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 gyuch-an02/claude-omakase --skill write-a-skillgit clone --depth 1 https://github.com/gyuch-an02/claude-omakaseWrote 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/gyuch-an02/claude-omakase/write-a-skill)<a href="https://agentmods.dev/skills/gyuch-an02/claude-omakase/write-a-skill"><img src="https://agentmods.dev/badge/skills/gyuch-an02/claude-omakase/write-a-skill/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/gyuch-an02/claude-omakase/write-a-skill"><img src="https://agentmods.dev/badge/skills/gyuch-an02/claude-omakase/write-a-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00035 | $0.00396 |
| Opus 5 | $0.00017 | $0.00198 |
| Sonnet 5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
write-a-skill 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 11d 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
Write a Skill
Help the user turn a recurring workflow into a reusable Claude Code skill.
Process
- Understand the workflow: ask what task the user repeats. What triggers it? What does success look like?
- Draft a SKILL.md:
- YAML frontmatter:
name,description,triggers(3-5 phrases that activate it) - Body: concise instructions Claude follows when the skill activates
- Include steps, examples, and what NOT to do
- YAML frontmatter:
- Write the file: create
~/.claude/skills/<name>/SKILL.mdwith the draft - Test it: ask the user to start a new session and trigger the skill by saying one of the trigger phrases
- Iterate: refine based on what felt off in the test
Good skill anatomy
---
name: my-skill
description: One sentence. When to use it.
triggers: ["phrase 1", "phrase 2", "phrase 3"]
---
# My Skill
What Claude does when this skill activates. Be concrete.
## Steps
1. ...
2. ...
## Examples
**User:** [trigger phrase]
**Claude:** [response]
Tips
- Keep it under 200 lines — skills should be focused
- Triggers should be natural phrases the user actually says
- One skill = one workflow. Don't bundle unrelated things.
- If the skill needs reference data (e.g. API docs), add a separate file and reference it
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.
- 11d ago First seen · 50 lines · 35 tokens per session scan A 4723f3e8d087
write-a-skill is a skill published in the GitHub repository gyuch-an02/claude-omakase (8 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 396 once invoked, about $0.0002 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
pipeline-report
A procedure for reporting the state of an amoCRM sales funnel, a set of stages that deals move through before they are won or lost. It groups deals by stage and value and checks how long they have been inactive.
complete-task
A workflow for completing or reassigning ELMA365 business-process tasks. ELMA365 is a business process management system in which tasks move a process from one step to the next.
gigachat-embeddings
A text-embedding workflow for GigaChat. Embeddings are numeric representations that let software compare meanings rather than only matching exact words.
gigachat-image
An image-generation workflow for GigaChat, an AI service that creates pictures from text descriptions. It also supports checking the remaining usage allowance and adding an uploaded reference image.
employer-research
An employer research tool for hh.ru, a Russian job board. It builds a profile from the employer's description, industry, active vacancies, and disclosed salary data.
vacancy-details
A workflow for examining a single hh.ru job listing and finding similar vacancies. hh.ru is a Russian job board; the workflow also explains coded requirements, location details, and salary statistics.