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 commands/girofu/skill-fetch/fetch-skill-configgit clone --depth 1 https://github.com/girofu/skill-fetchWrote 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/commands/girofu/skill-fetch/fetch-skill-config)<a href="https://agentmods.dev/commands/girofu/skill-fetch/fetch-skill-config"><img src="https://agentmods.dev/badge/commands/girofu/skill-fetch/fetch-skill-config.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 | $0.00014 | $0.00765 |
| Opus 5 | $0.00007 | $0.00382 |
| Sonnet 5 | $0.00003 | $0.00153 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
fetch-skill-config 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fetch Skill Config
Interactive setup for skill-fetch API keys. Configures ~/.claude/skills/.fetch-config.json and optionally installs the SkillsMP MCP server.
Procedure
Step 1: Read existing config
Read the file ~/.claude/skills/.fetch-config.json. If it exists, parse the JSON. If it doesn't exist, treat all keys as empty.
Step 2: Display current status
Show the user a status table:
## API Key Status
| Key | Status | Registry |
|-----|--------|----------|
| SKILLSMP_API_KEY | [SET/NOT SET] | SkillsMP (Sources 1-2) - Recommended |
| SKILLHUB_API_KEY | [SET/NOT SET] | SkillHub (Source 8) - Optional |
| SKILLS_DIRECTORY_API_KEY | [SET/NOT SET] | Skills Directory (Source 9) - Optional |
Sources 3-7 (GitHub, Anthropic Skills, ClawSkillHub, skills.sh, PolySkill) work without API keys.
Step 3: Ask which keys to configure
Use AskUserQuestion to ask: "Which API keys would you like to configure? (enter numbers, e.g. 1,2 or all)"
Options:
SKILLSMP_API_KEY— Get from skillsmp.com (free, recommended)SKILLHUB_API_KEY— Optional, for SkillHub APISKILLS_DIRECTORY_API_KEY— Optional, for Skills Directory API
If the user says "none" or "skip", end here.
Step 4: Collect keys one by one
For each selected key, use AskUserQuestion to ask:
- SKILLSMP_API_KEY: "Enter your SkillsMP API key (get one free at https://skillsmp.com):"
- SKILLHUB_API_KEY: "Enter your SkillHub API key:"
- SKILLS_DIRECTORY_API_KEY: "Enter your Skills Directory API key:"
If user enters empty or "skip" for a key, skip it (keep existing value if any).
Step 5: Write config file
Merge new values with existing config (preserve keys the user didn't change). Write the result to ~/.claude/skills/.fetch-config.json:
{
"SKILLSMP_API_KEY": "...",
"SKILLHUB_API_KEY": "...",
"SKILLS_DIRECTORY_API_KEY": "..."
}
Only include keys that have non-empty values.
Step 6: SkillsMP MCP server setup
If SKILLSMP_API_KEY was set (new or existing), check if the SkillsMP MCP server is already available by checking if skillsmp_search MCP tools exist in the current session.
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 · 87 lines · 14 tokens per session scan A 00e4082a22e2
fetch-skill-config is a command published in the GitHub repository girofu/skill-fetch (30 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 765 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 2026-08-30.
Other commands, from other repositories
sync-claude-user-plugins
Copy commands and skills from user-scope Claude plugins into the global OpenCode directories.
install-recommended-skills-globally
Install recommended productivity skills (grill-me, handoff, writing-great-skills) globally via gh skill install.
sync-claude-skills
Copy skills and agents from project-scope Claude plugins into .opencode.
persona
応答口調のキャラクターを切り替える.
persona-compress
自然言語ファイルを圧縮して入力トークンを削減する.
persona-new
新しいペルソナのキャラクターを作成する.