Wolts should own their memory loading — remove .claude/rules workaround
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 12
- Forks
- 1
- Avg merge
- 7h 13m
- Merged PRs (30d)
- 31
Description
Context
Issue #97 (import gate blocking sessions) was fixed by symlinking wolt/memory/index.md into .claude/rules/memory-index.md. This bypasses Claude Code's import approval dialog because rules load without a trust gate.
But this is a workaround, not the right architecture. Wolt memory should be loaded by the wolt's own infrastructure, not by leaking into .claude/rules/. The .claude/ directory is Claude Code's config space — mixing wolt memory files in there creates coupling and confusion about who owns what.
What should happen
Wolts should manage their own memory loading through the platform — either via:
- A hook that injects memory content at session start (e.g.
--append-system-prompt) - A platform-level mechanism that feeds memory into the session context without relying on Claude Code's file-loading pipeline
- An
InstructionsLoadedhook or similar that auto-approves known wolt paths
Current state
.claude/rules/memory-index.md→ symlink to../../wolt/memory/index.md(workaround, merged for #97)@wolt/memory/index.mdremoved from CLAUDE.md- Memory still loads correctly via the rules path, but it's in Claude Code's namespace instead of the wolt's
When to revisit
After the new onboard flow lands — that's a natural point to redesign how memory gets injected into sessions.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing issue #97, the .claude/rules/memory-index.md symlink, wolt/memory/index.md, CLAUDE.md, and the new onboard flow. Define the platform-owned memory injection approach, then verify that memory loads without the Claude Code rules workaround and that the symlink and related coupling are removed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- developer-experience
- Issue type
- Refactor
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100