@sellable/mcp 0.1.203 → 0.1.205

package/README.md

@@ -345,12 +345,12 @@ with outcomes, and tracked people (LinkedIn profiles), all scoped by workspace.
 
 - Auth + active workspace: `~/.sellable/config.json` (or `SELLABLE_CONFIG_PATH`; old `$CODEX_HOME/sellable.json`, `~/.codex/sellable.json`, and `~/.claude/sellable.json` files remain compatibility fallbacks)
 - Engage memory (style guide + searches + tracked people): `sellable.engage.json` (or `SELLABLE_ENGAGE_MEMORY_PATH`)
-- Team-editable, project-local configs (recommended to edit in git):
-  - `./.sellable/configs/writing/styleguide.md`
-  - `./.sellable/configs/audience/icp-filters.md`
-  - `./.sellable/configs/proof/claims.md`
-  - `./.sellable/configs/discovery/influencers.md`
-  - `./.sellable/configs/discovery/post-filters.md`
+- Team-editable durable configs (home-level source of truth):
+  - `~/.sellable/configs/writing/styleguide.md`
+  - `~/.sellable/configs/audience/icp-filters.md`
+  - `~/.sellable/configs/proof/claims.md`
+  - `~/.sellable/configs/discovery/influencers.md`
+  - `~/.sellable/configs/discovery/post-filters.md`
 
 Files under `mcp/sellable/skills/**/core/*` are **package repo files**, not the intended user config surface.
 
@@ -363,7 +363,7 @@ Primary public entrypoint for the approval-gated campaign creation flow.
 ### interview
 
 Public identity/company memory interview. Builds durable core files under
-`./.sellable/configs/core/**`, raw archives under `./.sellable/interviews/**`,
+`~/.sellable/configs/core/**`, raw archives under `~/.sellable/interviews/**`,
 and reusable answer/proof/story/transcript/reference memory for downstream
 Sellable writing workflows.
 

package/agents/post-find-leads-message-scout.md

@@ -44,9 +44,15 @@ the branch input.
 2. Use that prompt as the drafting contract. Do not use any alternate prompt,
    examples-only shortcut, or create-campaign safety/checklist instructions as a
    substitute for the full message prompt.
-3. Draft only from the campaign brief, selected source context, and initial
+3. Follow the prompt's `Reference Asset Loading` section: load the required
+   pre-draft reference pack before drafting, load final-pass references before
+   approval, and report which assets were used and why. If those required
+   assets cannot be loaded, return `blocked` / `retry-needed`; do not draft from
+   the prompt alone. `ai-tells.md` is part of the required pack and is never
+   optional.
+4. Draft only from the campaign brief, selected source context, and initial
    campaign-table execution slice rows supplied by the parent.
-4. Keep the work provisional until the user chooses `Use Template` in Messages.
+5. Keep the work provisional until the user chooses `Use Template` in Messages.
 
 ## Owned Output
 
@@ -54,6 +60,8 @@ Return the following to the parent thread:
 
 - proposed first-message template using supported `{{...}}` tokens
 - token fill rules and fallbacks
+- `Reference Asset Loading` note naming the required and conditional assets used
+  and why each was used
 - one rendered good-fill sample for a plausible passing campaign-table row
 - one omit/fallback sample when the row signal is not safe
 - pass/fail notes against the generate-messages quality gates
@@ -125,10 +133,14 @@ reacted to`, `saw you engaging with`, or equivalent source-citation copy as a
 hope this is relevant`, `saw you in a few conversations about [topic], so
 may be off, but this seemed relevant`, `saw you might be interested in [topic],
 so hope this is relevant`, `hope this is relevant if [topic] is on your plate`,
-or `saw you raise your hand for [topic], so figured this was (hopefully) worth sending`.
+or `found you in a thread about [topic], so may be off, but this seemed relevant`.
+Only use `saw you raise your hand for [topic], so figured this was (hopefully)
+worth sending` when the source was an explicit lead-magnet comment, reply, or
+opt-in.
 The cheekier `saw you raise your hand for [topic] (creepy to reach out based
 on that, i know) - but this felt too on the nose to ignore` version is also
-allowed when the sender's voice can carry it. Bad: `you commented on...`, `you reacted
+allowed only for explicit lead-magnet comments, replies, or opt-ins and when the
+sender's voice can carry it. Bad: `you commented on...`, `you reacted
 to...`, `saw you engaging with...`, `your LinkedIn activity...`, `you might
 not remember the thread...`, or `found you through [source] and your role
 looked close...`. Otherwise omit the engagement signal and use role/company/problem context.

