skill-convert

skill-convert is a command for coding agents from stevesolun/micro-skills. It costs 38 tokens per session (1,062 once invoked), scanned B, original, MIT.

A command that turns a large, single-file skill into a set of smaller workflow steps with checks between them. It accepts a skill name or a file path and stores the result in the plugin's data directory.

In plain words
What is it for?
Use it to convert project, user, agent, or plugin skills into gated micro-skill pipelines.
Why use it?
It helps break a monolithic skill into smaller stages that can be checked as the work progresses. It also records the original file's hash so later changes can be detected.

Command

Part of the micro-skill-pipeline plugin — 1 skill, 7 commands, 1 agent, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add commands/stevesolun/micro-skills/skill-convert
Clone the repo
git clone --depth 1 https://github.com/stevesolun/micro-skills

Or install micro-skill-pipeline, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 1 agent, 2 hooks.

Wrote 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.

agentmods badge for skill-convert

README.md
[![agentmods](https://agentmods.dev/badge/commands/stevesolun/micro-skills/skill-convert.svg)](https://agentmods.dev/commands/stevesolun/micro-skills/skill-convert)
Your own site
<a href="https://agentmods.dev/commands/stevesolun/micro-skills/skill-convert"><img src="https://agentmods.dev/badge/commands/stevesolun/micro-skills/skill-convert.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,062 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.01062
Opus 5 $0.00019 $0.00531
Sonnet 5 $0.00008 $0.00212
Haiku 4.5 $0.00004 $0.00106

Measured 5d ago against content hash 485b594d315f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

skill-convert scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

4. `~/.claude/plugins/` -- search recursively: `find ~/.claude/plugins -path "*/$ARGUMENTS/SKILL.md" -type f`
micro-skill-pipeline/commands/skill-convert.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convert a skill into a micro-skill pipeline. $ARGUMENTS can be a skill name or a file path.

Step 0: Resolve the skill

If $ARGUMENTS looks like a file path (contains / or \ or ends in .md), use it directly.

Otherwise, treat it as a skill name and search for it in these locations (stop at first match):

  1. .claude/skills/$ARGUMENTS/SKILL.md (project-level)
  2. ~/.claude/skills/$ARGUMENTS/SKILL.md (user-level)
  3. ~/.claude/.agents/skills/$ARGUMENTS/SKILL.md (agent skills)
  4. ~/.claude/plugins/ -- search recursively: find ~/.claude/plugins -path "*/$ARGUMENTS/SKILL.md" -type f
  5. If multiple matches found, list them and ask the user which one to convert.
  6. If no match found, report: "Could not find skill '$ARGUMENTS'. Provide the full path instead."

Steps

  1. Read the resolved skill file. Compute SHA256 hash (cross-platform): (sha256sum "<path>" 2>/dev/null || shasum -a 256 "<path>" 2>/dev/null || certutil -hashfile "<path>" SHA256 2>/dev/null | head -2 | tail -1) | cut -d' ' -f1

  2. Classify each section of the source:

    • "Do this" instructions -> Build step (03-build.md)
    • "Check/avoid/ensure" instructions -> convert to YES/NO questions using the Gate Question Extraction Rules below, then write to check-gates.md
    • Reference data (tables, lists, examples) -> Separate reference files
    • QA/validation prose (non-convertible to YES/NO) -> universal check context in 04-check.md
    • Context/scope instructions -> Scope step (01-scope.md)
  3. Determine the skill name from the source filename or directory name.

  4. Create the pipeline directory: ${CLAUDE_PLUGIN_DATA}/converted/<skill-name>/

  5. Build the pipeline files (each under 40 lines):

    • SKILL.md -- orchestrator referencing the 5 stages, under 30 lines
    • references/01-scope.md -- constraints relevant to this skill's domain
    • references/02-plan.md -- design step specific to this skill's output type
    • references/03-build.md -- execution instructions from the original
    • references/04-check.md -- universal checks plus extracted domain checks
    • references/05-deliver.md -- finalization steps
    • check-gates.md -- domain-specific YES/NO gate questions
    • failure-log.md -- seeded with "avoid" items from the original skill

Read the full file on GitHub · 75 lines

Changes

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.

  1. 5d ago First seen · 75 lines · 38 tokens per session scan B 485b594d315f

Subscribe to this mod's changes

skill-convert is a command published in the GitHub repository stevesolun/micro-skills (11 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,062 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.