agentleFS
Sign inStart free
shuvamkshuvamk/openbench/.claude/skills/context-sync/SKILL.md

context-sync

Skill2 starsChanged 5 months agoApache-2.0View on GitHub

End-of-session brain sync — diffs what changed against .context/ and applies the necessary updates. Run at the end of any session that touched product code, and after merges.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Commit as part of the feature branch (same PR), message docs(context): sync <scope>.

    line 29
  2. Distinctive:

    Never a separate PR — CI's context-freshness check requires same-PR updates.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 7 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

context-sync

.context/ is the living brain: read before acting, updated after acting. This skill makes "updated" true.

Procedure

  1. Diff the session's work: git diff --name-only main...HEAD (plus uncommitted). Also run node .claude/hooks/context-sync-check.mjs for the mechanical hints.
  2. Map changes → brain files:
    • New/changed package, dependency, API route, data flow → architecture.md (current-state prose + diagram; keep it what is, not history).
    • Engine adapter capability/gap/lossy field → engine-status.md (status table + per-engine section + checklist).
    • Any autonomous judgment call made this session → decisions.md as a new ADR (append-only, date, rationale, consequences).
    • IR shape changes → interchange-format.md (already required by ir-schema-guard).
    • New domain term used in code/issues → glossary.md.
    • Question raised but not answered → open-questions.md row (owner + issue). Question answered → move to decisions.md, delete the row.
    • Production deploy happened → deploy-log.md line (the deploy-sanity skill owns the format).
  3. Apply the edits. Precision beats completeness — wrong brain is worse than sparse brain.
  4. Commit as part of the feature branch (same PR), message docs(context): sync <scope>. Never a separate PR — CI's context-freshness check requires same-PR updates.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free