sync-context
Skill363 starsChanged 7 months agoMITView on GitHub
Update context files to reflect current codebase state — new components, changed APIs, new patterns, and reasoning behind non-obvious decisions. Routes updates to the correct file based on what changed. Run after any significant design change before committing.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- zhiding512/claude-skillstheir own version, first seen Oct 13, 2026
- mikezamayias/agent-skillstheir own version, first seen Oct 11, 2026
- Shaybush/claude-skillstheir own version, first seen Sep 10, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- Shaybush/claude-skills★ 3same name
- mikezamayias/agent-skills★ 1same name
- zhiding512/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 repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- audit-renderSkill
- create-componentSkill
- debug-layoutSkill
- production-readySkill
- release-checkSkill
- review-docsSkill
- review-fullSkill
- reviewSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Update context files to reflect the current state of the codebase.
- Distinctive: line 37
Read the target file, then edit it following the existing format:
- Distinctive: line 46
No duplicate information across files
- Distinctive: line 47
All updated files have correct content
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Update context files to reflect the current state of the codebase.
Step 1 — Gather what changed
git diff HEAD
git log --oneline -10
git diff HEAD --name-only | grep -E '\.(tsx|ts)$'Step 2 — Classify each change and route to the correct file
| Change type | Target file |
| New component, removed component, changed component props | packages/ui/CLAUDE.md (component catalog table) |
| New focus pattern, focus anti-pattern, useInteractive API change | .claude/rules/focus-system.md |
| New AI SDK convention, changed part types or states | .claude/rules/ai-sdk.md |
| New layout rule, intrinsic element, borderStyle | .claude/rules/opentui-layout.md |
| Non-obvious design decision worth preserving | .claude/rules/design-decisions.md |
| New docs convention, demo pattern | packages/docs/CLAUDE.md |
| New universal anti-pattern, import rule, test command | Root CLAUDE.md |
Step 3 — For each update, evaluate
- Is this new or already documented? (Don't duplicate)
- Is the "why" non-obvious? (Only document if a future engineer might undo without understanding)
- Is existing documentation still accurate? (Update or remove stale entries)
- Is this a permanent pattern or temporary workaround? (Only document permanent)
Step 4 — Apply updates
Read the target file, then edit it following the existing format:
- Component catalog: add/update row in the table
- Rules: add section or update existing content
- Anti-patterns: add
-bullet item - Design decisions: add
##section with rationale
Step 5 — Verify
- Root
CLAUDE.mdmust stay under 100 lines - No duplicate information across files
- All updated files have correct content
What NOT to add
- Implementation details that belong in code comments
- Tutorials or guides
- Obvious decisions that don't need rationale
- Bug workarounds or version-specific notes
- Anything derivable from reading the code directly
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.

