Agent skill

Update Claudeclaw

by sbusso in sbusso/claudeclaw

Efficiently bring upstream ClaudeClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.

MITAuto-check passedDevelopment

Install Update Claudeclaw

skills CLI
$ npx skills add sbusso/claudeclaw --skill update-claudeclaw -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sbusso/claudeclaw update-claudeclaw --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sbusso/claudeclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/update-claudeclaw .claude/skills/update-claudeclaw && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
update-claudeclaw
GitHub stars
194
Token cost
~2.6k tokens
SKILL.md length
1,323 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Efficiently bring upstream ClaudeClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.

  • Works in 8 steps: Preflight (stop early if unsafe) → Create a safety net → Preview what upstream changed (no edits… → …
  • Development work in your project
  • SKILL.md covers How it works, Rollback and Token usage
  • Calls git and npm

What it does

Update Claudeclaw is an agent skill from sbusso/claudeclaw. Efficiently bring upstream ClaudeClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. It works with Git and npm. The repository describes itself as: Use Claude to orchestrate agents like OpenClaw. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/update-claudeclaw”

Requirements

  • Docker

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Preflight (stop early if unsafe)
  2. Create a safety net
  3. Preview what upstream changed (no edits yet)
  4. Conflict preview (before committing anything)
  5. Validation
  6. Breaking changes check
  7. Check for skill updates
  8. Summary + rollback instructions

What it can do on your machine

Read from SKILL.md and the folder at commit 1395af4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Update Claudeclaw loads about 2.6k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 1,323 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sbusso/claudeclaw at commit 1395af4, republished under its MIT licence (© sbusso). 1,323 words, ~2,592 tokens.

Download SKILL.mdSave it as .claude/skills/update-claudeclaw/SKILL.md (or your agent's skills folder).
name
update-claudeclaw
description
Efficiently bring upstream ClaudeClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.

About

Your ClaudeClaw fork drifts from upstream as you customize it. This skill pulls upstream changes into your install without losing your modifications.

Run /update-claudeclaw in Claude Code.

How it works

Preflight: checks for clean working tree (git status --porcelain). If upstream remote is missing, asks you for the URL (defaults to https://github.com/sbusso/claudeclaw.git) and adds it. Detects the upstream branch name (main or master).

Backup: creates a timestamped backup branch and tag (backup/pre-update-<hash>-<timestamp>, pre-update-<hash>-<timestamp>) before touching anything. Safe to run multiple times.

Preview: runs git log and git diff against the merge base to show upstream changes since your last sync. Groups changed files into categories:

  • Skills (.claude/skills/): unlikely to conflict unless you edited an upstream skill
  • Source (src/): may conflict if you modified the same files
  • Build/config (package.json, tsconfig*.json, agent/, src/runtimes/docker/): review needed

Update paths (you pick one):

  • merge (default): git merge upstream/<branch>. Resolves all conflicts in one pass.
  • cherry-pick: git cherry-pick <hashes>. Pull in only the commits you want.
  • rebase: git rebase upstream/<branch>. Linear history, but conflicts resolve per-commit.
  • abort: just view the changelog, change nothing.

Conflict preview: before merging, runs a dry-run (git merge --no-commit --no-ff) to show which files would conflict. You can still abort at this point.

Conflict resolution: opens only conflicted files, resolves the conflict markers, keeps your local customizations intact.

Validation: runs npm run build and npm test.

Breaking changes check: after validation, reads CHANGELOG.md for any [BREAKING] entries introduced by the update. If found, shows each breaking change and offers to run the recommended skill to migrate.

Rollback

The backup tag is printed at the end of each run:

git reset --hard pre-update-<hash>-<timestamp>

Backup branch backup/pre-update-<hash>-<timestamp> also exists.

Token usage

Only opens files with actual conflicts. Uses git log, git diff, and git status for everything else. Does not scan or refactor unrelated code.


Goal

Help a user with a customized ClaudeClaw install safely incorporate upstream changes without a fresh reinstall and without blowing tokens.

Operating principles

  • Never proceed with a dirty working tree.
  • Always create a rollback point (backup branch + tag) before touching anything.
  • Prefer git-native operations (fetch, merge, cherry-pick). Do not manually rewrite files except conflict markers.
  • Default to MERGE (one-pass conflict resolution). Offer REBASE as an explicit option.
  • Keep token usage low: rely on git status, git log, git diff, and open only conflicted files.

