@sellable/mcp 0.1.5 → 0.1.6

package/README.md

@@ -80,50 +80,33 @@ The token is provided when you generate it. Use `list_workspaces` +
 
 ### 4. Codex Setup
 
-For customer/package installs, use:
+For customer/package installs, use the public installer:
 
 ```bash
-npx -y @sellable/install --host codex --token skt_live_your_token_here --workspace-id your_workspace_id
+npx -y @sellable/install@0.1.6 --host codex --token skt_live_your_token_here --workspace-id your_workspace_id
 ```
 
-For local repo/Desktop development, run the installer from this repo:
+If you already have `~/.sellable/config.json`, rerun/verify without rewriting
+auth:
 
 ```bash
-npm run sellable:codex:install -- --token skt_live_your_token_here --workspace-id your_workspace_id
+npx -y @sellable/install@0.1.6 --host codex
+sellable --verify-only --host codex
 ```
 
 The installer does the full local setup:
 
-- builds the Sellable MCP server
-- uses repo-local `web` skills by default, so the Codex picker has one Sellable
-  entry per workflow
-- removes stale Personal Sellable skill copies, including
-  `sellable-create-campaign-v2`
 - writes `~/.sellable/config.json`
 - registers the `sellable` MCP server with Codex
-- installs the local `sellable@sellable-local` Desktop plugin so Codex
-  Desktop loads the `mcp__sellable__*` tools into skill sessions
-- runs a Codex CLI smoke that must load `get_auth_status` and the
-  `create-campaign-v2` prompt
-
-If you already have `~/.sellable/config.json`, verify the install without
-rewriting auth:
-
-```bash
-npm run sellable:codex:install -- --verify-only
-```
-
-For published-package installs instead of this local checkout:
-
-```bash
-npm run sellable:codex:install -- --server-mode package --skill-scope personal --token skt_live_your_token_here --workspace-id your_workspace_id
-```
+- installs the `sellable@sellable` Desktop plugin so Codex Desktop loads the
+  `mcp__sellable__*` tools into skill sessions
 
 After the installer passes, fully quit and reopen Codex Desktop. Start a new
-thread from the repo and select the `web` `Sellable Create Campaign` entry. If
-the app still says `mcp__sellable__*` tools are missing after the installer
-passes, check that `~/.codex/config.toml` contains both
-`[marketplaces.sellable-local]` and `[plugins."sellable@sellable-local"]`.
+thread and select `Sellable Create Campaign`, or invoke
+`$sellable:create-campaign`. If the app still says
+`mcp__sellable__*` tools are missing after the installer passes, check that
+`~/.codex/config.toml` contains both `[marketplaces.sellable]` and
+`[plugins."sellable@sellable"]`.
 The skill being visible only proves skill discovery; the plugin is what mounts
 the Sellable MCP tools for Codex Desktop.
 
