<feed xmlns='http://www.w3.org/2005/Atom'>
<title>rulesets/CLAUDE.md, branch main</title>
<subtitle>Claude Code skills, rules, and language bundles
</subtitle>
<id>https://git.cjennings.net/rulesets/atom?h=main</id>
<link rel='self' href='https://git.cjennings.net/rulesets/atom?h=main'/>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/rulesets/'/>
<updated>2026-06-11T06:36:35+00:00</updated>
<entry>
<title>feat: insights follow-ups — empirical-first debugging, staging guard, invariants</title>
<updated>2026-06-11T06:36:35+00:00</updated>
<author>
<name>Craig Jennings</name>
<email>c@cjennings.net</email>
</author>
<published>2026-06-11T06:36:35+00:00</published>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/rulesets/commit/?id=63b9a5f6b451f63e7f18381c47f4464bda993ead'/>
<id>urn:sha1:63b9a5f6b451f63e7f18381c47f4464bda993ead</id>
<content type='text'>
From the 2026-06-11 usage report. The debug skill gains a hypothesis-discipline contract (rank candidate causes by cheapest empirical test, run probes in parallel, report only confirmed findings) targeting the serial theory-cycling the report flagged. commits.md's pre-commit checklist gains a staged-files guard covering the untracked-set and canonical-vs-mirror conventions. A small tracked CLAUDE.md carries the rulesets mirror invariant at turn zero. Two [#C] pilots filed: a read-only morning ops orchestrator and a monthly session-harvest workflow.

The report's 500-token-cap finding was a mislabel: the underlying transcripts show 529 Overloaded and stream-idle-timeout errors with no token cap configured anywhere, so nothing to change there.
</content>
</entry>
</feed>