Step 0: Preflight (stop early if unsafe)

Run:

  • git status --porcelain If output is non-empty:
  • Tell the user to commit or stash first, then stop.

Confirm remotes:

  • git remote -v If upstream is missing:
  • Ask the user for the upstream repo URL (default: https://github.com/sbusso/claudeclaw.git).
  • Add it: git remote add upstream <user-provided-url>
  • Then: git fetch upstream --prune

Determine the upstream branch name:

  • git branch -r | grep upstream/
  • If upstream/main exists, use main.
  • If only upstream/master exists, use master.
  • Otherwise, ask the user which branch to use.
  • Store this as UPSTREAM_BRANCH for all subsequent commands. Every command below that references upstream/main should use upstream/$UPSTREAM_BRANCH instead.

Fetch:

  • git fetch upstream --prune

Step 1: Create a safety net

Capture current state:

  • HASH=$(git rev-parse --short HEAD)
  • TIMESTAMP=$(date +%Y%m%d-%H%M%S)

Create backup branch and tag (using timestamp to avoid collisions on retry):

  • git branch backup/pre-update-$HASH-$TIMESTAMP
  • git tag pre-update-$HASH-$TIMESTAMP

Save the tag name for later reference in the summary and rollback instructions.

Step 2: Preview what upstream changed (no edits yet)

Compute common base:

  • BASE=$(git merge-base HEAD upstream/$UPSTREAM_BRANCH)

Show upstream commits since BASE:

  • git log --oneline $BASE..upstream/$UPSTREAM_BRANCH

Show local commits since BASE (custom drift):

  • git log --oneline $BASE..HEAD

Show file-level impact from upstream:

  • git diff --name-only $BASE..upstream/$UPSTREAM_BRANCH

Bucket the upstream changed files:

  • Skills (.claude/skills/): unlikely to conflict unless the user edited an upstream skill
  • Source (src/): may conflict if user modified the same files
  • Build/config (package.json, package-lock.json, tsconfig*.json, agent/, src/runtimes/docker/, launchd/): review needed
  • Other: docs, tests, misc

Present these buckets to the user and ask them to choose one path using AskUserQuestion:

  • A) Full update: merge all upstream changes
  • B) Selective update: cherry-pick specific upstream commits
  • C) Abort: they only wanted the preview
  • D) Rebase mode: advanced, linear history (warn: resolves conflicts per-commit)

If Abort: stop here.

Step 3: Conflict preview (before committing anything)

If Full update or Rebase:

  • Dry-run merge to preview conflicts. Run these as a single chained command so the abort always executes:
    git merge --no-commit --no-ff upstream/$UPSTREAM_BRANCH; git diff --name-only --diff-filter=U; git merge --abort
  • If conflicts were listed: show them and ask user if they want to proceed.
  • If no conflicts: tell user it is clean and proceed.

Step 4A: Full update (MERGE, default)

Run:

  • git merge upstream/$UPSTREAM_BRANCH --no-edit

If conflicts occur:

  • Run git status and identify conflicted files.
  • For each conflicted file:
    • Open the file.
    • Resolve only conflict markers.
    • Preserve intentional local customizations.
    • Incorporate upstream fixes/improvements.
    • Do not refactor surrounding code.
    • git add <file>
  • When all resolved:
    • If merge did not auto-commit: git commit --no-edit
Show full SKILL.md (541 more words)Show less

Step 4B: Selective update (CHERRY-PICK)

If user chose Selective:

  • Recompute BASE if needed: BASE=$(git merge-base HEAD upstream/$UPSTREAM_BRANCH)
  • Show commit list again: git log --oneline $BASE..upstream/$UPSTREAM_BRANCH
  • Ask user which commit hashes they want.
  • Apply: git cherry-pick <hash1> <hash2> ...

If conflicts during cherry-pick:

  • Resolve only conflict markers, then:
    • git add <file>
    • git cherry-pick --continue If user wants to stop:
    • git cherry-pick --abort

Step 4C: Rebase (only if user explicitly chose option D)

Run:

  • git rebase upstream/$UPSTREAM_BRANCH

If conflicts:

  • Resolve conflict markers only, then:
    • git add <file>
    • git rebase --continue If it gets messy (more than 3 rounds of conflicts):
    • git rebase --abort
    • Recommend merge instead.

