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 sbusso/claudeclaw --skill update-skillsgit clone --depth 1 https://github.com/sbusso/claudeclawWrote 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/sbusso/claudeclaw/update-skills)<a href="https://agentmods.dev/skills/sbusso/claudeclaw/update-skills"><img src="https://agentmods.dev/badge/skills/sbusso/claudeclaw/update-skills/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/sbusso/claudeclaw/update-skills"><img src="https://agentmods.dev/badge/skills/sbusso/claudeclaw/update-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.01197 |
| Opus 5.5 | $0.00006 | $0.00479 |
| Sonnet 5.5 | $0.00003 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
update-skills 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 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.
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.
Copies of this mod
8 near-identical copies found in the catalogue:
- update-skills — 98% identical, 2 lines differ
- update-skills — 98% identical, 2 lines differ
- update-skills — 98% identical, 2 lines differ
- update-skills — 98% identical, 2 lines differ
- update-skills — 98% identical, 2 lines differ
- update-skills — 98% identical, 2 lines differ
- update-skills — 98% identical, 2 lines differ
- update-skills — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
About
Skills are distributed as git branches (skill/*). When you install a skill, you merge its branch into your repo. This skill checks upstream for newer commits on those skill branches and helps you update.
Run /update-skills in Claude Code.
How it works
Preflight: checks for clean working tree and upstream remote.
Detection: fetches upstream, lists all upstream/skill/* branches, determines which ones you've previously merged (via merge-base), and checks if any have new commits.
Selection: presents a list of skills with available updates. You pick which to update.
Update: merges each selected skill branch, resolves conflicts if any, then validates with build + test.
Goal
Help users update their installed skill branches from upstream without losing local customizations.
Operating principles
- Never proceed with a dirty working tree.
- Only offer updates for skills the user has already merged (installed).
- Use git-native operations. Do not manually rewrite files except conflict markers.
- Keep token usage low: rely on
gitcommands, only open files with actual conflicts.
Step 0: Preflight
Run:
git status --porcelain
If output is non-empty:
- Tell the user to commit or stash first, then stop.
Check remotes:
git remote -v
If upstream is missing:
- Ask the user for the upstream repo URL (default:
https://github.com/sbusso/claudeclaw.git). git remote add upstream <url>
Fetch:
git fetch upstream --prune
Step 1: Detect installed skills with available updates
List all upstream skill branches:
git branch -r --list 'upstream/skill/*'
For each upstream/skill/<name>:
- Check if the user has merged this skill branch before:
git merge-base --is-ancestor upstream/skill/<name>~1 HEAD— if this succeeds (exit 0) for any ancestor commit of the skill branch, the user has merged it at some point. A simpler check:git log --oneline --merges --grep="skill/<name>" HEADto see if there's a merge commit referencing this branch.- Alternative:
MERGE_BASE=$(git merge-base HEAD upstream/skill/<name>)— if the merge base is NOT the initial commit and the merge base includes commits unique to the skill branch, it has been merged. - Simplest reliable check: compare
git merge-base HEAD upstream/skill/<name>withgit merge-base HEAD upstream/main. If the skill merge-base is strictly ahead of (or different from) the main merge-base, the user has merged this skill.
- Check if there are new commits on the skill branch not yet in HEAD:
git log --oneline HEAD..upstream/skill/<name>- If this produces output, there are updates available.
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 · 131 lines · 16 tokens per session scan A 7433306d189f
update-skills is a skill published in the GitHub repository sbusso/claudeclaw (194 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 1,197 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
pipeline-conductor
Operating procedure for the kirocrew-pipeline-conductor agent. Use when a pipeline conductor session is seeded, inspected or debugged. You MANAGE one issue/PR pipeline on one repo: two columns per item (session working? item solved?), send intent, never re-derive a red yourself.
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
shipping-a-pr
Use when finished work needs to ship as a pull request, or when creating, syncing, updating metadata, checking status, monitoring CI, or addressing review comments on a PR. Not for reviewing a PR you are not shipping.
commit
Create git commits with good messages. Use when user says "commit", "create commit", or asks to commit changes.
release-notes
Draft a release note section from a commit range, grouped by what the reader gets.