feat(plugin): Scribe replaces native memory by instruction; tighten project-scope discipline #70

Merged

bvandeusen merged 1 commits from dev into main 2026-06-10 13:35:28 -04:00

Conversation 0 Commits 1 Files Changed 4

+64 -16

bvandeusen commented 2026-06-10 13:16:31 -04:00

Owner

Copy Link

Copy Source

Direction change (operator): the Scribe plugin must not depend on disabling a native Claude function to work — it earns its place by steering behavior, not by toggling autoMemoryEnabled. Tracked on plan task #755 (work-logs #341/#342). Supersedes #755 Phase 6 (autoMemoryEnabled:false), which is now disregarded.

Memory doctrine — no dual-write

• using-scribe/SKILL.md — new section "Scribe holds these functions — don't keep a second copy": route rules/recall/planning to Scribe, don't also write them to native auto-memory, never instruct disabling a native function, and accept a "Scribe-shaped hole" if the plugin is removed (recover over time).
• mcp/server.py _INSTRUCTIONS — removed the paragraph that told every session to create/refresh a "rules live in Scribe" pointer in CLAUDE.md / ~/.claude memory. That was an active dual-write instruction; the SessionStart hook is the bridge now. Replaced with the no-dual-write / no-settings-dependency doctrine.

Project-scope discipline — stop cross-project bleed

• using-scribe/SKILL.md — new section "Stay inside the active project's scope": pass project_id to every read; only reference/offer work on the in-scope project; ask before switching.
• _INSTRUCTIONS — scope rule extended from reads → also referencing/offering; flags get_recent as cross-project.
• get_recent docstring — scope note steering to scoped list_* when a project is active.
• Audit found search / list_tasks / list_notes already enforce project_id, and the SessionStart hook text (plugin_context.py) was already clean — so the gaps were exactly these spots.

Distribution

• plugin.json 0.1.4 → 0.1.5 so client caches actually refresh (re-shipping under the same version does not bust the cache).
• On merge: backend (_INSTRUCTIONS, get_recent) propagates via the app deploy; the skill propagates via plugin autoUpdate to 0.1.5.

CI green on dev (run #821, 9eddb84).

🤖 Generated with Claude Code

Direction change (operator): the Scribe plugin must **not** depend on disabling a native Claude function to work — it earns its place by steering behavior, not by toggling `autoMemoryEnabled`. Tracked on plan task #755 (work-logs #341/#342). **Supersedes #755 Phase 6** (`autoMemoryEnabled:false`), which is now disregarded. ## Memory doctrine — no dual-write - **`using-scribe/SKILL.md`** — new section *"Scribe holds these functions — don't keep a second copy"*: route rules/recall/planning to Scribe, don't also write them to native auto-memory, never instruct disabling a native function, and accept a "Scribe-shaped hole" if the plugin is removed (recover over time). - **`mcp/server.py` `_INSTRUCTIONS`** — **removed the paragraph that told every session to create/refresh a "rules live in Scribe" pointer in CLAUDE.md / `~/.claude` memory.** That was an active dual-write instruction; the SessionStart hook is the bridge now. Replaced with the no-dual-write / no-settings-dependency doctrine. ## Project-scope discipline — stop cross-project bleed - **`using-scribe/SKILL.md`** — new section *"Stay inside the active project's scope"*: pass `project_id` to every read; only reference/offer work on the in-scope project; ask before switching. - **`_INSTRUCTIONS`** — scope rule extended from reads → also referencing/offering; flags `get_recent` as cross-project. - **`get_recent`** docstring — scope note steering to scoped `list_*` when a project is active. - Audit found `search` / `list_tasks` / `list_notes` already enforce `project_id`, and the SessionStart hook text (`plugin_context.py`) was already clean — so the gaps were exactly these spots. ## Distribution - `plugin.json` **0.1.4 → 0.1.5** so client caches actually refresh (re-shipping under the same version does not bust the cache). - On merge: backend (`_INSTRUCTIONS`, `get_recent`) propagates via the app deploy; the skill propagates via plugin autoUpdate to 0.1.5. CI green on `dev` (run #821, `9eddb84`). 🤖 Generated with [Claude Code](https://claude.com/claude-code)

bvandeusen added 1 commit 2026-06-10 13:16:31 -04:00

feat(plugin): Scribe replaces native memory by instruction; tighten project-scope discipline ... 9eddb8497c

Direction change (operator, see plan task #755 work-log): the plugin must
NOT depend on disabling a native Claude function to work. It earns its place
by steering behavior, not by toggling autoMemoryEnabled.

Memory doctrine (no dual-write):
- using-scribe SKILL.md gains "Scribe holds these functions — don't keep a
  second copy": route rules/recall/planning to Scribe, don't also write them
  to native auto-memory, never instruct disabling a native function, and
  accept a "Scribe-shaped hole" if the plugin is removed (recover over time).
- mcp/server.py _INSTRUCTIONS: drop the paragraph that told the model to
  create/refresh a "rules live in Scribe" pointer in CLAUDE.md / ~/.claude
  memory. That was an active dual-write instruction; the SessionStart hook is
  the bridge now. Replaced with the no-dual-write / no-settings-dependency
  doctrine. Supersedes plan #755 Phase 6 ("set autoMemoryEnabled:false").

Project-scope discipline (stop cross-project bleed):
- using-scribe SKILL.md gains "Stay inside the active project's scope": pass
  project_id to every read, only reference/offer work on the in-scope project,
  ask before switching.
- _INSTRUCTIONS scope bullet extended from reads to referencing/offering, and
  flags get_recent as cross-project.
- get_recent docstring gains a scope note steering to scoped list_* when a
  project is active.

plugin.json 0.1.4 -> 0.1.5 so clients' caches actually refresh (re-shipping
under the same version does not bust the cache).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

bvandeusen merged commit e631a4e615 into main 2026-06-10 13:35:28 -04:00

Sign in to join this conversation.

Reviewers

No Reviewers

Labels

No items

No Label

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

bvandeusen

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: bvandeusen/FabledScribe#70