@@ -164,9 +147,9 @@ Use the Codex skill entrypoint:
 $sellable:create-campaign
 ```
 
-Skill package path in this repo:
+Installed skill package path:
 
-- `.agents/skills/sellable-create-campaign/SKILL.md`
+- `~/.codex/plugins/cache/sellable/sellable/<version>/skills/sellable-create-campaign/SKILL.md`
 
 ## Host Parity Runbook (Codex + Claude)
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.5",
+  "version": "0.1.6",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

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

@@ -74,20 +74,27 @@ Validated draft directory:
 - Net-new runs start at `bootstrap` -> `brief-interview` in
   `core/flow.v2.json`. Do not start at `validate-artifacts` unless resuming a
   compatibility run where all upstream artifacts already exist.
+- Use the host-native structured question gate whenever it is exposed. In
+  Claude Code, this is `AskUserQuestion`. In Codex, this is
+  `request_user_input`. Treat them as equivalent approval/intake gates and
+  persist the same draft artifacts after the user answers. If the session is
+  non-interactive or the host does not expose either structured question tool,
+  fall back to a normal chat question with the exact same choices and make the
+  fallback explicit to the user.
 - Fast Intake Mode is mandatory for hosted/rehearsal net-new runs. Ask the
   first founder strategy/source question packet in under 60 seconds. Before
   that first packet, the first assistant turn may only call
   `bootstrap_create_campaign`, load this workflow prompt with
   `get_subskill_prompt({ subskillName: "create-campaign-v2" })`, optionally run
-  one lightweight identity lookup, then call `AskUserQuestion`. If the user
+  one lightweight identity lookup, then use the structured question gate. If the user
   supplied a company website/domain, call exactly one of `fetch_company`,
   `WebFetch`, or `WebSearch` to identify what the company actually does before
   generating intake options. If the user supplied a LinkedIn profile URL, call
   `fetch_linkedin_profile` before generating intake options. Do not infer the
   product category from the company name alone. If no domain, website, or
   LinkedIn profile is supplied, use neutral/custom intake options rather than
-  guessed vertical-specific options. Before the first AskUserQuestion, do not run
-  sender research, `list_senders`, source discovery, Sales Nav, Prospeo,
+  guessed vertical-specific options. Before the first structured question gate,
+  do not run sender research, `list_senders`, source discovery, Sales Nav, Prospeo,
   Signals, Bash, Read, Write, Edit, Glob, Grep, full company research, or
   draft-directory inspection/creation. Do draft-directory setup only after the
   founder answers. The first intake packet must ask buyer, offer/CTA, proof, and
@@ -199,9 +206,9 @@ There are two human gates:
   Earlier artifact gates are interrupt-only unless this contract explicitly
   names the `message-review` gate.
 
-Auto-continue without `AskUserQuestion` when the artifact says `Status:
-confirmed` (or equivalent), confidence is high/medium, volume is viable, and
-there is no strategic tradeoff.
+Auto-continue without a structured question gate when the artifact says
+`Status: confirmed` (or equivalent), confidence is high/medium, volume is
+viable, and there is no strategic tradeoff.
 
 Ask the user only when one of these is true:
 
@@ -688,9 +695,9 @@ or tone feedback you want before I build the approval packet.` Do not write
   The next Codex UAT goal is to prove message quality before mint, so no
   approval packet or campaign mutation should happen just because the mechanics
   are working.
-- immediately after rendering `message-review.md`, call `AskUserQuestion` with
-  exactly two choices, in this order: `approve-message`, `revise-messaging`.
-  Stop after the question. Do not write `approval-packet.md`,
+- immediately after rendering `message-review.md`, use the structured question
+  gate with exactly two choices, in this order: `approve-message`,
+  `revise-messaging`. Stop after the question. Do not write `approval-packet.md`,
   `customer-roleplay.md`, or a commit-gate question until
   `message-review-decision.md` contains `approve-message`.
 - if the selected winner or PS uses named customer/logo proof, quantified proof,
@@ -821,7 +828,7 @@ Do not:
   invitation to give manual feedback before approval
 - `Question: approve-message or revise-messaging?`
 - `Recommendation:` exactly `approve-message` or `revise-messaging`
-- The two-choice `AskUserQuestion` immediately after the rendered review
+- The two-choice structured question gate immediately after the rendered review
 
 `message-review-decision.md` must contain exactly one selected route:
 `approve-message` or `revise-messaging`. It does not authorize DB mutation.
@@ -956,15 +963,17 @@ anchors at the user.
 
 When rendering the approval packet inline, start it with exactly
 `Status: approval-packet`. Write the same content to `approval-packet.md`
-before showing the gate. The same assistant turn must then call
-`AskUserQuestion` with the six commit choices below. A commit-gate question
-without the inline `Status: approval-packet` packet is invalid UX. If a
+before showing the gate. The same assistant turn must then use the structured
+question gate with the six commit choices below. In Claude Code, call
+`AskUserQuestion`; in Codex, call `request_user_input` when available. A
+commit-gate question without the inline `Status: approval-packet` packet is
+invalid UX. If a
 customer roleplay is performed, write `customer-roleplay.md` before the final
 choice. A roleplay result that says "looks good", "approve", or equivalent is
 only critique; it does not satisfy the gate. Write `commit-gate-decision.md`
 only after the user/operator makes one explicit choice.
 
-Use `AskUserQuestion` with exactly these 6 choices, in this order:
+Use the structured question gate with exactly these 6 choices, in this order:
 