package/dist/engage-memory.js

@@ -8,11 +8,6 @@ function resolveConfigsDir() {
     if (process.env.SELLABLE_CONFIGS_DIR) {
         candidates.push(path.resolve(process.env.SELLABLE_CONFIGS_DIR));
     }
-    // Same resolution strategy as skills.ts
-    if (process.argv[1]) {
-        candidates.push(path.resolve(path.dirname(process.argv[1]), "../../.sellable/configs"));
-    }
-    candidates.push(path.resolve(process.cwd(), ".sellable/configs"));
     candidates.push(path.resolve(os.homedir(), ".sellable/configs"));
     for (const candidate of candidates) {
         if (fs.existsSync(candidate)) {

package/dist/identity-memory.js

@@ -20,10 +20,6 @@ export function resolveIdentityConfigsDir() {
     if (process.env.SELLABLE_CONFIGS_DIR) {
         candidates.push(path.resolve(process.env.SELLABLE_CONFIGS_DIR));
     }
-    if (process.argv[1]) {
-        candidates.push(path.resolve(path.dirname(process.argv[1]), "../../.sellable/configs"));
-    }
-    candidates.push(path.resolve(process.cwd(), ".sellable/configs"));
     candidates.push(path.resolve(os.homedir(), ".sellable/configs"));
     for (const candidate of candidates) {
         if (fs.existsSync(candidate)) {

package/dist/tools/engage-memory.js

@@ -2,7 +2,7 @@ import { copySenderConfig, getEngageMemory, migrateFlatConfigs, recordProvenSear
 export const engageMemoryToolDefinitions = [
     {
         name: "get_engage_memory",
-        description: "Load backward-compatible engage memory from .sellable/configs/: style guide, proven search keywords, tracked people, plus optional core identity/company memory. All data lives in readable markdown files the user can also edit directly. When senderId is provided, reads compatibility overrides from senders/{senderId}/ with flat-path fallback.",
+        description: "Load backward-compatible engage memory from ~/.sellable/configs/: style guide, proven search keywords, tracked people, plus optional core identity/company memory. All data lives in readable markdown files the user can also edit directly. When senderId is provided, reads compatibility overrides from senders/{senderId}/ with flat-path fallback.",
         inputSchema: {
             type: "object",
             properties: {
@@ -17,7 +17,7 @@ export const engageMemoryToolDefinitions = [
     },
     {
         name: "set_engage_style_guide",
-        description: "Write the user's commenting style guide. When senderId is provided, writes to .sellable/configs/senders/{senderId}/styleguide-core.md. Otherwise writes to .sellable/configs/writing/styleguide-core.md.",
+        description: "Write the user's commenting style guide. When senderId is provided, writes to ~/.sellable/configs/senders/{senderId}/styleguide-core.md. Otherwise writes to ~/.sellable/configs/writing/styleguide-core.md.",
         inputSchema: {
             type: "object",
             properties: {

