m038andClaude Opus 5
cdae34a706
Four rounds of CLAUDE.md reduction (255 -> 305 -> 179 -> 74 lines) turned
up one consistent finding: every stale fact was a *description* of code or
config, never a rule. Two had been written by Claude days earlier.
Documents the operational test ("does this line change what Claude does on
a task where it wouldn't otherwise open the relevant file?"), the tiering
table, why gotchas are the one category that cannot move to a read-on-demand
docs/exceptions/, invariants-over-enumerations, and how to tell when a
reduction pass has hit the floor.
Also surfaces the docs/solutions frontmatter fields in CLAUDE.md's
entry-point table so the store is greppable by module, not just browsable.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
docs/
If you're Mischa
Doing something operational? → guides/
- Posting a journal entry
- Managing GPX files
- Switching to a new trip
- Rebuilding local dev from scratch
Checking project status? → working/ — what's in there + the plan status convention
Design or architecture decisions? → reference/
If you're Claude
Always-loaded project rules → CLAUDE.md (repo root)
Active specs and plans → working/specs/ and working/plans/
Stable facts → reference/
Raw research input → research/