@sellable/mcp 0.1.213 → 0.1.215

package/skills/create-campaign-v2/references/approval-gate-framing.md

@@ -66,7 +66,7 @@ Before showing the gate OR running any approve-path tool, verify the
 - The active Sellable-auth workspace matches the workspace the draft
   directory was written in (prevents cross-workspace mint drift).
 
-This invariant is identical to the Phase 84 "sender/workspace mismatch
+This invariant is identical to the offline-validation "sender/workspace mismatch
 = abort" rule and the global memory rule `CRITICAL: Never Send Messages
 From Wrong Workspace`. If the invariant fails:
 
@@ -78,7 +78,7 @@ From Wrong Workspace`. If the invariant fails:
 4. Leave the draft directory intact; a fresh session in the correct
    workspace can resume from where this one aborted.
 
-The invariant is a hard stop, not an escalation in the Plan 85-02 sense.
+The invariant is a hard stop, not a retryable escalation.
 
 ## Anchor Validation
 
@@ -310,7 +310,7 @@ leadSourceType, leadSourceProvider })` and capture `{ campaignId, watchUrl }`
    payload from `lead-filter.md`)
 5. flip brief status to `committed`; move draft to `.committed/`
 6. surface the first watch-link handoff using `watch-link-handoff.md`
-7. hand off to the autonomous tail (Plan 85-02)
+7. hand off to the autonomous tail
 
 See `watch-link-handoff.md` for the exact link-surfacing protocol and the
 partial-mint recovery rules.
@@ -349,12 +349,12 @@ automatic rollback.
 
 ### `revise-brief`
 
-Route back to Phase 83 or Phase 84 depending on what the user wants to change.
+Route back to the relevant brief or validation step depending on what the user wants to change.
 Do NOT commit/mint a campaign. If a draft shell already exists, keep it
 non-sendable and update it only through the normal draft-shell sync points.
 
 Draft effect: preserve nothing by default; the brief itself is usually
-rewritten upstream. Delete all downstream artifacts so Phase 84 will re-run:
+rewritten upstream. Delete all downstream artifacts so offline validation will re-run:
 
 - delete `lead-review.md`
 - delete `lead-sample.json`
@@ -364,7 +364,7 @@ rewritten upstream. Delete all downstream artifacts so Phase 84 will re-run:
 
 ### `revise-leads`
 
-Route back to Phase 84 `find leads`. Do NOT commit/mint a campaign. If a draft
+Route back to `find leads`. Do NOT commit/mint a campaign. If a draft
 shell already exists, keep it non-sendable and replace only draft-shell source
 state when the revised source is approved.
 
@@ -379,7 +379,7 @@ Draft effect:
 
 ### `revise-rubric`
 
-Route back to Phase 84 `filter leads`. Do NOT commit/mint a campaign. If a draft
+Route back to `filter leads`. Do NOT commit/mint a campaign. If a draft
 shell already exists, keep it non-sendable and update only saved draft rubrics
 after the revised filter is confirmed.
 
@@ -394,7 +394,7 @@ Draft effect:
 
 ### `revise-messaging`
 
-Route back to Phase 84 `generate message`. Do NOT commit/mint a campaign. If a
+Route back to `generate message`. Do NOT commit/mint a campaign. If a
 draft shell already exists, keep it non-sendable.
 
 Draft effect:
@@ -433,7 +433,7 @@ non-sendable shell for operator cleanup.
   picks a choice. Draft-shell writes happen in earlier allowed flow steps, not
   inside the commit-gate question turn.
 - `import_leads` is **not** part of atomic mint. Full sourcing/import happens
-  in Plan 85-02 Step 13 after mint.
+  after mint.
 - Revision choices produce no spend/send-side effects.
 - Aborting produces no spend/send-side effects.
 - A failed `approve` path (e.g. `create_campaign` errors, or `save_rubrics`

package/skills/create-campaign-v2/references/escalation-ladder.md

@@ -1,6 +1,6 @@
 # Escalation Ladder
 
-This reference governs when the Plan 85-02 autonomous tail STOPS and returns
+This reference governs when the autonomous tail STOPS and returns
 control to the user. Load this file whenever the tail needs to decide
 between continuing autonomously, retrying, or escalating.
 
@@ -100,8 +100,8 @@ When escalating, the skill:
    watch link if the user asks for it or diagnostics show the link is missing or
    broken.
 4. Presents an actionable options menu via `AskUserQuestion`:
-   - `revise-brief` — go back to Phase 83/84 brief editing
-   - `revise-leads` — go back to Phase 84 find-leads
+   - `revise-brief` — go back to brief editing
+   - `revise-leads` — go back to find-leads
    - `abort` — stop and clean up (moves committed dir under `.aborted/`
      if the user wants to cold-start)
    - `resume-from-<step>` — retry from the failing step (e.g.

package/skills/create-campaign-v2/references/final-handoff-contract.md

@@ -186,10 +186,10 @@ disables once the campaign is running.
 ## Workspace + Sender Invariant
 
 Before calling `start_campaign` via the Claude greenlight path,
-re-validate the workspace/sender invariants Phase 84 committed against.
+re-validate the workspace/sender invariants that offline validation committed against.
 If the current auth context no longer matches (workspace switched mid
 session, sender removed, etc.), abort the start with the same invariant
-error Phase 84 uses. Do NOT start a campaign from the wrong workspace.
+error offline validation uses. Do NOT start a campaign from the wrong workspace.
 
 ## Pre-Start State Guards
 
@@ -238,7 +238,7 @@ does NOT silently proceed.
 - A Claude greenlight on an already-running campaign is a no-op
   confirmation, not a duplicate start.
 - Workspace/sender mismatch at greenlight time aborts the start with
-  the Phase 84 invariant.
+  the offline-validation invariant.
 - The start route, not a follow-up `update_campaign`, persists
   `currentStep: "running"`.
 - A pre-check refusal is NOT an escalation — it's a fixable state. The