@sellable/mcp 0.1.80 → 0.1.82

package/skills/create-campaign-v2/references/watch-link-handoff.md

@@ -1,110 +1,110 @@
 # Watch Link Handoff
 
-This reference governs how create-campaign-v2 surfaces the watch link after
-the commit gate passes and the atomic mint succeeds. Load this file before
-showing the watch link, and on every resume where the link needs to be
-re-surfaced.
+This reference governs how create-campaign-v2 surfaces the watch link in the
+shell-first flow. Load it before showing the link and on every resume where the
+link needs to be re-surfaced.
+
+CampaignOffer state is canonical; disk artifacts are a debug trail. All 14 disk
+artifacts remain as debug outputs, but resume, gating, and handoff read campaign
+state first.
 
 ## Plumbing Reuse
 
 `create_campaign` already returns a signed `watchUrl` on the response
 (`CampaignDetail.watchUrl` in `mcp/sellable/src/tools/campaigns.ts`). V2 does
 NOT mint a new token, does NOT call a different route, and does NOT construct
-the URL locally. The skill captures whatever `watchUrl` the existing tool
-returns and surfaces it verbatim.
+the URL locally. Capture whatever `watchUrl` the existing tool returns and
+surface it verbatim.
 
-The v1 `create-campaign` SKILL uses the same "watch mode" pattern: after a
-step change, the skill names what changed and orients the user to what the
-watch link will show next. V2 adopts that pattern verbatim — the only
-difference is V2 surfaces the link once, at the atomic mint boundary, and
-then re-surfaces it on resume.
+## Shell-First Link
 
-## Atomic Mint Sequence
+The active flow creates the campaign shell after the v1 brief has been rendered
+and persisted. The link is surfaced only after `create_campaign` returns both:
 
-The watch link is only surfaced after **both** of these tool calls succeed in
-this order:
+- `campaignId`
+- `watchUrl`
 
-1. `create_campaign({ campaignBrief, currentStep: "auto-execute-leads" })`
-   → response MUST include `{ campaignId, watchUrl }`
-2. `save_rubrics({ campaignOfferId, rubric })`
-   → must return success
+The shell must already contain the v1 campaign brief, so the user lands on a
+useful brief instead of an empty campaign.
 
-Both calls must succeed before the link is printed. Never print the link
-between the two calls. Never print the link if either call fails.
+Example skeleton:
 
-## Required Output Block
+```text
+I created the campaign shell with the brief already in it.
+You can watch the lead source, filters, and messages fill in from here.
 
-After both tool calls succeed, print exactly one user-facing block. The block
-must contain:
+No leads import and nothing sends yet.
 
-- a plain confirmation that the campaign was created and the approved brief was
-  saved
-- a one-line orientation sentence: `Open this to watch lead sourcing, rubric
-scoring, and messaging populate live.`
-- the `watchUrl` captured from the `create_campaign` response
+Watch link: {watchUrl}
 
-Example skeleton:
+Cool, let's find leads.
+```
 
-```text
-Campaign created. I saved the approved brief too.
+Atomic-mint legacy orientation:
 
