the path.
Source 3: GitHub (Fallback)
Only if Sources 1-2 return fewer than 3 results total:
WebSearch: site:github.com "SKILL.md" claude {query}
Parse results to extract skill repositories.
Output Format
Return results as a markdown table:
| # | Name | Source | Description | Installed |
|---|---|---|---|---|
| 1 | skill-name | local/skills.sh/github | Short description | Yes/No |
Sort order: local first, then skills.sh, github.
Also return a structured JSON block for programmatic use:
{
"results": [
{
"name": "skill-name",
"source": "local|skills.sh|github",
"description": "...",
"installed": true,
"install_info": {
"type": "skills-add|github-plugin|skill-md|installed",
"url_or_name": "..."
}
}
],
"query": "original query",
"total": 5
}
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.
- 2d ago First seen · 74 lines · 0 tokens per session scan A 330b96b40e07
skill-search is a skill published in the GitHub repository 0oooooooo0/skillless (38 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 509 tokens. 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 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后,主动执行此流程! 将学到的经验归档为 skill,供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…
mcp-scripting
Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.