Step 5: Validation

Run:

  • npm run build
  • npm test (do not fail the flow if tests are not configured)

If build fails:

  • Show the error.
  • Only fix issues clearly caused by the merge (missing imports, type mismatches from merged code).
  • Do not refactor unrelated code.
  • If unclear, ask the user before making changes.

Step 6: Breaking changes check

After validation succeeds, check if the update introduced any breaking changes.

Determine which CHANGELOG entries are new by diffing against the backup tag:

  • git diff <backup-tag-from-step-1>..HEAD -- CHANGELOG.md

Parse the diff output for lines starting with +[BREAKING]. Each such line is one breaking change entry. The format is:

[BREAKING] <description>. Run `/<skill-name>` to <action>.

If no [BREAKING] lines are found:

  • Skip this step silently. Proceed to Step 7 (skill updates check).

If one or more [BREAKING] lines are found:

  • Display a warning header to the user: "This update includes breaking changes that may require action:"
  • For each breaking change, display the full description.
  • Collect all skill names referenced in the breaking change entries (the /<skill-name> part).
  • Use AskUserQuestion to ask the user which migration skills they want to run now. Options:
    • One option per referenced skill (e.g., "Run /add-whatsapp to re-add WhatsApp channel")
    • "Skip — I'll handle these manually"
  • Set multiSelect: true so the user can pick multiple skills if there are several breaking changes.
  • For each skill the user selects, invoke it using the Skill tool.
  • After all selected skills complete (or if user chose Skip), proceed to Step 7 (skill updates check).

Step 7: Check for skill updates

After the summary, check if skills are distributed as branches in this repo:

  • git branch -r --list 'upstream/skill/*'

If any upstream/skill/* branches exist:

  • Use AskUserQuestion to ask: "Upstream has skill branches. Would you like to check for skill updates?"
    • Option 1: "Yes, check for updates" (description: "Runs /update-skills to check for and apply skill branch updates")
    • Option 2: "No, skip" (description: "You can run /update-skills later any time")
  • If user selects yes, invoke /update-skills using the Skill tool.
  • After the skill completes (or if user selected no), proceed to Step 8.

Step 8: Summary + rollback instructions

Show:

  • Backup tag: the tag name created in Step 1
  • New HEAD: git rev-parse --short HEAD
  • Upstream HEAD: git rev-parse --short upstream/$UPSTREAM_BRANCH
  • Conflicts resolved (list files, if any)
  • Breaking changes applied (list skills run, if any)
  • Remaining local diff vs upstream: git diff --name-only upstream/$UPSTREAM_BRANCH..HEAD

Tell the user:

  • To rollback: git reset --hard <backup-tag-from-step-1>
  • Backup branch also exists: backup/pre-update-<HASH>-<TIMESTAMP>

Service name: Derived from the directory name: com.claudeclaw.<dirname> (macOS) / claudeclaw-<dirname> (Linux).

  • Restart the service to apply changes:
    • If using launchd: launchctl unload ~/Library/LaunchAgents/com.claudeclaw.plist && launchctl load ~/Library/LaunchAgents/com.claudeclaw.plist
    • If running manually: restart npm run dev

© sbusso, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/update-claudeclaw of sbusso/claudeclaw.

Open the folder on GitHubat commit 1395af4

Compare with similar skills

Update Claudeclaw next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Update Claudeclaw compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update Claudeclaw this skillsbusso/claudeclaw194—~2.6kAutomated safety check: PassMIT
Migrate Internal Package into GhostTryGhost/Ghost56k—~3.8kAutomated safety check: PassMIT
Open Code Review CLIalibaba/open-code-review46k—~3.1kAutomated safety check: PassApache-2.0
Open Code Review Delegatealibaba/open-code-review46k—~2.3kAutomated safety check: PassApache-2.0
Verdaccio Pull Request Workflowverdaccio/verdaccio18k—~1.9kAutomated safety check: PassMIT
Hunk Release Workflowmodem-dev/hunk9.6k—~3.8kAutomated safety check: PassMIT

Similar skills

  • Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.

    56k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Open Code Review CLI

    alibaba/open-code-review

    Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.

    46k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Open Code Review Delegate

    alibaba/open-code-review

    Has the host agent do the code review itself while the ocr CLI handles file selection and rule lookup, covering workspace changes, branch ranges or single commits.

    46k GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Takes a change through a verdaccio pull request: branch, local checks, changeset, title and body, labels, CI and review rounds, and ports to other release lines.