+```text
 Open this to watch lead sourcing, rubric scoring, and messaging populate live.
-
-Watch link: {watchUrl}
 ```
 
-The exact wording may be adapted for tone, but the one-line orientation and
-the `watchUrl` are both required. Do not collapse the block into a single
-line with the link inline — the user needs to see the orientation clearly
-before they click.
+The exact wording may be adapted for tone, but the copy must make three things
+clear:
 
-## Partial-Mint Recovery
+- the campaign shell exists now
+- the brief is already visible in the campaign
+- import, sequence, and start are still blocked
 
-The following failure modes must NOT print the watch link:
+If shell creation fails or the response is missing `watchUrl`, stop and surface
+the error. Do not continue into campaignless source scouting in the active
+shell-first flow.
+If a legacy atomic-mint response is missing `watchUrl`, it is not a silent skip.
+Stop before `save_rubrics` and recover the missing signed URL first.
 
-- `create_campaign` errors (no campaign exists, no watchUrl was returned) →
-  surface the underlying error, do not proceed to `save_rubrics`. No
-  rollback needed.
-- `create_campaign` succeeds but the response is missing `watchUrl` → treat
-  as a recoverable failure. Stop before `save_rubrics`. Do not print a link.
-  Surface an explicit error that names the contract violation (the backend
-  tool should always return `watchUrl`; a missing value is a plumbing bug,
-  not a silent skip).
-- `save_rubrics` fails after `create_campaign` succeeds → either rollback the
-  `CampaignOffer` row, or mark an explicit recoverable failure state so the
-  user can retry rubric save. Never leave a silent partial campaign with no
-  rubrics. Do NOT print the watch link during this recovery window.
+## Step Orientation
 
-The guiding rule: a watch link points at a live, fully-minted campaign. If
-the campaign is half-minted, the link is misleading and must not be shown.
+After the shell exists, re-surface the same watch link only when it helps orient
+the user after a meaningful step change:
 
-## Resume Re-Surface
+- source selected: the campaign should point at the primary provider step
+- rubrics saved: the campaign should show filter/rubric state
+- message set approved: the campaign should show message state
+- 10-lead test batch imported/generated: the campaign should show the test rows
+- settings handoff: the campaign should open to Settings for sender attachment
+- running: the campaign is live
 
-Users can quit the session after `approve` and reopen later. Plan 85-02
-handles autonomous tail resume via `CampaignOffer.currentStep`. Part of the
-resume contract is re-surfacing the same watch link so the user reorients
-without digging through prior transcript.
+Do not spam the link between internal tool calls.
+
+## Resume Re-Surface
 
 On resume:
 
 1. Load the `CampaignOffer` for the campaign being resumed.
-2. Call the same tool that yielded the link on mint (e.g.
-   `create_campaign({ campaignId })`, which is idempotent and returns the
-   existing campaign's `watchUrl` + state — see the v1 pattern in
-   `mcp/sellable/skills/create-campaign/SKILL.md`).
-3. Print the same block again with the one-line orientation plus `watchUrl`.
+2. Recover the signed link through the existing resume path
+   (`create_campaign({ campaignId })` when available).
+3. Inspect `currentStep` and print a short orientation for where the user will
+   land now.
+4. Print the recovered `watchUrl`.
 
 The re-surface must use the signed `watchUrl` from the tool response, not a
 cached or reconstructed URL.
 
 ## Hard Rules
 
-- Surface the link **once** on successful atomic mint, and re-surface on
-  resume. Do not spam the link between intermediate autonomous-tail steps.
-- Never print the link while the mint is mid-flight. Both
-  `create_campaign` and `save_rubrics` must have succeeded first.
-- Never fabricate or reconstruct the URL locally. Capture it from the
-  `create_campaign` response.
-- Missing `watchUrl` in the response is an error, not a silent skip.
-- Partial-mint states (campaign row created but rubrics not saved) must
-  block link surfacing and surface the recovery path instead.
+- Never fabricate or reconstruct the URL locally.
+- Missing `watchUrl` is an error, not a silent skip.
+- The first watch link must be shown only after the v1 brief is on the campaign.
+- A watch link is not approval to import, attach sequence, or start.
+- Import/enrichment remains blocked until rubrics are saved and the approved
+  message set is synced into the campaign brief.
+
+## Partial-Mint Recovery
+
+If `save_rubrics` fails after `create_campaign` succeeds, prefer a recoverable
+failure state with explicit retry. Rollback is an operator escape hatch, not the
+default. Never leave a silent partial campaign.
+Use rollback only as an explicit operator escape hatch.
+Store a recoverable failure state for retry before any watch link is shown.
+
+Do NOT print the watch link during this recovery window. A partial campaign link
+is misleading and must not be shown; block link surfacing and surface the
+recovery path instead.
+During partial mint, block link surfacing and surface the recovery path.

package/skills/create-campaign-v2-tail/SKILL.md

@@ -8,6 +8,11 @@ visibility: internal
 
 This is the tail detail extracted from the main create-campaign-v2 SKILL.md to keep the entry prompt slim. The agent loads this on-demand BEFORE entering the auto-execute or validate-sample steps. Follow this verbatim.
 
+CampaignOffer state is canonical; disk artifacts are a debug trail. All 14 disk
+artifacts remain as debug outputs, but resume, gating, and handoff read campaign
+state first. selectedLeadListId remains the source list; workflowTableId is the
+campaign table.
+
 ## MANDATORY TOOL ORDER (read this BEFORE any tail step)
 
 Every tail run MUST call these tools in this exact order. The tail is
@@ -20,16 +25,24 @@ Do NOT manually run rubric-check, enrich, or message-generation
 tools — the cascade already does them.
 
