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/gyuch-an02/claude-omakase/python-clinpx skills add gyuch-an02/claude-omakase --skill python-cligit clone --depth 1 https://github.com/gyuch-an02/claude-omakaseWhat 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 | $0.00008 | $0.00266 |
| Opus 5 | $0.00004 | $0.00133 |
| Sonnet 5 | $0.00002 | $0.00053 |
| Haiku 4.5 | $0.00001 | $0.00027 |
Grade A, and why
[object Object] 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.
What it actually says
{{slug}}
What this skill does
{{task_description}}
When to activate
Use this skill when the user:
{{triggers_bullets}}
Steps
- Confirm the target script path and any required arguments with the user.
- Check that the virtual environment is active or dependencies are installed:
python -m pip show <package> 2>/dev/null | grep Version || echo "not installed" - Run the script, capturing stdout and stderr:
python <script.py> <args> - If exit code != 0, surface the error with context. Common fixes:
- Missing dependency →
pip install <package> - Wrong Python version → check
python --version
- Missing dependency →
- Show the user the output or output file path when done.
Examples
User: [describe a concrete user request here]
Claude: Running…
python <script.py> <args>
Done. [describe the result]
Generated by claude-omakase. Edit this file to replace placeholder steps with your actual script.
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 · 49 lines · 8 tokens per session scan A f08df076e890
[object Object] is a skill published in the GitHub repository gyuch-an02/claude-omakase (8 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 266 once invoked, about $0.0000 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
zephex
Use when the user works in their own codebase with Zephex MCP or the zephex terminal CLI: onboard a repo, find or read code, map architecture, run or diagnose tests, check packages before install, audit a live HTTPS URL, remember project facts, or debug multi-file issues — including when they only say "use Zephex,"…
computer-use-macos
Top-level macOS computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.
computer-use-windows
Top-level Windows computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.
computer-use-linux
Top-level Linux computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
convex-insights
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.