instructions/dev: Konverter-Vergleich – eigene Ableitung gegen Referenzwerkzeuge am privaten Korpus, sieben Maße, Grundlinie nur bewusst fortgeschrieben (#233); 10.1.0-beta.3

Files changed:
- CHANGES.md
- VERSION
- docs/dev/development.md
- instructions/dev/converter-comparison.md
- instructions/dev/stack-mode.md
- instructions/dev/testing-conventions.md

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SnAJ7Z3CpVD3PRbN73QtU2

docs/dev/development.md

@@ -207,6 +207,14 @@ works only because the private repository's own Actions settings grant `torben/c
 without that grant the checkout step fails with "Determining the default branch … not found",
 which reads like a missing repository rather than a missing permission.
 
+That workflow shows that the corpus still derives, not that the derivation is good. The second
+question is a session's: `harness/compare/` in the same private repository derives every corpus
+file with the checkout's filters and with reference tools (pymupdf4llm, markitdown, pandoc, each in
+a throwaway environment of its own, never in `tools/.venv`), measures wording fidelity, markup
+overhead, missing semantics, structure, CHECK precision and runtime, and reports the difference to
+a committed baseline. When a session runs it and what it does with the result is
+[instructions/dev/converter-comparison.md](../../instructions/dev/converter-comparison.md).
+
 Three more workflows carry the live tests of the tracker adapters (Super Productivity, CalDAV):
 `ci.yml` runs the CalDAV half in a step of its own against Radicale as a process,
 `tracker-live.yml` runs nightly and covers both providers, and `sp-live-image.yml` builds the