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 aiya000/dotfiles --skill convert-skills-for-cloudgit clone --depth 1 https://github.com/aiya000/dotfilesWrote 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/aiya000/dotfiles/convert-skills-for-cloud)<a href="https://agentmods.dev/skills/aiya000/dotfiles/convert-skills-for-cloud"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/convert-skills-for-cloud/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/aiya000/dotfiles/convert-skills-for-cloud"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/convert-skills-for-cloud.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 | $0.00141 | $0.01996 |
| Opus 5.5 | $0.00056 | $0.00798 |
| Sonnet 5.5 | $0.00028 | $0.00399 |
| Haiku 4.5 | $0.00014 | $0.00200 |
Grade A, and why
convert-skills-for-cloud scanned grade A 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 20d 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 directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| **local-only** | Its purpose needs the local machine (Windows logs, adb, `~/.claude/settings.json`, a local hook). Not zipped | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
convert-skills-for-cloud
Turns the local skills into uploadable zips for claude.ai. A skill uploaded there is synced into
every Claude Code cloud session -- a fresh container that has none of this machine: no home
directory layout, no gh, no WSL, no hooks, and nothing that survives the session.
So this is not a zip command. Each skill is read, judged, and rewritten where it assumes the local machine, in a staged copy, and only then validated and zipped.
Two files in this skill's directory do the mechanical part:
scripts/audit.sh SKILL_DIR...-- lists every local-only assumption, by categoryscripts/package.py SKILL_DIR... --out OUT_DIR-- checks the rules claude.ai applies on upload, and zips each folder as<name>/...
And one holds the judgement: read references/cloud-adaptation-tips.md before rewriting
anything. It has a section for each audit category, with the fix and examples from these very
skills. When a conversion teaches something new, add it there (step 7).
Arguments
- Skill names (
/convert-skills-for-cloud git-commit save-memory) -- those, plus the skills they depend on (step 3) --all, or nothing -- every skill--out <dir>-- where the zips go (default below)
Steps
1. Find the sources and the output directory
Sources, first that exists:
<repo>/.claude_global/skills/when the current repository is the dotfiles repository (git rev-parse --show-toplevel) -- the case in a cloud session~/.dotfiles/.claude_global/skills/~/.claude/skills/(resolve the symlink:ls -ld)
Never edit the sources in steps 2-6. Everything happens in a staged copy.
Build directory (<build>), first that applies:
--outif given- In a cloud session (
CLAUDE_CODE_REMOTE=true):<scratchpad>/cloud-skills/, the scratchpad named in the system prompt -- the user can open files there, and it is gone with the container, which is fine for build output ~/tmp/cloud-skills/when~/tmpexists${TMPDIR:-/tmp}/cloud-skills/
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago First seen · 157 lines · 141 tokens per session scan A c8797c28888a
convert-skills-for-cloud is a skill published in the GitHub repository aiya000/dotfiles (21 stars, last pushed 2d ago), licensed MIT. It adds 141 tokens to every session and 1,996 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
Other skills, from other repositories
restart__pull_request
A pull-request restart workflow for replacing a messy review with a new pull request containing one clean commit and a summary of the earlier discussion.
rescue__pull_request_review
An automated workflow for handling GitHub pull-request review comments, applying requested code changes, committing them, and pushing them back.
submit__pull_request
An automated pull-request submission workflow. A pull request is a request for a code change to be reviewed and merged; this workflow writes its explanation, creates it, watches its automated checks, and fixes failed checks.
write__pull_request
A workflow for writing a pull request description, the explanation attached to a proposed code change for review. It analyses the changes and commit history.
monitor__ci_status
An automated monitor for GitHub Actions, the service that runs checks such as tests after code changes. It watches all checks after a pull request or a push to a pull-request branch and can invoke a failure-recovery process.
monitor__pull_request_conflict
An automated check for GitHub pull requests, which are proposed code changes awaiting review or merging.