/crew-update
SkillAI & modelsCheck for a newer version, update, report what changed, then prompt /clear to reload.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the /crew-update skill
What this skill tells your AI
The instructions your AI receives, as published by byerlikaya/claude-starter-kit in kit/skills/crew-update/SKILL.md and read by ahel’s review.
Bring the Crewforth install up to the latest published version:
- Detect install type. If
.claude/VERSIONexists → a full install (steps below). If Crewforth runs as a plugin (no.claude/VERSION), it updates through the plugin system: runclaude plugin update crewforth@crewforth, tell the user it applies when they restart Claude Code, and stop here. - Current version: read
.claude/VERSION. - Latest version:
npm view crewforth version(needs network). If it can't be reached, say so and stop — don't guess. - Compare. Already on the latest → report "up to date (vX)" and stop. Otherwise show old → new.
- Before: run
bash .claude/eval/update-guard.sh pre(Bash tool, not PowerShell). It records what is on disk (in.claude/.state/, nothing else) and prints one of three verdicts:clean→ nothing to report, go on.UNCOMMITTED:with the changed paths in.claude/andCLAUDE.md→ show the user that list and ask — with your question tool — whether to go ahead (the update rewrites Crewforth-owned files under.claude/), commit or stash first, or stop. Continue only on their yes.NOT IN GIT:(a private install gitignores.claude/andCLAUDE.md, so edits there cannot be detected) → pass its two lines to the user and go on; there is nothing to commit.
- Update — this rewrites Crewforth-owned files under
.claude/(your./CLAUDE.mdand project skills are preserved). Show this plan first, then run:npx --yes crewforth@latest update --here --yes. Two DIFFERENT--yesflags, both required for a non-interactive run: the one before the package name is npx's own — it auto-confirms npx'sOk to proceed?install prompt, which reads the real TTY and IGNORES piped input, so without it the command hangs before Crewforth even starts. The--here --yesafter the package go to the updater (--here= apply on the current branch,--yes= accept the smart defaults). Together they let it run to completion instead of blocking on a prompt your shell can't answer. If you'd rather review each handover decision yourself, tell the user to runnpx crewforth@latest update(no flags) in their own terminal, where both the npx and the interactive prompts work. - After: run
bash .claude/eval/update-guard.sh post(Bash tool, not PowerShell) and show the user its lists — added, changed, moved, removed. - Verify: run
/crew-doctor(orbash .claude/eval/doctor.sh— Bash tool, not PowerShell) so a bad/partial update surfaces immediately. If the updater's or doctor's output contains a line starting with ⭐, pass it to the user verbatim as the LAST line of your summary — it prints once per Crewforth version, and it is meant for the user, not for you. - Report old → new + the headline changes. Take them from
.claude/.state/whats-new.md— the updater writes there the installed package's own CHANGELOG sections between the old and the new version. Do not fetch release notes from the network. No file → say no release notes were included. - Reload (manual — a command can't do it itself): the discipline in the running session is still the OLD one.
Tell the user to run
/clear(or quit and relaunch Claude Code): a new session loads the updated.claude/DISCIPLINE.md.
Signals
- GitHub stars
- 24
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
crew-update- Source
- github.com/byerlikaya/claude-starter-kit
github.com/byerlikaya/claude-starter-kit
More in AI & models
skill-creator
Skill · anthropics
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelswizard
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & modelsai-first-engineering
Skill · affaan-m
More in AI & models
Skill · anthropics
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelswizard
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & modelsai-first-engineering
Skill · affaan-m
More in AI & models