 ```text
-Step 13 — import review batch + kick bounded cascade
+Step 13 — import/confirm review batch only
+  materialize/reuse approved source with campaignOfferId
   import_leads(targetLeadCount=importLimit)
   wait_for_lead_list_ready
   confirm_lead_list
-  get_rows_minimal                 # capture enrichCellIds
+  wait_for_campaign_table_ready    # campaign table exists
+  get_rows_minimal                 # read imported review batch
+  update_campaign(currentStep=filter-choice)
+
+Post-import main thread
+  launch Lead Fit Builder + Message Draft Builder after workflowTableId exists
+  save_rubrics({ campaignOfferId, leadScoringRubrics }) after the campaign table exists
+  show readable filters + one concrete sample message
+  after approval, update_campaign_brief writes `## Approved Message Template` with `{{...}}` tokens
+
+Step 14 — kick bounded cascade + observe sample
   queue_cells(cellIds=<review-batch Enrich Prospect cells only>)  <-- starts bounded chain
   wait_for_campaign_table_ready    # review-batch cascade drains here
-  update_campaign(currentStep=validate-sample)
-
-Step 14 — observe sample
   get_rows_minimal                 # read passesRubric + message cell status per row
   compute projectedPass
   if OK: update_campaign(currentStep=auto-execute-messaging)
@@ -46,7 +59,9 @@ Step 15 — observe messaging
   (generate_messages is NOT an MCP tool; messages come from the cascade)
 
