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.
git 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-convert)<a href="https://agentmods.dev/commands/stevesolun/micro-skills/skill-convert"><img src="https://agentmods.dev/badge/commands/stevesolun/micro-skills/skill-convert/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/commands/stevesolun/micro-skills/skill-convert"><img src="https://agentmods.dev/badge/commands/stevesolun/micro-skills/skill-convert.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.01062 |
| Opus 5.5 | $0.00015 | $0.00425 |
| Sonnet 5.5 | $0.00008 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade B, and why
skill-convert scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. `~/.claude/plugins/` -- search recursively: `find ~/.claude/plugins -path "*/$ARGUMENTS/SKILL.md" -type f` 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 $ARGUMENTS looks like a file path (contains / or \ or ends in .md), use it directly.
Otherwise, treat it as a skill name and search for it in these locations (stop at first match):
.claude/skills/$ARGUMENTS/SKILL.md(project-level)~/.claude/skills/$ARGUMENTS/SKILL.md(user-level)~/.claude/.agents/skills/$ARGUMENTS/SKILL.md(agent skills)~/.claude/plugins/-- search recursively:find ~/.claude/plugins -path "*/$ARGUMENTS/SKILL.md" -type f- If multiple matches found, list them and ask the user which one to convert.
- If no match found, report: "Could not find skill '$ARGUMENTS'. Provide the full path instead."
Steps
-
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 -
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)
-
Determine the skill name from the source filename or directory name.
-
Create the pipeline directory:
${CLAUDE_PLUGIN_DATA}/converted/<skill-name>/ -
Build the pipeline files (each under 40 lines):
SKILL.md-- orchestrator referencing the 5 stages, under 30 linesreferences/01-scope.md-- constraints relevant to this skill's domainreferences/02-plan.md-- design step specific to this skill's output typereferences/03-build.md-- execution instructions from the originalreferences/04-check.md-- universal checks plus extracted domain checksreferences/05-deliver.md-- finalization stepscheck-gates.md-- domain-specific YES/NO gate questionsfailure-log.md-- seeded with "avoid" items from the original skill
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.
- 1mo ago First seen · 75 lines · 38 tokens per session scan B 485b594d315f
skill-convert is a command published in the GitHub repository stevesolun/micro-skills (13 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 1,062 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other commands, from other repositories
sunset-review
Use this skill when the user wants to identify unused, near-zero-use, or stale skills/agents/commands in the plugin surface so they can be demoted or retired. Combines agent-dispatch telemetry (start-events only) with static reference scanning, classifies every surface item into Active / Investigate / Demote / Retire…
autopilot
Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor → session-end for N iterations with all 10 kill-switches (SPIRAL, FAILED wave, carryover > 50%, max-hours, max-sessions, resource-overload, token-budget, stall-timeout, sub-threshold confidence…
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
repo-audit
Use this skill when the user wants to audit a repository for baseline compliance, check code quality, security posture, CI/CD setup, testing, documentation, and ecosystem configuration. Runs 9 checklist categories and emits a Markdown report plus JSON sidecar at .orchestrator/metrics/repo-audit- .json. Context: User…
bootstrap
Use this skill when scaffolding the minimum repository structure required by session-orchestrator. Invoked automatically by the Bootstrap Gate when CLAUDE.md, Session Config, or bootstrap.lock is missing. Also available as /bootstrap for manual invocation. Three intensity tiers: fast (demos/spikes), standard (MVPs)…
brainstorm
Use when you have a feature idea but the scope or UX is still ambiguous — runs a lightweight Socratic design dialogue (3-5 AUQ rounds) and writes a spec markdown file. Use BEFORE /plan feature when product intent needs validation; skip to /plan feature when scope is already clear. HARD-GATE prevents any code work…