 ```text
 approve
@@ -1329,6 +1338,33 @@ atomic mint).
 > `search_prospeo`, `search_sales_nav`, `search_apollo`,
 > `search_signals`, and any other provider search tool added later.
 > Campaignless searches after mint orphan results from the campaign UI.
+>
+> **Lead-list vs campaign-table identity rule (do not confuse them):**
+> after the first `confirm_lead_list`, two workflow tables exist:
+>
+> - the **lead-list** table (the original `sourceLeadListId` returned by
+>   `import_leads`), and
+> - 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.
+>
+> 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`. Capture `import.importLimit`,
    `sample.sampleSize`, `sample.minProjectedPass`,

package/skills/create-campaign-v2/core/flow.v2.json

@@ -73,7 +73,8 @@
         "get_auth_status",
         "get_active_workspace",
         "get_subskill_prompt",
-        "AskUserQuestion"
+        "AskUserQuestion",
+        "request_user_input"
       ],
       "doNotAllow": [
         "create_campaign",
@@ -155,10 +156,7 @@
         }
       ],
       "requiredArtifacts": [],
-      "producesArtifacts": [
-        "brief-v1.md",
-        "brief.md"
-      ],
+      "producesArtifacts": ["brief-v1.md", "brief.md"],
       "allowedTools": [
         "get_subskill_prompt",
         "get_auth_status",
@@ -171,7 +169,8 @@
         "fetch_linkedin_posts",
         "WebFetch",
         "WebSearch",
-        "AskUserQuestion"
+        "AskUserQuestion",
+        "request_user_input"
       ],
       "doNotAllow": [
         "create_campaign",
@@ -183,17 +182,12 @@
         "start_campaign"
       ],
       "watchRequired": false,
-      "waitFor": [
-        "brief_v1_ready",
-        "confirm_with_user"
-      ],
+      "waitFor": ["brief_v1_ready", "confirm_with_user"],
       "transitions": {
         "brief_v1_ready": "brief-review",
         "confirm_with_user": "brief-review"
       },
-      "optionalProducesArtifacts": [
-        "lead-source-intake.json"
-      ]
+      "optionalProducesArtifacts": ["lead-source-intake.json"]
     },
     {
       "id": "brief-review",
@@ -216,22 +210,17 @@
           "action": "ask_continue_or_revise_only_if_needed",
           "autoContinueWhen": {
             "artifactStatus": "confirmed",
-            "confidenceIn": [
-              "high",
-              "medium"
-            ],
+            "confidenceIn": ["high", "medium"],
             "noOpenStrategicTradeoff": true,
             "noMissingRequiredInputs": true
           }
         }
       ],
-      "requiredArtifacts": [
-        "brief-v1.md",
-        "brief.md"
-      ],
+      "requiredArtifacts": ["brief-v1.md", "brief.md"],
       "producesArtifacts": [],
       "allowedTools": [
         "AskUserQuestion",
+        "request_user_input",
         "get_subskill_prompt"
       ],
       "doNotAllow": [
@@ -244,11 +233,7 @@
         "start_campaign"
       ],
       "watchRequired": false,
-      "waitFor": [
-        "user_brief_confirmed",
-        "revise_brief",
-        "auto_continue"
-      ],
+      "waitFor": ["user_brief_confirmed", "revise_brief", "auto_continue"],
       "transitions": {
         "user_brief_confirmed": "find-leads",
         "revise_brief": "brief-interview",
@@ -292,20 +277,11 @@
         },
         {
           "action": "write_artifacts",
-          "artifacts": [
-            "lead-review.md",
-            "lead-sample.json"
-          ]
+          "artifacts": ["lead-review.md", "lead-sample.json"]
         }
       ],
-      "requiredArtifacts": [
-        "brief-v1.md",
-        "brief.md"
-      ],
-      "producesArtifacts": [
-        "lead-review.md",
-        "lead-sample.json"
-      ],
+      "requiredArtifacts": ["brief-v1.md", "brief.md"],
+      "producesArtifacts": ["lead-review.md", "lead-sample.json"],
       "allowedTools": [
         "get_subskill_prompt",
         "get_provider_prompt",
@@ -317,6 +293,7 @@
         "fetch_company",
         "fetch_linkedin_profile",
         "AskUserQuestion",
+        "request_user_input",
         "load_csv_linkedin_leads",
         "load_csv_domains",
         "get_rows_minimal"
@@ -331,19 +308,13 @@
         "start_campaign"
       ],
       "watchRequired": false,
-      "waitFor": [
-        "lead_review_ready",
-        "revise_brief",
-        "confirm_with_user"
-      ],
+      "waitFor": ["lead_review_ready", "revise_brief", "confirm_with_user"],
       "transitions": {
         "lead_review_ready": "lead-review",
         "revise_brief": "brief-interview",
         "confirm_with_user": "lead-review"
       },
