<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/tests/skill-size, branch dev</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>subagent-driven-development: move situational content to references/ so SKILL.md survives compaction (#2565)</title>
<updated>2026-10-21T19:34:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-10-21T19:34:50+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=8a14cf8f9bbf099c59252030fa7e0dc934896aa4'/>
<id>8a14cf8f9bbf099c59252030fa7e0dc934896aa4</id>
<content type='text'>
After a compaction, Claude Code re-attaches each invoked skill truncated to
20,000 characters (#2481). SDD was 32,358, so everything from the fix loop
on (the five-round cap, the breaker, the ledger round line, the final
review's single fix wave, Finish) was gone for the rest of a long session.
One reported task ran 18 fix rounds after that.

Content SDD only needs at particular moments now lives in references/,
behind a pointer at the step that needs it: fix-loop.md (read before every
round), final-review.md (with Finish), handling-reports.md (non-DONE
statuses), resuming.md (an existing ledger), preflight.md (the conflict
scan before Task 1), batching.md, and cannot-verify.md. Those reads come
fresh from disk, so they don't depend on what survived compaction. The
Process graph shows the fix loop and final review as pointer nodes, and
the illustrative Example Workflow is gone. SKILL.md is 19,506 bytes.

tests/skill-size/test-skill-size.sh fails when any SKILL.md reaches 20,000
bytes. It still fails for writing-skills and executing-plans.

Claude-Session: https://claude.ai/code/session_01EgKgPPzKtNA2okiCmqb11F</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
After a compaction, Claude Code re-attaches each invoked skill truncated to
20,000 characters (#2481). SDD was 32,358, so everything from the fix loop
on (the five-round cap, the breaker, the ledger round line, the final
review's single fix wave, Finish) was gone for the rest of a long session.
One reported task ran 18 fix rounds after that.

Content SDD only needs at particular moments now lives in references/,
behind a pointer at the step that needs it: fix-loop.md (read before every
round), final-review.md (with Finish), handling-reports.md (non-DONE
statuses), resuming.md (an existing ledger), preflight.md (the conflict
scan before Task 1), batching.md, and cannot-verify.md. Those reads come
fresh from disk, so they don't depend on what survived compaction. The
Process graph shows the fix loop and final review as pointer nodes, and
the illustrative Example Workflow is gone. SKILL.md is 19,506 bytes.

tests/skill-size/test-skill-size.sh fails when any SKILL.md reaches 20,000
bytes. It still fails for writing-skills and executing-plans.

Claude-Session: https://claude.ai/code/session_01EgKgPPzKtNA2okiCmqb11F</pre>
</div>
</content>
</entry>
</feed>