 Step 16 — awaiting-user-greenlight
-  attach_recommended_sequence({ campaignId })  # tier-aware: premium/SN -> If Open Profile->INMAIL_OPEN, else INVITE->accepted->DM
+  get_campaign + list_senders
+  if no sender attached: surface campaign settings link and STOP
+  if sender attached: attach_recommended_sequence({ campaignId })  # tier-aware: premium/SN -> If Open Profile->INMAIL_OPEN, else INVITE->accepted->DM
   re-surface watchUrl + review-batch orientation
   STOP. DO NOT call start_campaign. DO NOT auto-advance currentStep.
 ```
@@ -118,10 +133,17 @@ After every `update_campaign({ currentStep: ... })` in the tail, narrate
 what changed and orient the user to what the watch link will show next —
 reuse the v1 `create-campaign` watch-mode pattern verbatim.
 
+Resume currentStep names covered by this tail: `"auto-execute-leads"`,
+`"validate-sample"`, `"auto-execute-messaging"`,
+`"awaiting-user-greenlight"`, and `"running"`. New mint-early runs normally
+enter Step 13 from `"confirm-lead-list"`; the `"auto-execute-leads"` string is
+kept for compatibility resumes.
+
 ## Step 13: auto-execute-leads
 
-Entered on `CampaignOffer.currentStep === "auto-execute-leads"` (set by
-atomic mint).
+Entered from the lead-source confirmation path, with
+`CampaignOffer.currentStep === "confirm-lead-list"` or an equivalent source
+import milestone.
 
 > Reminder: every provider search you run from this point forward — the
 > review-batch source rerun in Step 13, any expansion search after the
@@ -139,24 +161,16 @@ atomic mint).
 > - the **campaign workflow table** (`CampaignOffer.workflowTableId`,
 >   also returned as `campaignTableId` from `confirm_lead_list`).
 >
-> `confirm_lead_list` overwrites `CampaignOffer.selectedLeadListId` with
-> the campaign-table id. That means after the first confirm, the
-> campaign-table id is NOT a valid `sourceLeadListId` for any future
-> `import_leads` call.
->
-> When you scale up the import, `mode: "add"` requires the ORIGINAL
-> lead-list id (the one returned by the first `import_leads`), never the
-> campaign-table id. Passing the campaign-table id silently writes
-> straight into the campaign workflow table, bypassing the lead list
-> entirely; the lead list stays at its original size and the
-> campaign-builder `/leads` UI throws "Lead list not found" because it
-> expects `selectedLeadListId` to resolve as a lead list.
+> `confirm_lead_list` must preserve the source lead-list id as
+> `CampaignOffer.selectedLeadListId` and store the campaign workflow table as
+> `CampaignOffer.workflowTableId`. The campaign-table id is NOT a valid
+> `sourceLeadListId` for future `import_leads(mode: "add")` calls.
 >
-> Capture the original `leadListId` from the FIRST `import_leads`
-> response and reuse it for every scale-up `import_leads(mode: "add")`
-> call on the same campaign. If the original id is unknown, query
-> for the lead-list table by name or skip the `mode: "add"` path; do
-> not pass the campaign-table id as `sourceLeadListId`.
+> Capture the original `leadListId` from the FIRST `import_leads` response and
+> reuse it for every scale-up `import_leads(mode: "add")` call on the same
+> campaign. If the original id is unknown, query for the lead-list table by
+> name or skip the `mode: "add"` path; do not pass the campaign-table id as
+> `sourceLeadListId`.
 
 1. Load `core/auto-execute.yaml` through
    `get_subskill_asset({ subskillName: "create-campaign-v2", assetPath: "core/auto-execute.yaml" })`.
@@ -165,12 +179,16 @@ atomic mint).
    `messaging.critique.enabled`, `handoff.autoStart`,
    `handoff.orientation`, `retry.sameToolSameError`,
    `logging.logEveryThresholdTrip`.
-2. Resolve the approved source before importing. If there is no
-   `lead-source-intake.json`, keep the existing discovered-provider path:
-   `import_leads({ campaignOfferId, targetLeadCount: importLimit })`.
+2. Resolve and materialize the approved source before importing. Load
+   `references/post-mint-source-materialization.md` when the source is normal
+   discovery or when a legacy no-shell approval fixture must be replayed. If
+   CampaignOffer state already attached searches/selections to this campaign,
+   reuse them. If there is no `lead-source-intake.json`, replay the approved
+   provider recipe from `lead-review.md` with `campaignOfferId` before
+   `import_leads`.
    If a manifest exists, branch by `sourceType`:
    - `supplied-linkedin-profiles`: revalidate file metadata and confirmation
-     token, confirm `load_csv_linkedin_leads` only after approval to batch the
+     token, confirm `load_csv_linkedin_leads` as source-list materialization to batch the
      supplied CSV into a Sellable lead list, persist the returned `leadListId`,
      then call `confirm_lead_list({ sourceLeadListId: leadListId,
 targetLeadCount: importLimit })`. Do not call `import_leads` for this
@@ -188,66 +206,66 @@ targetLeadCount: importLimit })`. Do not call `import_leads` for this
      the cap, import only the first `importLimit` rows and leave the rest for
      a later expansion step.
      Persist or recover materialized IDs on resume: `leadListId`,
-     `domainFilterId`, `searchId`, `campaignTableId`, imported row IDs, and queued
-     cell IDs. If the source file changed after preview, or an existing lead list
+     `domainFilterId`, `searchId`, `selectedLeadListId`, `workflowTableId`, and
+     imported row IDs. If the source file changed after preview, or an existing lead list