    18k GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Hunk Release Workflow

    modem-dev/hunk

    Maintainer workflow for preparing, publishing, verifying and curating Hunk releases, with confirmation gates before tags, publishes and public edits.

    9.6k GitHub stars~3.8k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Code Review

    yaklang/yakit

    对 Yakit 仓库的代码改动做规范化 code review:按代码逻辑、TS 定义、UI 引用与 Props、CSS 样式、依赖版本、配置项六个维度审查,检查测试用例缺失,强制执行 tsc 类型检查与 vitest 测试验证,输出「结果汇总 / 明细解释 / 合并结论」三块报告,经用户确认后写入文件。当用户要求 review、审查、评审代码改动,或在提交、合并、提 PR…

    7.8k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check: notes

More from sbusso/claudeclaw

All 23 skills in this repo
  • Debug

    sbusso/claudeclaw

    Debug container agent issues. An agent skill from sbusso/claudeclaw.

    194 GitHub starsUsed in 1 repo~3.3k tokens
    Auto-check: notes
  • X Integration

    sbusso/claudeclaw

    X (Twitter) integration for ClaudeClaw. An agent skill from sbusso/claudeclaw.

    194 GitHub stars~3k tokensUpdated 1 mo ago
    Auto-check: notes
  • Add Gmail

    sbusso/claudeclaw

    Add Gmail integration to ClaudeClaw. An agent skill from sbusso/claudeclaw.

    194 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Add Qmd

    sbusso/claudeclaw

    Add QMD (Query Markup Documents) as an advanced memory search backend.

    194 GitHub stars~629 tokensUpdated 1 mo ago
    Auto-check passed
  • Add Telegram

    sbusso/claudeclaw

    Add Telegram as a channel. An agent skill from sbusso/claudeclaw.

    194 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check: notes
  • Add Telegram Swarm

    sbusso/claudeclaw

    Add Agent Swarm (Teams) support to Telegram. An agent skill from sbusso/claudeclaw.

    194 GitHub stars~3.7k tokensUpdated 1 mo ago
    Auto-check: notes

Works with

Categories

Questions about Update Claudeclaw

What does Update Claudeclaw do?

Efficiently bring upstream ClaudeClaw updates into a customized install, with preview, selective cherry-pick, and low token usage. Update Claudeclaw is an agent skill from sbusso/claudeclaw. Efficiently bring upstream ClaudeClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.

When should I use Update Claudeclaw?

Update Claudeclaw fits situations like: development work in your project.

How do I install Update Claudeclaw in Claude Code?

Run `npx skills add sbusso/claudeclaw --skill update-claudeclaw -a claude-code`. Or copy the skill folder (skills/update-claudeclaw in sbusso/claudeclaw) into .claude/skills/update-claudeclaw in your project. Claude Code loads it when a task matches its description.

How do I install Update Claudeclaw in Codex?

Run `npx skills add sbusso/claudeclaw --skill update-claudeclaw -a codex`. Or copy the skill folder (skills/update-claudeclaw in sbusso/claudeclaw) into .agents/skills/update-claudeclaw in your project. Codex loads it when a task matches its description.

Can I use Update Claudeclaw in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sbusso/claudeclaw --skill update-claudeclaw -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-claudeclaw, .gemini/skills/update-claudeclaw, .github/skills/update-claudeclaw and .opencode/skills/update-claudeclaw in your project.

What does Update Claudeclaw need to run?

Going by SKILL.md and its folder, Update Claudeclaw needs the command-line tools its instructions call (git and npm). Our summary lists: Docker.

Does Update Claudeclaw access the network?

SKILL.md contains no URLs. Its commands use git and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Update Claudeclaw safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Update Claudeclaw use?

Update Claudeclaw is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Update Claudeclaw use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Update Claudeclaw?

Skills that share tags, products or a category with Update Claudeclaw: Migrate Internal Package into Ghost (TryGhost/Ghost, 56k stars), Open Code Review CLI (alibaba/open-code-review, 46k stars), Open Code Review Delegate (alibaba/open-code-review, 46k stars) and Verdaccio Pull Request Workflow (verdaccio/verdaccio, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Claudeclaw?

sbusso (a GitHub user) maintains it in sbusso/claudeclaw, which has 194 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on August 12, 2026.

Source: sbusso/claudeclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.