-      "optionalRequiredArtifacts": [
-        "lead-source-intake.json"
-      ],
+      "optionalRequiredArtifacts": ["lead-source-intake.json"],
       "toolRules": {
         "suppliedLinkedinProfiles": "Preview only before approval: call load_csv_linkedin_leads without confirmed, campaignOfferId, currentStep, leadListId, sourceLeadListId, or provider-import parameters; skip provider discovery.",
         "suppliedDomains": "May confirm load_csv_domains before approval only without campaignOfferId/currentStep to produce a standalone domainFilterId, then run a campaignless Prospeo sample constrained by domainFilterId.",
@@ -404,10 +375,7 @@
           "action": "ask_continue_revise_or_confirm_only_if_needed",
           "autoContinueWhen": {
             "status": "confirmed",
-            "confidenceIn": [
-              "high",
-              "medium"
-            ],
+            "confidenceIn": ["high", "medium"],
             "projectedGoodFitsAtLeast": 150,
             "samplePassRateAtLeast": 0.7,
             "noProviderMismatch": true,
@@ -415,13 +383,11 @@
           }
         }
       ],
-      "requiredArtifacts": [
-        "lead-review.md",
-        "lead-sample.json"
-      ],
+      "requiredArtifacts": ["lead-review.md", "lead-sample.json"],
       "producesArtifacts": [],
       "allowedTools": [
         "AskUserQuestion",
+        "request_user_input",
         "get_subskill_prompt"
       ],
       "doNotAllow": [
@@ -455,49 +421,31 @@
         {
           "action": "run_stage",
           "target": "filter-leads",
-          "inputs": [
-            "brief.md",
-            "lead-review.md",
-            "lead-sample.json"
-          ]
+          "inputs": ["brief.md", "lead-review.md", "lead-sample.json"]
         },
         {
           "action": "write_artifacts",
-          "artifacts": [
-            "lead-filter.md"
-          ],
-          "optionalArtifacts": [
-            "rubric.json"
-          ]
+          "artifacts": ["lead-filter.md"],
+          "optionalArtifacts": ["rubric.json"]
         },
         {
           "action": "ask_revise_only_if_filter_is_not_confirmed",
           "autoContinueWhen": {
             "status": "confirmed",
-            "decisionIn": [
-              "continue",
-              "confirmed"
-            ],
+            "decisionIn": ["continue", "confirmed"],
             "expectedUsableLeadsAtLeast": 150,
             "noHeavyFilteringWarning": true,
             "noCampaignMissRisk": true
           }
         }
       ],
-      "requiredArtifacts": [
-        "brief.md",
-        "lead-review.md",
-        "lead-sample.json"
-      ],
-      "producesArtifacts": [
-        "lead-filter.md"
-      ],
-      "optionalProducesArtifacts": [
-        "rubric.json"
-      ],
+      "requiredArtifacts": ["brief.md", "lead-review.md", "lead-sample.json"],
+      "producesArtifacts": ["lead-filter.md"],
+      "optionalProducesArtifacts": ["rubric.json"],
       "allowedTools": [
         "get_subskill_prompt",
-        "AskUserQuestion"
+        "AskUserQuestion",
+        "request_user_input"
       ],
       "doNotAllow": [
         "create_campaign",
@@ -543,17 +491,12 @@
           "artifact": "message-validation.md"
         }
       ],
-      "requiredArtifacts": [
-        "brief.md",
-        "lead-review.md",
-        "lead-sample.json"
-      ],
-      "producesArtifacts": [
-        "message-validation.md"
-      ],
+      "requiredArtifacts": ["brief.md", "lead-review.md", "lead-sample.json"],
+      "producesArtifacts": ["message-validation.md"],
       "allowedTools": [
         "get_subskill_prompt",
-        "AskUserQuestion"
+        "AskUserQuestion",
+        "request_user_input"
       ],
       "toolRules": [
         "Before writing message-validation.md, message-review.md, approval-packet.md, or a commit-gate AskUserQuestion, the current run must read 100% of the real generate-messages prompt via chunked get_subskill_prompt({ subskillName: \"generate-messages\", offset, limit }) calls.",
@@ -608,10 +551,7 @@
             "lead-filter.md",
             "message-validation.md"
           ],
-          "optionalFiles": [
-            "message-prep.md",
-            "message-candidate-drafts.md"
-          ]
+          "optionalFiles": ["message-prep.md", "message-candidate-drafts.md"]
         },
         {
           "action": "write_message_review",
@@ -639,10 +579,7 @@
             "Question: approve-message or revise-messaging?",
             "Recommendation:"
           ],
-          "allowedRecommendations": [