package/dist/tools/prompts.js

@@ -330,7 +330,7 @@ export function getPostFindLeadsScoutRegistry() {
                 "basis.workflowTableId",
                 "basis.reviewSampleRowHash or basis.reviewSampleRowIds",
             ],
-            promptRequired: 'get_subskill_prompt({ subskillName: "generate-messages" }); the full generate-messages prompt is required for normal message drafting',
+            promptRequired: 'get_subskill_prompt({ subskillName: "generate-messages" }); the full generate-messages prompt is required for normal message drafting, then follow its Reference Asset Loading step and load the required pre-draft reference pack before drafting. ai-tells.md is required and never optional. If the required assets cannot be loaded, return blocked/retry-needed instead of drafting from the prompt alone.',
             basisFields: [
                 "campaign revision or updatedAt",
                 "brief hash",
@@ -343,6 +343,7 @@ export function getPostFindLeadsScoutRegistry() {
             messageDraftOutputFields: [
                 "templateRecommendation",
                 "tokenFillRules",
+                "referenceAssetLoading",
                 "renderedSample",
                 "concerns",
                 "status",
@@ -357,7 +358,7 @@ export function getPostFindLeadsScoutRegistry() {
         usage: {
             codex: "After confirm_lead_list copies source rows and the initial campaign-table execution slice exists, ask the filter-choice question immediately. Do not spawn returned post-lead scout names before that question. Once the user answers, spawn Message Draft Builder from the same campaign/table basis. If the user chooses filters, also spawn Lead Fit Builder, move to Filter Rules, save rubrics, ask for filter approval, then keep the browser on Filter Leads and show `Filters saved + waiting for message approval` while the message recommendation is reviewed. If filters are skipped, move to Messages/message review.",
             claude: "After confirm_lead_list copies source rows and the initial campaign-table execution slice exists, ask the filter-choice question immediately. Do not invoke returned post-lead Task/Agent names before that question. Once the user answers, invoke Message Draft Builder from the same campaign/table basis. If the user chooses filters, also invoke Lead Fit Builder, move to Filter Rules, save rubrics, ask for filter approval, then keep the browser on Filter Leads and show `Filters saved + waiting for message approval` while the message recommendation is reviewed. If filters are skipped, move to Messages/message review.",
-            parentThreadRule: 'Named agents are optional acceleration, but message drafting is not optional. If post-find-leads-message-scout is available, run it as the background Message Draft Builder after the filter-choice answer. If it is absent, do not customer-surface install status; the main thread must execute the same message branch from CampaignOffer state, selected source state, workflowTableId, and initial campaign-table execution slice rows. Local markdown/json files are not normal-path inputs. The filter-choice question is the first post-import user gate; do not load post-lead registries or filter references before it. Message drafting starts after the filter-choice answer, must load get_subskill_prompt({ subskillName: "generate-messages" }), must read live campaign table state through scoped MCP/product tools, and must reject mismatched selectedLeadListId/workflowTableId/campaign/workspace input. Do not use any alternate or examples-only message prompt. On the filter path, keep the browser on Filter Rules after save_rubrics so the user can approve the saved criteria; only then move to Filter Leads, show `Filters saved + waiting for message approval`, and wait there for message approval. Enrichment, filtering, Generate Message cells, sender setup, sequence attach, and launch wait for template approval on the Use Template path. On the skip path, move to Messages/message review and wait for message approval before enrichment or Settings. Do not render message review from checklist or shortcut instructions; message review requires a messageDraftRecommendation whose basis proves the generate-messages prompt ran for the current campaign/table execution slice. Do not automatically rerun Message Draft Builder after filters/enrichment finish; show the initial draft by default and offer an enriched rewrite only with explicit user opt-in.',
+            parentThreadRule: 'Named agents are optional acceleration, but message drafting is not optional. If post-find-leads-message-scout is available, run it as the background Message Draft Builder after the filter-choice answer. If it is absent, do not customer-surface install status; the main thread must execute the same message branch from CampaignOffer state, selected source state, workflowTableId, and initial campaign-table execution slice rows. Local markdown/json files are not normal-path inputs. The filter-choice question is the first post-import user gate; do not load post-lead registries or filter references before it. Message drafting starts after the filter-choice answer, must load get_subskill_prompt({ subskillName: "generate-messages" }), must follow Reference Asset Loading and load the required pre-draft reference pack before drafting, must include ai-tells.md because it is never optional, must return blocked/retry-needed if required assets cannot be loaded, must read live campaign table state through scoped MCP/product tools, and must reject mismatched selectedLeadListId/workflowTableId/campaign/workspace input. Do not use any alternate or examples-only message prompt. On the filter path, keep the browser on Filter Rules after save_rubrics so the user can approve the saved criteria; only then move to Filter Leads, show `Filters saved + waiting for message approval`, and wait there for message approval. Enrichment, filtering, Generate Message cells, sender setup, sequence attach, and launch wait for template approval on the Use Template path. On the skip path, move to Messages/message review and wait for message approval before enrichment or Settings. Do not render message review from checklist or shortcut instructions; message review requires a messageDraftRecommendation whose basis proves the generate-messages prompt ran for the current campaign/table execution slice. Do not automatically rerun Message Draft Builder after filters/enrichment finish; show the initial draft by default and offer an enriched rewrite only with explicit user opt-in.',
         },
     };
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.203",
+  "version": "0.1.205",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-campaign/context/learnings.md

@@ -4,7 +4,7 @@ This log captures what has worked in real campaigns.
 