      is missing/wrong-workspace, escalate before materialization instead of
      silently applying stale preview data. Retrying Step 13 must not duplicate
-     lead lists, searches, campaign rows, or queued cells.
-3. `wait_for_lead_list_ready` and `confirm_lead_list`.
-4. **Verify the table is set up properly before queuing.** Call
-   `get_rows_minimal({ tableId })` and confirm:
-   - `Enrich Prospect` column exists on the table and every imported
-     row has a corresponding cell with `status === "pending"`.
-   - `DNC Check`, `ICP Score`, `Passes Rubric`, and `Generate Message`
-     columns all exist too (the cascade depends on all of them).
-   - If any are missing, or the cell is in a non-`pending` terminal
-     state from an earlier run, ESCALATE with an explicit "table not
-     configured for autonomous tail" diagnosis. Do NOT attempt to
-     patch the table shape from the tail.
-5. **Kick off the bounded review-batch cascade.** `queue_cells({ tableId,
-cellIds: <pending enrichCellIds for the imported review batch only> })`.
-   You queue ONLY the review-batch `Enrich Prospect` cells; the cascade
-   auto-dispatches `DNC Check`, `ICP Score`, `Passes Rubric`, and (for rows
-   where `Passes Rubric === true`) `Generate Message` as each upstream
-   completes. Do not queue cells for any rows beyond `importLimit` before
-   user expansion approval.
-6. `wait_for_campaign_table_ready` — waits for the review-batch cascade to
-   drain.
-   If it times out with most cells still `pending`, ESCALATE: the
-   engine is blocked.
-7. If the import returns zero usable leads, ESCALATE per
+     lead lists, searches, or campaign rows.
+     Normal discovery provider order:
+   - Signal Discovery: `get_provider_prompt({ provider: "signal-discovery",
+campaignOfferId, confirmed: true })` -> `search_signals({ campaignOfferId,
+...approved recipe })` -> `select_promising_posts({ campaignOfferId,
+selectionMode: "replace", selections, headlineICPCriteria })` ->
+     `import_leads({ campaignOfferId, provider: "signal-discovery",
+targetLeadCount: importLimit })`.
+   - Sales Nav: `get_provider_prompt({ provider: "sales-nav", campaignOfferId,
+confirmed: true })` -> rebuild/verify filter IDs -> `search_sales_nav({
+campaignOfferId, filters, confirmed: true })` -> `import_leads({
+campaignOfferId, provider: "sales-nav", searchId, targetLeadCount:
+importLimit })`.
+   - Prospeo: `get_provider_prompt({ provider: "prospeo", campaignOfferId,
+confirmed: true })` -> reuse `domainFilterId` when present ->
+     `search_prospeo({ campaignOfferId, filters, domainFilterId, confirmed:
+true })` -> `import_leads({ campaignOfferId, provider: "prospeo",
+searchId, targetLeadCount: importLimit })`.
+3. `wait_for_lead_list_ready` when a provider import job exists, then
+   `confirm_lead_list`. Persist both identifiers: `selectedLeadListId` remains
+   the source list and `workflowTableId` is the campaign table.
+4. `wait_for_campaign_table_ready` until the bounded review-batch rows are
+   available in the campaign table.
+5. Call `get_rows_minimal({ tableId: workflowTableId })` and confirm the first
+   review batch is present. Do not queue cells in Step 13.
+6. If the import returns zero usable leads, ESCALATE per
    `references/escalation-ladder.md` (hard fail).
-8. `update_campaign({ campaignId, currentStep: "validate-sample" })`.
-9. Orient user on the watch link (same pattern as every other step
+7. `update_campaign({ campaignId, currentStep: "filter-choice" })`.
+8. Orient user on the watch link (same pattern as every other step
    change).
 
 **Do NOT call `check_rubric`, `wait_for_rubric_results`,
-`enrich_with_prospeo`, or `bulk_enrich_with_prospeo` in Step 13.**
+`queue_cells`, `enrich_with_prospeo`, or `bulk_enrich_with_prospeo` in Step 13.**
 Those are direct-API tools that fetch enrichment/scoring data to the
-caller; they do not write to the workflow table cells. The cascade
-triggered by `queue_cells` runs the `Enrich Prospect` column's
-http_request, which writes the enrichment into the cell, which
-triggers the next column, and so on. Running the direct-API tools
-is duplicate work with no cell-population side effect.
+caller or start the workflow-table cascade too early. The cascade starts in
+Step 14 only after `save_rubrics` and `update_campaign_brief` have both
+succeeded.
 
 ## Step 14: validate-sample (loop)
 
 Entered on `CampaignOffer.currentStep === "validate-sample"`. Full
 decision tree lives in `references/sample-validation-loop.md`.
 
-**Step 14 is pure observation.** The bounded review-batch cascade that Step
-13 kicked off (via `queue_cells` on Enrich Prospect) has already written ICP
-scores and Passes Rubric values back into the workflow table. Step 14 reads
-those review-batch cell results — it does NOT call `check_rubric`,
-`wait_for_rubric_results`, `bulk_enrich_with_prospeo`, or any other
-direct enrichment/scoring tool. All of that already happened in the
-cascade; running them again is wasted work and can overwrite the
-real cell results with unrelated data.
+**Step 14 starts the bounded cascade, then observes it.** Step 13 imported the
+review batch only. After `save_rubrics` and the approved message template are
+persisted, Step 14 queues the review-batch Enrich Prospect cells, waits for the
+table cascade to drain, then reads the resulting ICP scores and Passes Rubric
+values. It does NOT call `check_rubric`, `bulk_enrich_with_prospeo`, or any
+other direct enrichment/scoring tool.
 
 Shape:
 