-            "approve-message",
-            "revise-messaging"
-          ],
+          "allowedRecommendations": ["approve-message", "revise-messaging"],
           "judgeAgainst": [
             "generate-messages rules",
             "gold-standard-* references",
@@ -666,19 +603,13 @@
         },
         {
           "action": "ask_message_review_choice",
-          "choices": [
-            "approve-message",
-            "revise-messaging"
-          ],
+          "choices": ["approve-message", "revise-messaging"],
           "stopAfterQuestion": true
         },
         {
           "action": "write_message_review_decision",
           "artifact": "message-review-decision.md",
-          "allowedChoices": [
-            "approve-message",
-            "revise-messaging"
-          ],
+          "allowedChoices": ["approve-message", "revise-messaging"],
           "doesNotAuthorizeMint": true
         },
         {
@@ -694,12 +625,10 @@
         "lead-filter.md",
         "message-validation.md"
       ],
-      "producesArtifacts": [
-        "message-review.md",
-        "message-review-decision.md"
-      ],
+      "producesArtifacts": ["message-review.md", "message-review-decision.md"],
       "allowedTools": [
         "AskUserQuestion",
+        "request_user_input",
         "get_subskill_prompt"
       ],
       "doNotAllow": [
@@ -712,10 +641,7 @@
         "start_campaign"
       ],
       "watchRequired": false,
-      "waitFor": [
-        "message_approved",
-        "revise_messaging"
-      ],
+      "waitFor": ["message_approved", "revise_messaging"],
       "transitions": {
         "message_approved": "approval-packet",
         "revise_messaging": "message-generation"
@@ -739,9 +665,7 @@
             "message-review.md",
             "message-review-decision.md"
           ],
-          "optionalFiles": [
-            "rubric.json"
-          ]
+          "optionalFiles": ["rubric.json"]
         },
         {
           "action": "require_message_review_decision",
@@ -763,11 +687,7 @@
             "risks and next action"
           ],
           "userFacing": true,
-          "doNotUseWords": [
-            "anchor",
-            "validation anchor",
-            "lane"
-          ]
+          "doNotUseWords": ["anchor", "validation anchor", "lane"]
         },
         {
           "action": "optional_customer_roleplay",
@@ -785,14 +705,11 @@
         "message-review.md",
         "message-review-decision.md"
       ],
-      "producesArtifacts": [
-        "approval-packet.md"
-      ],
-      "optionalProducesArtifacts": [
-        "customer-roleplay.md"
-      ],
+      "producesArtifacts": ["approval-packet.md"],
+      "optionalProducesArtifacts": ["customer-roleplay.md"],
       "allowedTools": [
         "AskUserQuestion",
+        "request_user_input",
         "get_subskill_prompt"
       ],
       "doNotAllow": [
@@ -809,9 +726,7 @@
       "transitions": {
         "approval_packet_ready": "commit-gate"
       },
-      "optionalRequiredArtifacts": [
-        "lead-source-intake.json"
-      ]
+      "optionalRequiredArtifacts": ["lead-source-intake.json"]
     },
     {
       "id": "validate-artifacts",
@@ -826,9 +741,7 @@
             "lead-filter.md",
             "message-validation.md"
           ],
-          "optionalFiles": [
-            "rubric.json"
-          ]
+          "optionalFiles": ["rubric.json"]
         },
         {
           "action": "validate_anchors",
@@ -841,17 +754,13 @@
           "doesNotAuthorizeMint": true
         }
       ],
-      "allowedTools": [
-        "AskUserQuestion"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
       "watchRequired": false,
       "waitFor": "artifacts_validated",
       "transitions": {
         "artifacts_validated": "approval-packet"
       },
-      "optionalRequiredArtifacts": [
-        "lead-source-intake.json"
-      ]
+      "optionalRequiredArtifacts": ["lead-source-intake.json"]
     },
     {
       "id": "commit-gate",
@@ -899,9 +808,7 @@
           "onlyApproveAuthorizesMint": true
         }
       ],
-      "allowedTools": [
-        "AskUserQuestion"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
       "watchRequired": false,
       "waitFor": [
         "user_approved",
@@ -919,9 +826,7 @@
         "user_revise_messaging": "revise-messaging",
         "user_abort": "abort"
       },
-      "optionalRequiredArtifacts": [
-        "lead-source-intake.json"
-      ]
+      "optionalRequiredArtifacts": ["lead-source-intake.json"]
     },
     {
       "id": "atomic-mint",