 Entries should be short, specific, and based on observed outcomes.
 
-**Cross-skill learnings** that would help other skills (engage, create-post) should ALSO be written to `.sellable/insights/cross-skill.md` so the entire system learns.
+**Cross-skill learnings** that would help other skills (engage, create-post) should ALSO be written to `~/.sellable/insights/cross-skill.md` so the entire system learns.
 
 ## Log
 

package/skills/create-campaign/references/brief-template.md

@@ -41,8 +41,8 @@ Example: "In a 15-minute call, we will audit your top 10 accounts and show where
 - **Bridge to:** [How it connects to their pain]
 - **Avoid:** [Generic phrases to skip - "best-in-class", "industry-leading", etc.]
 - **Voice:** [Reference core memory / composed engage memory first. Use legacy writing memory only as fallback.]
-- **Outbound rules:** [Reference `.sellable/configs/writing/outbound.md` if loaded -- observation -> relevance -> ask]
-- **Proof boundaries:** [Reference `.sellable/configs/core/proof-ledger.md` and `.sellable/configs/core/wins-ledger.md` if loaded. Do not upgrade or invent claims.]
+- **Outbound rules:** [Reference `~/.sellable/configs/writing/outbound.md` if loaded -- observation -> relevance -> ask]
+- **Proof boundaries:** [Reference `~/.sellable/configs/core/proof-ledger.md` and `~/.sellable/configs/core/wins-ledger.md` if loaded. Do not upgrade or invent claims.]
 
 ## Do NOT Target
 

package/skills/create-campaign-brief/references/brief-template.md

@@ -15,7 +15,7 @@ assistant message directly from the `result.result` stream-json payload —
 it does not read a file off disk.
 
 If you find yourself emitting a TodoWrite step like "Write brief.md v1
-to disk" or "Save brief to .sellable/..." — DELETE that step and return
+to disk" or "Save brief to ~/.sellable/..." — DELETE that step and return
 the brief inline instead. The tools `Write`, `Edit`, and `Bash` are
 intentionally not in the Phase 83 harness allowlist; attempting them
 will cause a ToolSearch loop that deadlocks the turn.
@@ -37,7 +37,7 @@ offer is, why it should work, and what must be true before we launch. Do not
 prescribe message structure, opener order, or final copy here.]
 
 Draft path:
-`.sellable/create-campaign-brief/drafts/{workspace-slug}/{campaign-slug}/brief.md`
+`~/.sellable/create-campaign-brief/drafts/{workspace-slug}/{campaign-slug}/brief.md`
 
 ## Product
 

package/skills/create-campaign-brief/references/draft-lifecycle.md

@@ -2,7 +2,7 @@
 
 Phase 83 writes one Markdown file:
 
-`.sellable/create-campaign-brief/drafts/{workspace-slug}/{campaign-slug}/brief.md`
+`~/.sellable/create-campaign-brief/drafts/{workspace-slug}/{campaign-slug}/brief.md`
 
 ## Rules
 

package/skills/create-campaign-brief/references/examples/briefs/gelee.md

@@ -58,7 +58,7 @@ _Personalization: References their previous exit or current venture by name + th
 
 Hi {{first_name}}, let me know if i'm off, but {{seems_like_you}}.
 
-saw you were active in some {{signal_topic}} conversations recently and figured this might be relevant.
+saw you in a few conversations around {{signal_topic}}, so hope this is relevant.
 
 we work with about 30 exited founders right now (yc, techstars, sequoia backed) handling their entire linkedin with ai + human review.
 
@@ -131,7 +131,7 @@ is this worth a look or should i send a short overview?
 
 Hi sarah, let me know if i'm off, but seems like you started building something new in the pharma space after the Benchling exit.
 
-saw you were active in some founder-led growth conversations recently and figured this might be relevant.
+saw you in a few conversations around founder-led growth, so hope this is relevant.
 
 we work with about 30 exited founders right now (yc, techstars, sequoia backed) handling their entire linkedin with ai + human review.
 

package/skills/create-campaign-brief/references/examples/briefs/superpower.md

@@ -35,70 +35,82 @@ Signal-based outreach using peer-to-peer tone. Positioning Superpower as early d
 
 **VARIANT 1 — Subject: jeff/{{first name}} intro**
 
-hey {{first name}}, saw you were active around some {{topic}} stuff recently and figured this might actually be relevant
+hey {{first name}},
 
-any chance you're exploring early detection or preventive health programs at {{company}}?
+saw you in a few conversations around {{topic}}, so hope this is relevant.
 
-we screen for 1,000+ conditions from a single blood draw and surface risks before they ever become claims.
+if preventive health is anywhere near the benefits plan at {{company}}, Superpower may be worth a look.
 
-basically your team gets to see what's coming instead of just reacting to it
+it screens for 1,000+ conditions from a single blood draw and surfaces risks before they become claims.
 
-can I send over some more info?
+basically your team gets to see what's coming instead of only reacting to it.
+
+should i send over the short version?
 
 **VARIANT 2 — Subject: jeff/{{first name}} intro**
 
-hey {{first name}}. saw you were active in some {{topic}} conversations recently and wanted to run something by you
+hey {{first name}},
+
+saw you in a few conversations around {{topic}}, so hope this is relevant.
 
 most annual physicals test 15 biomarkers max.
 
-there's over 100 that actually matter and the gap between those two numbers is where the expensive claims tend to sit
+Superpower looks at 100+ biomarkers and screens for 1,000+ conditions from one draw.
 
-teams like Lyft and Notion are already exploring this. one draw, 1,000+ conditions, $199 a person.
+teams like Lyft and Notion are already exploring this at $199 a person.
 
-if your claims costs have been going up and you're not sure where it's coming from... that gap may be a good place to start looking
+if preventive health is nowhere near your lane, ignore me.
 
-can I send over some more info?
+should i send over the short version?
 
 ## Examples
 
 **Example 1 (Variant 1 — self-insured health plans):**
 Subject: susana/prab intro
 
-hey susana, saw you were active around self-insured health plan content recently and figured this might actually be relevant
+hey susana,
+
+saw you in a few conversations around self-insured health plans, so hope this is relevant.
 
-any chance you're exploring preventive health programs at Quantum Health?
+if preventive health is anywhere near the benefits plan at Quantum Health, Superpower may be worth a look.
 
-we screen for 1,000+ conditions from a single blood draw and surface risks before they ever become claims.
+it screens for 1,000+ conditions from a single blood draw and surfaces risks before they become claims.
 
-basically your team gets to see what's coming instead of just reacting to it
+basically your team gets to see what's coming instead of only reacting to it.
 
-can I send over some more info?
+should i send over the short version?
 
 **Example 2 (Variant 2 — employee wellness programs):**
 Subject: lisa/prab intro
 
-hey lisa. saw you were active in some employee wellness programs conversations recently and wanted to run something by you
+hey lisa,
+
+saw you in a few conversations around employee wellness programs, so hope this is relevant.
 
 most annual physicals test 15 biomarkers max.
 
-there's over 100 that actually matter and the gap is driving the surprise expensive claims every year
+Superpower looks at 100+ biomarkers and screens for 1,000+ conditions from one draw.
+
+teams like Lyft and Notion are already exploring this at $199 a person.
 
-teams like Lyft and Notion are already exploring this. one test, 1,000+ conditions, $199 a person
+if preventive health is nowhere near your lane, ignore me.
 
-can I send over some more info?
+should i send over the short version?
 
 **Example 3 (Variant 1 — employee wellness programs):**
 Subject: princess/prab intro
 
-hey princess, saw you were active around employee wellness programs content recently and figured this might actually be relevant
+hey princess,
+
+saw you in a few conversations around employee wellness programs, so hope this is relevant.
 
-any chance you're exploring preventive health programs at Marriott?
+if preventive health is anywhere near the benefits plan at Marriott, Superpower may be worth a look.
 
-we screen for 1,000+ conditions from a single blood draw and surface risks before they ever become claims.
+it screens for 1,000+ conditions from a single blood draw and surfaces risks before they become claims.
 
-basically your team gets to see what's coming instead of just reacting to it
+basically your team gets to see what's coming instead of only reacting to it.
 
-can I send over some more info?
+should i send over the short version?
 
 ## Social Proof
 
@@ -112,7 +124,8 @@ Teams like Lyft and Notion are exploring Superpower's early detection platform.
 - **ICP filtering:** All prospects filtered against ICP criteria before entering send queue
 - **Positioning:** Early detection tool for claims prevention, not a wellness benefit
 - **Tone:** All lowercase, casual, peer-to-peer - building relationship before asking
-- **Two approved variants:** Testing different hooks (exploratory vs. problem-aware)
+- **Two approved variants:** Testing a low-certainty signal bridge vs. proof-led
+  benefits mechanism
 
 ### Rubric Markdown
 
@@ -212,8 +225,8 @@ Teams like Lyft and Notion are already using early detection screening. One bloo
 
 **Subject: Prab/{{first_name}} intro**
 
-Hey {{first_name}}, not sure if you've looked into this but felt it may be relevant to your work.
+Hey {{first_name}},
 
-have you ever looked into early detection or preventive health programs for {{company}}?
+hope this is relevant if preventive health is anywhere near the benefits plan at {{company}}.
 
-we screen for 1,000+ conditions from a single blood draw and surface risks before they ever become claims.
+Superpower screens for 1,000+ conditions from a single blood draw and surfaces risks before they become claims.

package/skills/create-campaign-brief/references/phase75-active-runtime-message-pack.md

@@ -14,7 +14,8 @@ Included as primary gold examples:
 - `Galley`
 - `Clover`
 - `Persona`
-- `Superpower`
+- `Superpower` — domain-language reference only; use the cleaned low-certainty
+  opener, not retired engagement-source phrasing
 
 Not included in runtime inspiration:
 
@@ -33,6 +34,9 @@ Not included in runtime inspiration:
 
 - Feed only endorsed examples into generation.
 - Keep bad lines only if they are explicitly labeled `BAD` and paired with a `BETTER` version.
+- Treat sellable.dev, Hey Digital, Persona, Galley, and Clover as the primary
+  line-level quality anchors. Superpower is useful for benefits/healthcare
+  mechanism language, but it must not outrank those examples on opener style.
 - Default to one approved message in the generated brief unless the ICP is genuinely broad.
 - A/B CTA is optional. Use it only when the second option is truly strong.
 - If there is a great low-friction proof asset or case study, that is often the best Option B.
@@ -213,22 +217,21 @@ Why included:
 
 - simple language in a hard domain
 - useful plain-language healthcare constraint example
-- why it works: it asks about the buyer's existing benefits priority, explains
-  the mechanism in plain language, and keeps the ask tiny instead of forcing a
-  call
+- why it works: it uses a low-certainty signal bridge, explains the mechanism
+  in plain language, and keeps the ask tiny instead of forcing a call
 
 ```md
 Hey {{first_name}},
 
-not sure if you've looked into this but felt it may be relevant to your work.
+saw you in a few conversations around {{topic}}, so hope this is relevant.
 
-have you ever looked into early detection or preventive health programs for {{company}}?
+if preventive health is anywhere near the benefits plan at {{company}}, Superpower may be worth a look.
 
-we screen for 1,000+ conditions from a single blood draw and surface risks before they ever become claims.
+it screens for 1,000+ conditions from a single blood draw and surfaces risks before they become claims.
 
-basically your team gets to see what's coming instead of just reacting to it
+basically your team gets to see what's coming instead of only reacting to it.
 
-can I send over some more info?
+should i send over the short version?
 ```
 
 Locked production variant from the same Superpower campaign:

package/skills/create-campaign-v2/references/ai-tells.md

@@ -47,12 +47,13 @@ recite profile facts. `"I noticed your..."` reads as scraped intel.
 **Allowed alternative:** Use a concise permissioned bridge:
 `"Hope this is relevant if X is still live."`, `"Saw you might be
 interested in X, so hope this is relevant."`, `"Saw you in a few
-conversations around X, so hope this is relevant."` for LinkedIn-post-sourced
-campaigns, or the self-aware
-`"saw you raise your hand for X, so figured this was (hopefully) worth
-sending"` or `"saw you raise your hand for X (creepy to reach out based
-on that, i know) - but this felt too on the nose to ignore"` shapes when the
-engagement source is the reason for the note.
+conversations around X, so hope this is relevant."`, or `"Found you in a
+thread about X, so may be off, but this seemed relevant."` for
+LinkedIn-post-sourced campaigns. Use the self-aware `"saw you raise your
+hand for X, so figured this was (hopefully) worth sending"` or `"saw you
+raise your hand for X (creepy to reach out based on that, i know) - but
+this felt too on the nose to ignore"` shapes only when the source was an
+explicit lead-magnet comment, reply, or opt-in.
 
 **Severity:** REJECT
 
@@ -280,10 +281,12 @@ reach-out.
 **Allowed alternative:** Use a concise topic-level bridge when the
 source is meaningful, then continue with apologetic uncertainty:
 `"Saw you in a few conversations about LinkedIn outreach, so may be
-off, but this seemed relevant."` or `"Saw you in a few conversations
-around LinkedIn outreach, so hope this is relevant."` If the source was
-only casual reading or the role/topic connection is weak, omit the
-personalization line and open from the buyer pain.
+off, but this seemed relevant."`, `"Saw you in a few conversations
+around LinkedIn outreach, so hope this is relevant."`, or `"Found you in
+a thread about LinkedIn outreach, so may be off, but this seemed
+relevant."` If the source was only casual reading or the role/topic
+connection is weak, omit the personalization line and open from the
+buyer pain.
 
 **Severity:** REJECT
 
@@ -305,6 +308,28 @@ does not narrate the source.
 
 **Severity:** REJECT
 
+## Tell #17 — Flattened "worth sending" source bridge
+
+**Pattern:** `"saw you raise your hand for [topic], so figured this was
+worth sending"` / `"figured this was worth sending"` without the
+parenthetical uncertainty `(hopefully)` or a `hope this is relevant`
+bridge.
+
+**Why it's an AI tell:** It sounds like a model trying to justify the
+outreach after reading a signal. The flat version makes the sender sound
+over-certain and self-focused: "I decided this was worth sending." Real
+operators usually soften the bridge or make it explicitly tentative.
+
+**Allowed alternative:** Use a permissioned, lower-certainty bridge:
+`"saw you raise your hand for [topic], so figured this was (hopefully)
+worth sending."` only for explicit lead-magnet comments, replies, or
+opt-ins. Otherwise use `"saw you might be interested in [topic], so hope
+this is relevant."`, `"saw you in a few conversations around [topic], so
+hope this is relevant."`, or `"found you in a thread about [topic], so
+may be off, but this seemed relevant."`
+
+**Severity:** REJECT
+
 ---
 
 ## How to add new tells

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

@@ -413,7 +413,7 @@ queue, attach sequence, or start. If a draft shell exists, leave it paused/
 non-sendable for operator cleanup instead of silently deleting a workspace row.
 
 Draft effect: move the draft directory to
-`.sellable/create-campaign-v2/drafts/{workspace-slug}/.aborted/{campaign-slug}-{timestamp}/`.
+`~/.sellable/create-campaign-v2/drafts/{workspace-slug}/.aborted/{campaign-slug}-{timestamp}/`.
 Legacy no-shell runs touch no DB rows and create no `CampaignOffer`.
 No DB rows touched in legacy no-shell aborts; draft-shell aborts leave the
 non-sendable shell for operator cleanup.

package/skills/create-campaign-v2/references/gold-standard-message-examples.md

@@ -22,6 +22,13 @@ Do not put active validation fixtures in this file as exact company-specific
 examples. The library should teach transferable winning motions, not leak the
 fixture answer into Phase 84.
 
+For line-level runtime inspiration, prefer
+`mcp/sellable/skills/create-campaign-v2/references/gold-standard-runtime-message-pack.md`.
+That file contains the real sellable.dev, Hey Digital, Persona, Galley, and
+Clover examples. Use this file for strategy skeletons and guardrails. If an old
+archive line conflicts with the runtime pack, the runtime pack wins; do not let
+synthetic or retired opener phrasing outrank the real examples.
+
 ## Example 1: Revvix / Spektion Event-Led Security
 
 Use when the brief has:
@@ -227,21 +234,23 @@ Use when the brief has:
 - signal-led topic engagement
 - benefits / rewards / wellness buyers
 - proof-heavy preventive-health positioning
+- a weak engagement signal that should be framed as a low-certainty relevance
+  bridge, not buyer intent
 
 Template shape:
 
 ```text
 hey {{first name}},
 
-saw you were active around some {{topic}} stuff recently and figured this might actually be relevant
+saw you in a few conversations around {{topic}}, so hope this is relevant.
 
-any chance you're exploring early detection or preventive health programs at {{company}}?
+if preventive health is anywhere near the benefits plan at {{company}}, Superpower may be worth a look.
 
-we screen for 1,000+ conditions from a single blood draw and surface risks before they ever become claims.
+it screens for 1,000+ conditions from a single blood draw and surfaces risks before they become claims.
 
-basically your team gets to see what's coming instead of just reacting to it
+basically your team gets to see what's coming instead of only reacting to it.
 
-can I send over some more info?
+should i send over the short version?
 ```
 
 Alternative proof-led variant:
@@ -249,24 +258,25 @@ Alternative proof-led variant:
 ```text
 hey {{first name}},
 
-saw you were active in some {{topic}} conversations recently and wanted to run something by you
+saw you in a few conversations around {{topic}}, so hope this is relevant.
 
 most annual physicals test 15 biomarkers max.
 
-there's over 100 that actually matter and the gap between those two numbers is where the expensive claims tend to sit
+Superpower looks at 100+ biomarkers and screens for 1,000+ conditions from one draw.
 
-teams like Lyft and Notion are already exploring this. one draw, 1,000+ conditions, $199 a person.
+teams like Lyft and Notion are already exploring this at $199 a person.
 
-if your claims costs have been going up and you're not sure where it's coming from... that gap may be a good place to start looking
+if preventive health is nowhere near your lane, ignore me.
 
-can I send over some more info?
+should i send over the short version?
 ```
 
 Why it works:
 
-- signal comes first
+- the topic signal is low-certainty and does not imply intent
+- `hope this is relevant` is safer than `figured this might actually be relevant`
 - all lowercase matters
-- the CTA stays tiny
+- the CTA stays tiny but specific enough to picture
 - this should not get polished into generic benefits copy
 - the proof sentence does real work; it is not optional filler
 
@@ -286,9 +296,7 @@ Template shape:
 ```text
 hey {{first_name}},
 
-reaching out because it looked like you were active around some {{signal_topic}} recently.
-
-figured this might actually be relevant.
+saw you in a few conversations around {{signal_topic}}, so hopefully relevant.
 
 [product] does [simple one-line mechanism].
 
@@ -304,7 +312,7 @@ p.s. [short proof line]
 Why it works:
 
 - the signal is first and easy to understand
-- the "figured this might actually be relevant" line feels honest without
+- the "hopefully relevant" line feels honest without
   over-explaining
 - the product is framed simply
 - "two options" makes the CTA easy to scan
@@ -339,12 +347,18 @@ Use these patterns to avoid generic asks like:
 - worth a conversation?
 - open to a call?
 - worth a look?
+- open to compare notes?
 
 Prefer a binary or useful CTA when the brief supports it.
 
 CTA decision rule:
 
 - generate single-ask and A/B options before deciding
+- preserve a brief-approved CTA intent when it can be made concrete, but avoid
+  the phrase `compare notes` in buyer-facing copy. If the brief uses that
+  shorthand, translate it into a concrete quick-call or working-session CTA,
+  e.g. `Open to a quick call on how your team might turn LinkedIn content into
+  pipeline?`
 - use A/B only when both choices are genuinely useful and supported
 - for unfamiliar categories, the CTA should name the buyer-specific preview in
   one short phrase, not list every screen or workflow

package/skills/create-campaign-v2/references/gold-standard-message-patterns.md

@@ -164,7 +164,7 @@ Shape:
 Prefer:
 
 - lowercase or casual casing when the motion supports it
-- an honest line like "figured this might actually be relevant"
+- an honest line like "hope this is relevant" or "so hopefully relevant"
 - two clean options instead of a long CTA paragraph
 - direct wording over polished marketing language