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/stevesolun/micro-skills/skill-usegit clone --depth 1 https://github.com/stevesolun/micro-skillsWrote 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/stevesolun/micro-skills/skill-use)<a href="https://agentmods.dev/commands/stevesolun/micro-skills/skill-use"><img src="https://agentmods.dev/badge/commands/stevesolun/micro-skills/skill-use.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 | $0.00022 | $0.00543 |
| Opus 5 | $0.00011 | $0.00271 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
skill-use scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Activate the converted micro-skill pipeline for "$ARGUMENTS".
Steps
-
Find the converted skill: Look for
${CLAUDE_PLUGIN_DATA}/converted/$ARGUMENTS/SKILL.md. If it doesn't exist, report: "No converted pipeline found for '$ARGUMENTS'. Run /skill-list to see available conversions, or /skill-convert to create one." -
Staleness check: Read
${CLAUDE_PLUGIN_DATA}/converted/$ARGUMENTS/original-hash.txtto get the stored hash. Read${CLAUDE_PLUGIN_DATA}/registry.jsonto get thesourcePathfor this skill.- If
sourcePathexists and is not "scaffolded":- Compute current hash (cross-platform):
(sha256sum "<sourcePath>" 2>/dev/null || shasum -a 256 "<sourcePath>" 2>/dev/null || certutil -hashfile "<sourcePath>" SHA256 2>/dev/null | head -2 | tail -1) | cut -d' ' -f1 - Compare to stored hash
- If different: the original skill has been updated since conversion.
- Show the user: "The original skill at has changed since this pipeline was created. The converted pipeline may be outdated."
- Ask the user: "Would you like to reconvert the skill to pick up the changes? (This will update the pipeline while preserving your failure-log.md)"
- If user agrees: run the reconversion (read the updated original, reclassify sections, rewrite pipeline files, update hash, preserve failure-log.md)
- If user declines: proceed with the existing pipeline as-is
- Compute current hash (cross-platform):
- If
sourcePathno longer exists: warn "Original skill file no longer exists at . Pipeline may be orphaned."
- If
-
Load the pipeline: Read
${CLAUDE_PLUGIN_DATA}/converted/$ARGUMENTS/SKILL.mdand follow its instructions exactly -- execute the gated pipeline stage by stage (Scope, Plan, Build, Check, Deliver). -
Read the failure log first: Before starting the pipeline, read
${CLAUDE_PLUGIN_DATA}/converted/$ARGUMENTS/failure-log.mdand the project-levelfailure-log.mdif it exists. Every pattern is a mandatory constraint.
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.
- 4d ago First seen · 28 lines · 22 tokens per session scan A 155f9fd0f968
skill-use is a command published in the GitHub repository stevesolun/micro-skills (11 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 543 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
autoworker
Start the autoworker execution workflow for any non-trivial task.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.