@@ -936,24 +841,16 @@
         },
         {
           "tool": "create_campaign",
-          "requiredFields": [
-            "campaignBrief",
-            "currentStep"
-          ],
+          "requiredFields": ["campaignBrief", "currentStep"],
           "requiredValues": {
             "currentStep": "auto-execute-leads"
           },
-          "capture": [
-            "campaignId",
-            "watchUrl"
-          ],
+          "capture": ["campaignId", "watchUrl"],
           "onMissingWatchUrl": "recoverable_failure_abort_before_rubric_save"
         },
         {
           "tool": "save_rubrics",
-          "requiredFields": [
-            "rubric"
-          ],
+          "requiredFields": ["rubric"],
           "onFailure": "rollback_or_recoverable_stop"
         },
         {
@@ -964,21 +861,17 @@
         },
         {
           "action": "surface_watch_link",
-          "requires": [
-            "create_campaign_succeeded",
-            "save_rubrics_succeeded"
-          ]
+          "requires": ["create_campaign_succeeded", "save_rubrics_succeeded"]
         }
       ],
       "allowedTools": [
         "bootstrap_create_campaign",
         "create_campaign",
         "save_rubrics",
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "import_leads"
+        "AskUserQuestion",
+        "request_user_input"
       ],
+      "doNotAllow": ["import_leads"],
       "watchRequired": true,
       "waitFor": "autonomous_tail_started",
       "transitions": {
@@ -1002,9 +895,7 @@
           "target": "85-02"
         }
       ],
-      "allowedTools": [
-        "AskUserQuestion"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
       "transitions": {
         "autonomous_tail_started": "auto-execute-leads"
       }
@@ -1041,10 +932,7 @@
         },
         {
           "tool": "import_leads",
-          "requiredFields": [
-            "campaignOfferId",
-            "targetLeadCount"
-          ],
+          "requiredFields": ["campaignOfferId", "targetLeadCount"],
           "targetLeadCountFromConfig": "import.importLimit",
           "onZeroLeads": "escalate_hard_fail",
           "modeAddHandshake": {
@@ -1058,19 +946,13 @@
         },
         {
           "tool": "wait_for_lead_list_ready",
-          "sourceBranches": [
-            "normal-discovery",
-            "supplied-domains"
-          ],
+          "sourceBranches": ["normal-discovery", "supplied-domains"],
           "skipWhen": "resolved source branch is supplied-linkedin-profiles or existing-lead-list; direct lead-list branches have no provider import job to wait on and this probe can poison the campaign import status"
         },
         {
           "tool": "confirm_lead_list",
           "targetLeadCountFromConfig": "import.importLimit",
-          "sourceBranches": [
-            "supplied-linkedin-profiles",
-            "existing-lead-list"
-          ]
+          "sourceBranches": ["supplied-linkedin-profiles", "existing-lead-list"]
         },
         {
           "tool": "get_rows_minimal",
@@ -1089,10 +971,7 @@
         },
         {
           "tool": "update_campaign",
-          "requiredFields": [
-            "campaignId",
-            "currentStep"
-          ],
+          "requiredFields": ["campaignId", "currentStep"],
           "requiredValues": {
             "currentStep": "validate-sample"
           }
@@ -1107,14 +986,13 @@
         "wait_for_campaign_table_ready",
         "update_campaign",
         "AskUserQuestion",
+        "request_user_input",
         "load_csv_linkedin_leads",
         "load_csv_domains",
         "get_provider_prompt",
         "search_prospeo"
       ],
-      "doNotAllow": [
-        "start_campaign"
-      ],
+      "doNotAllow": ["start_campaign"],
       "watchRequired": true,
       "waitFor": "leads_imported",
       "transitions": {
@@ -1146,17 +1024,11 @@
         },
         {
           "tool": "wait_for_rubric_results",
-          "requiredFields": [
-            "targetCount"
-          ],
+          "requiredFields": ["targetCount"],
           "targetCountSource": "stats.totalRows_or_imported_batch_count",
           "note": "default targetCount=25 returns ready=true after first 25 completions even when cohort is still pending; always pass cohortSize explicitly (see references/sample-validation-loop.md §Known Tool Behaviors #3)",
           "readVia": "subagent",
-          "extractFields": [
-            "ready",
-            "passRate.completed",
-            "stats"
-          ],
+          "extractFields": ["ready", "passRate.completed", "stats"],