 ```text
-get_rows_minimal({ tableId })
+queue_cells({ tableId: workflowTableId, cellIds: reviewBatchEnrichCellIds })
+wait_for_campaign_table_ready({ tableId: workflowTableId })
+get_rows_minimal({ tableId: workflowTableId })
 passInSample = count of first sampleSize review-batch rows with passesRubric === true
 projectedPass = round(passInSample / sampleSize * importLimit)
 
@@ -376,13 +394,20 @@ Full contract lives in `references/final-handoff-contract.md`.
 
 Shape:
 
-1. `attach_sequence` (bind the committed sequence to the campaign).
-2. Re-surface the `watchUrl` using `references/watch-link-handoff.md`.
-3. Surface the `handoff.orientation` string from `auto-execute.yaml`
+1. Call `get_campaign({ campaignId })` and inspect sender/sequence state.
+2. Call `list_senders()` so you can surface connected sender options if the
+   campaign has no attached sender.
+3. If the campaign has no attached sender, surface a direct settings link:
+   `/campaign-builder/{campaignId}/settings?mode=claude`. Tell the user to attach
+   a sender in Settings, then return here. STOP before sequence attach/start.
+4. If a sender is attached, call `attach_recommended_sequence({ campaignId })`
+   (bind the tier-recommended sequence to the campaign).
+5. Re-surface the `watchUrl` using `references/watch-link-handoff.md`.
+6. Surface the `handoff.orientation` string from `auto-execute.yaml`
    alongside the link.
-4. STOP. Do NOT call `start_campaign`. Do NOT auto-advance
+7. STOP. Do NOT call `start_campaign`. Do NOT auto-advance
    `currentStep`. The autonomous tail ends here.
-5. Make the credit boundary explicit in the handoff: only the first review
+8. Make the credit boundary explicit in the handoff: only the first review
    batch has been enriched/messaged; expanding to more leads requires a
    separate user instruction.
 
@@ -394,10 +419,12 @@ campaign:
   the running state and shifts to a "campaign is live" confirmation.
 - **Claude greenlight path** — user replies with an affirmative ("yeah
   start" / "looks good, start" / "ship it"). The skill then performs,
-  in order: (a) bulk-approve queued messages via the EXISTING endpoint
+  in order: (a) `get_campaign` and verify a sender is attached, (b) if no
+  sequence is attached, `attach_recommended_sequence({ campaignId })`, (c)
+  bulk-approve queued messages via the EXISTING endpoint
   `POST /api/v3/workflow-tables/cells/approve-batch` (do NOT invent a
-  new tool/endpoint), (b) `start_campaign({ campaignId })`, (c)
-  `update_campaign({ campaignId, currentStep: "running" })`, (d)
+  new tool/endpoint), (d) `start_campaign({ campaignId })`, (e)
+  `update_campaign({ campaignId, currentStep: "running" })`, (f)
   re-surface `watchUrl` plus a "campaign is live" confirmation.
 
 A Claude greenlight on an already-running campaign is a no-op
@@ -418,6 +445,9 @@ runs.
 ## Tail Hard Rules
 
 - Review-batch sourcing/import happens in Step 13, not during atomic mint.
+- Step 13 materializes/reuses the approved source with `campaignOfferId` before
+  import. Do not import a legacy campaignless Signal source until selected posts
+  exist on the campaign.
 - Full-list expansion is not part of the default tail. It requires user
   approval after the review batch.
   Import must never exceed `importLimit`.
@@ -434,18 +464,19 @@ runs.
 
 <references_index>
 
-| File                                       | Load when                                                              |
-| ------------------------------------------ | ---------------------------------------------------------------------- |
-| `references/approval-gate-framing.md`      | Phase 85 commit gate, before showing the approval packet               |
-| `references/watch-link-handoff.md`         | Atomic mint + every tail resume, before surfacing watchUrl             |
-| `references/sample-validation-loop.md`     | Step 14, before enriching + scoring the sample                         |
-| `references/escalation-ladder.md`          | Any tail step that needs to decide retry / revise / escalate           |
-| `references/final-handoff-contract.md`     | Step 16, and every Claude greenlight turn                              |
-| `references/parallel-critique-protocol.md` | Step 15 when `messaging.critique.enabled` is true                      |
-| `references/thomas-variant-selection.md`   | Step 15 when `messaging.critique.opus.enabled` is true                 |
-| `references/thomas-revision-filters.md`    | Any critique rewrite, before persisting                                |
-| `core/auto-execute.yaml`                   | Start of Step 13, load once; all tail steps read parsed values         |
-| `core/auto-execute.README.md`              | When tuning `auto-execute.yaml` knobs or reviewing threshold-trip logs |
+| File                                             | Load when                                                                 |
+| ------------------------------------------------ | ------------------------------------------------------------------------- |
+| `references/approval-gate-framing.md`            | Phase 85 commit gate, before showing the approval packet                  |
+| `references/watch-link-handoff.md`               | Atomic mint + every tail resume, before surfacing watchUrl                |
+| `references/post-mint-source-materialization.md` | Step 13, before importing normal-discovery or legacy campaignless sources |
+| `references/sample-validation-loop.md`           | Step 14, before enriching + scoring the sample                            |
+| `references/escalation-ladder.md`                | Any tail step that needs to decide retry / revise / escalate              |
+| `references/final-handoff-contract.md`           | Step 16, and every Claude greenlight turn                                 |
+| `references/parallel-critique-protocol.md`       | Step 15 when `messaging.critique.enabled` is true                         |
+| `references/thomas-variant-selection.md`         | Step 15 when `messaging.critique.opus.enabled` is true                    |
+| `references/thomas-revision-filters.md`          | Any critique rewrite, before persisting                                   |
+| `core/auto-execute.yaml`                         | Start of Step 13, load once; all tail steps read parsed values            |
+| `core/auto-execute.README.md`                    | When tuning `auto-execute.yaml` knobs or reviewing threshold-trip logs    |
 
 Load every file in this table with: