self-update
Skill1 starsChanged 7 months agoApache-2.0View on GitHub
Checks whether the project's claude-bootstrap setup is current and applies updates safely. Compares the installed version against the source repo, shows what changed, and updates only what the user approves. Triggered by /update.
- Pipes a download into a shell
4 other projects use a version of this.
Adopted by
Most recently taken up by
- kirodotdev/KiroCrewtheir own version, first seen Oct 19, 2026
- getsentry/juniortheir own version, first seen Oct 13, 2026
- treylom/ThisCodetheir own version, first seen Sep 5, 2026
- CorentinGC/claude-skillstheir own version, first seen Mar 7, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- kirodotdev/KiroCrew★ 4.8ksame name
- getsentry/junior★ 409same name
- treylom/ThisCode★ 41same name
- CorentinGC/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyze-repoSkill
- augmentSkill
- code-reviewSkill
- context-guardSkill
- dep-checkSkill
- doctorSkill
- forgeSkill
- git-workflowSkill
- learnSkill
- onboardingSkill
- security-scanSkill
- test-runnerSkill
- tipsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Keep a project's bootstrap config current without clobbering the user's customizations.
- Very specific: line 36
Update bootstrap_version in .claude/.bootstrap.json.
- Very specific: line 40
NEVER overwrite a customized CLAUDE.md or SESSION_STATE.md without explicit confirmation.
- Distinctive: line 41
ALWAYS show what will change before applying, and back up before replacing.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Purpose
Keep a project's bootstrap config current without clobbering the user's customizations.
When To Use This
- The user runs
/updateor asks "is my Claude setup outdated?"
Steps
1. Read the installed version
python3 -c 'import json,pathlib; p=pathlib.Path(".claude/.bootstrap.json"); \
print(json.loads(p.read_text()).get("bootstrap_version","unknown") if p.exists() else "unknown")'2. Read the latest version from the source repo
curl -fsSL https://raw.githubusercontent.com/shivae372/claude-bootstrap/master/VERSION 2>/dev/null || echo unknown3. Compare and report (plain language)
- Up to date → say so and stop.
- Outdated → summarize what changed using the repo's CHANGELOG.md
(
curl -fsSL https://raw.githubusercontent.com/shivae372/claude-bootstrap/master/CHANGELOG.md).
4. Apply selectively (only what the user approves)
Offer: hooks, skills, commands, stack templates, or just-show-me. For each chosen item:
- Back up first:
cp <file> <file>.bak - Re-run the installer in merge mode to pull only new/updated component files:
curl -fsSL https://raw.githubusercontent.com/shivae372/claude-bootstrap/master/install.sh | bash -s -- --merge - Update
bootstrap_versionin.claude/.bootstrap.json.
Safety Rules
- NEVER overwrite
USER_PROFILE.json. - NEVER overwrite a customized
CLAUDE.mdorSESSION_STATE.mdwithout explicit confirmation. - ALWAYS show what will change before applying, and back up before replacing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.