           "doNotRetain": "rows_payload",
           "contextBloatNote": "25 rows ≈ 67KB; 100 rows ≈ 268KB; use subagent extraction (see references/sample-validation-loop.md §Known Tool Behaviors #2)"
         },
@@ -1182,7 +1054,8 @@
         "wait_for_rubric_results",
         "update_campaign_brief",
         "update_campaign",
-        "AskUserQuestion"
+        "AskUserQuestion",
+        "request_user_input"
       ],
       "doNotAllow": [
         "import_leads",
@@ -1198,10 +1071,7 @@
         "wait_for_rubric_results_targetCount_always_explicit"
       ],
       "watchRequired": true,
-      "waitFor": [
-        "sample_validated",
-        "sample_revision_required"
-      ],
+      "waitFor": ["sample_validated", "sample_revision_required"],
       "transitions": {
         "sample_validated": "auto-execute-messaging",
         "escalation_triggered": "escalation"
@@ -1283,10 +1153,7 @@
         },
         {
           "tool": "update_campaign",
-          "requiredFields": [
-            "campaignId",
-            "currentStep"
-          ],
+          "requiredFields": ["campaignId", "currentStep"],
           "requiredValues": {
             "currentStep": "awaiting-user-greenlight"
           }
@@ -1298,13 +1165,10 @@
         "wait_for_campaign_table_ready",
         "update_campaign_brief",
         "update_campaign",
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "import_leads",
-        "start_campaign",
-        "generate_messages"
+        "AskUserQuestion",
+        "request_user_input"
       ],
+      "doNotAllow": ["import_leads", "start_campaign", "generate_messages"],
       "hardRules": [
         "critique_failure_never_escalates",
         "critique_sample_size_bounded_by_config",
@@ -1316,10 +1180,7 @@
         "campaign_brief_must_contain_approved_message_template_tokens_before_generate_message_cascade"
       ],
       "watchRequired": true,
-      "waitFor": [
-        "review_batch_ready",
-        "sample_revision_required"
-      ],
+      "waitFor": ["review_batch_ready", "sample_revision_required"],
       "transitions": {
         "review_batch_ready": "awaiting-user-greenlight",
         "escalation_triggered": "escalation"
@@ -1336,10 +1197,7 @@
         },
         {
           "action": "surface_watch_link",
-          "requires": [
-            "create_campaign_succeeded",
-            "save_rubrics_succeeded"
-          ]
+          "requires": ["create_campaign_succeeded", "save_rubrics_succeeded"]
         },
         {
           "action": "surface_source_materialization_summary",
@@ -1361,25 +1219,18 @@
       ],
       "allowedTools": [
         "attach_recommended_sequence",
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "start_campaign",
-        "import_leads"
+        "AskUserQuestion",
+        "request_user_input"
       ],
+      "doNotAllow": ["start_campaign", "import_leads"],
       "autoStart": false,
       "watchRequired": true,
-      "waitFor": [
-        "user_greenlight",
-        "ui_start_detected"
-      ],
+      "waitFor": ["user_greenlight", "ui_start_detected"],
       "transitions": {
         "user_greenlight": "claude-greenlight",
         "ui_start_detected": "running"
       },
-      "optionalRequiredArtifacts": [
-        "lead-source-intake.json"
-      ]
+      "optionalRequiredArtifacts": ["lead-source-intake.json"]
     },
     {
       "id": "claude-greenlight",
@@ -1405,16 +1256,11 @@
         },
         {
           "tool": "start_campaign",
-          "requiredFields": [
-            "campaignId"
-          ]
+          "requiredFields": ["campaignId"]
         },
         {
           "tool": "update_campaign",
-          "requiredFields": [
-            "campaignId",
-            "currentStep"
-          ],
+          "requiredFields": ["campaignId", "currentStep"],
           "requiredValues": {
             "currentStep": "running"
           }
@@ -1432,7 +1278,8 @@
         "get_campaign",
         "start_campaign",
         "update_campaign",
-        "AskUserQuestion"
+        "AskUserQuestion",
+        "request_user_input"
       ],
       "watchRequired": true,
       "waitFor": "campaign_started",
@@ -1452,13 +1299,8 @@
           "action": "surface_campaign_live_confirmation"
         }
       ],
-      "allowedTools": [
-        "get_campaign",
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "start_campaign"
-      ],
+      "allowedTools": ["get_campaign", "AskUserQuestion", "request_user_input"],
+      "doNotAllow": ["start_campaign"],
       "terminal": true
     },
     {
@@ -1486,13 +1328,8 @@
           ]
         }
       ],
-      "allowedTools": [
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "start_campaign",
-        "import_leads"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
+      "doNotAllow": ["start_campaign", "import_leads"],
       "terminal": true
     },
     {
@@ -1515,14 +1352,8 @@
           ]
         }
       ],
-      "allowedTools": [
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "create_campaign",
-        "save_rubrics",
-        "import_leads"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
+      "doNotAllow": ["create_campaign", "save_rubrics", "import_leads"],
       "terminal": true
     },
     {
@@ -1535,9 +1366,7 @@
         },
         {
           "action": "reset_draft_artifacts",
-          "preserve": [
-            "brief.md"
-          ],
+          "preserve": ["brief.md"],
           "delete": [
             "lead-review.md",
             "lead-sample.json",
@@ -1547,14 +1376,8 @@
           ]
         }
       ],
-      "allowedTools": [
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "create_campaign",
-        "save_rubrics",
-        "import_leads"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
+      "doNotAllow": ["create_campaign", "save_rubrics", "import_leads"],
       "terminal": true
     },
     {
@@ -1567,26 +1390,12 @@
         },
         {
           "action": "reset_draft_artifacts",
-          "preserve": [
-            "brief.md",
-            "lead-review.md",
-            "lead-sample.json"
-          ],
-          "delete": [
-            "lead-filter.md",
-            "message-validation.md",
-            "rubric.json"
-          ]
+          "preserve": ["brief.md", "lead-review.md", "lead-sample.json"],
+          "delete": ["lead-filter.md", "message-validation.md", "rubric.json"]
         }
       ],
-      "allowedTools": [
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "create_campaign",
-        "save_rubrics",
-        "import_leads"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
+      "doNotAllow": ["create_campaign", "save_rubrics", "import_leads"],
       "terminal": true
     },
     {
@@ -1605,19 +1414,11 @@
             "lead-sample.json",
             "lead-filter.md"
           ],
-          "delete": [
-            "message-validation.md"
-          ]
+          "delete": ["message-validation.md"]
         }
       ],
-      "allowedTools": [
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "create_campaign",
-        "save_rubrics",
-        "import_leads"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
+      "doNotAllow": ["create_campaign", "save_rubrics", "import_leads"],
       "terminal": true
     },
     {
@@ -1629,14 +1430,8 @@
           "target": ".aborted/"
         }
       ],
-      "allowedTools": [
-        "AskUserQuestion"
-      ],
-      "doNotAllow": [
-        "create_campaign",
-        "save_rubrics",
-        "import_leads"
-      ],
+      "allowedTools": ["AskUserQuestion", "request_user_input"],
+      "doNotAllow": ["create_campaign", "save_rubrics", "import_leads"],
       "terminal": true
     }
   ]

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

@@ -98,9 +98,13 @@ exactly:
 Status: approval-packet
 ```
 
-The same assistant turn must then call `AskUserQuestion` with the six commit
-choices. Do not show a standalone commit-gate question in a later turn without
-the approval packet above it.
+The same assistant turn must then use the host-native structured question gate
+with the six commit choices. In Claude Code, call `AskUserQuestion`. In Codex,
+call `request_user_input` when that tool is available. Do not show a standalone
+commit-gate question in a later turn without the approval packet above it. If
+the session is non-interactive or neither structured question tool is exposed,
+fall back to a normal chat question with the exact same choices and say that the
+structured gate is unavailable in this session.
 
 The packet should read like an AI GTM engineer explaining the campaign, not an
 internal validation report. Start with the practical direction in plain
@@ -199,8 +203,8 @@ revise-messaging
 abort
 ```
 
-Use `AskUserQuestion` with these 6 options. Do not collapse, reorder, or add
-choices. Do not auto-select.
+Use the host-native structured question gate with these 6 options. Do not
+collapse, reorder, or add choices. Do not auto-select.
 
 If the host UI limits options per question, preserve all six routes with a
 two-question gate instead of mentioning implementation limits: