@sellable/mcp 0.1.136 → 0.1.138

package/skills/create-post/SKILL.md

@@ -52,12 +52,18 @@ Core principle: Find what's ALREADY working on LinkedIn → deeply autopsy the H
 
 3. Load memory (single call):
 
-   - Call `get_engage_memory()` to read style guide, proven searches, tracked people from `.sellable/configs/`.
-   - The style guide (`memory.styleGuide.markdown`) is the sender's voice profile. This is MANDATORY for post generation.
-   - If `memory.styleGuide` is missing, inform user they need to run the `interview` skill first.
-
-4. Read the sender's voice-specific configs (built-in Read tool):
-
+   - Call `get_engage_memory()` to read composed core identity/company memory, proven searches, tracked people, and legacy compatibility memory from `.sellable/configs/`.
+   - Treat `memory.styleGuide.markdown` as composed engage memory: core identity/company memory first, legacy files as fallback.
+   - If both core memory and compatibility voice memory are missing, inform the user they need to run the new core `interview` flow first.
+
+4. Read core and sender voice-specific configs (built-in Read tool):
+
+   - `.sellable/configs/core/about-me.md` and `.sellable/configs/core/context-modes.md` (identity + context modes for post stance)
+   - `.sellable/configs/core/story-bank.md` and `.sellable/configs/core/answer-bank.md` (real stories and reusable answers)
+   - `.sellable/configs/core/proof-ledger.md` and `.sellable/configs/core/wins-ledger.md` (safe proof and social proof)
+   - `.sellable/configs/core/anti-ai-writing-style.md` (anti-AI audit)
+   - `.sellable/configs/core/references/linkedin-posts/INDEX.md` and copied files under `core/references/linkedin-posts/`
+   - `.sellable/configs/core/references/inspiration/INDEX.md` (structural inspiration and anti-pattern references)
    - `.sellable/configs/writing/christian-reyes-linkedin-viral.md` (post-specific voice analysis)
    - `.sellable/configs/content/linkedin-posts-drafts.md` (existing drafts + hook bank)
    - `.sellable/configs/discovery/post-filters.md` (exclusion rules)
@@ -91,6 +97,8 @@ Core principle: Find what's ALREADY working on LinkedIn → deeply autopsy the H
 
 This block MUST be loaded into context before generating any hooks or drafts. It is the immutable voice specification.
 
+Core memory is primary. The static rules below are a compatibility anchor for Christian-specific posts, but the live inputs are `core/about-me.md`, `core/context-modes.md`, `core/story-bank.md`, `core/answer-bank.md`, `core/proof-ledger.md`, `core/wins-ledger.md`, `core/anti-ai-writing-style.md`, and `core/references/linkedin-posts/**`.
+
 ```
 SENDER POST VOICE RULES — EVERY SENTENCE MUST COMPLY:
 
@@ -816,12 +824,13 @@ Run on EVERY draft:
 5. **CTA check**: Any CTA in last 3 lines? Delete.
 6. **Emoji check**: Any emojis except final parenthetical? Delete.
 7. **Hype check**: "amazing", "incredible", "game-changing"? Replace.
-8. **AI filler check**: Banned phrases from voice config? Delete.
+8. **AI filler check**: Banned phrases from `core/anti-ai-writing-style.md` or voice config? Delete.
 9. **Rhythm check**: Read aloud. Breathless and urgent? If not, cut words.
 10. **Ending check**: Insight/mic drop/parenthetical? Not question or CTA?
 11. **Character count**: 1,200-2,500 chars? Adjust.
 12. **Line 3 check**: Is line 3 blank? Move content up.
 13. **Mobile check**: No section > 4 lines without break? Mini-hooks every 300 chars?
+14. **Anti-AI/proof final gate**: Run the anti-AI audit and proof ledger check. Any story, metric, win, customer/social proof, or answer must be sourced from the interview transcript, `story-bank.md`, `answer-bank.md`, `proof-ledger.md`, `wins-ledger.md`, or approved references.
 
 ## Phase 6: Rank
 
@@ -942,6 +951,23 @@ Ask: "Which posts do you want to publish? Any edits?"
 4. Repeat until sender approves.
 5. On final approval, offer to save to `.sellable/configs/content/linkedin-posts-drafts.md`.
 
+### Memory Candidate Review
+
+During polish, turn durable feedback into explicit memory candidates instead of silently rewriting files. For each reusable answer, win/social proof, story, topical take, banned phrase, unused interview snippet, or post example, ask the sender to **approve, edit, reject, or mark private** before saving. Do not upsert every answer automatically.
+
+Route approved candidates to the smallest relevant core target:
+
+- `core/answer-bank.md` for reusable answers, contrarian explanations, topic takes, and approved framing language.
+- `core/wins-ledger.md` for wins/social proof, metrics, proof receipts, public/private safety, and permission notes.
+- `core/story-bank.md` for reusable stories, founder moments, missed-fortune examples, and concrete post material.
+- `core/anti-ai-writing-style.md` for banned wording, fake-depth phrasing, dead openings, and post-specific anti-patterns.
+- `core/decision-rules.md` for durable post selection, topic safety, and correction rules.
+- `core/change-log.md` for every approved correction, rejected memory proposal worth remembering, private mark, and post-session operator note.
+- `core/transcripts/INDEX.md` plus the relevant `core/transcripts/topics/*.md` file for topic-specific interview snippets and unused material that should stay transcript-first.
+- `core/references/linkedin-posts/INDEX.md` plus a copied reference file under `core/references/linkedin-posts/` for approved post examples or high-signal source posts.
+
+Keep write-backs idempotent: use stable source keys such as `create-post:{date}:{sessionSlug}:{candidateSlug}`, check copied paths before adding reference rows, create no duplicate reference rows, and keep manual sections preserved. If the sender marks a candidate private, keep it out of public examples and proof surfaces unless they later approve a public-safe rewrite.
+
 ## Phase 10: Save Session Insights (Memory Persistence)
 
 **Everything we learned this session should help the NEXT session be better.** This is not optional — run after every session, even if the user doesn't explicitly ask.
@@ -1030,6 +1056,8 @@ If the interview surfaced stories or angles that weren't used in this session's
 - [Specific number or story not yet used] — save for [topic]
 ```
 
+After the legacy draft queue is updated, propose the same unused material for `core/story-bank.md`, `core/answer-bank.md`, `core/change-log.md`, and `core/transcripts/INDEX.md` when it has durable value. Transcript-first snippets go into `core/transcripts/topics/*.md`; derived memories are optional and require the sender's approve/edit/reject/mark-private decision.
+
 ### 10E: Update Tracked Influencers
 
 If any viral post authors from this session are worth tracking for future discovery, call `upsert_engage_tracked_person({ name, linkedinUrl, reason })`.
@@ -1068,6 +1096,21 @@ If any viral post authors from this session are worth tracking for future discov
 - e.g., "Bold reframe hooks scored 9+ — counter-intuitive numbers in line 1 force scroll-stop"
 - e.g., "Piggybacking on trending discourse ('personalized slop') worked for post creation — could work for comment angles too"
 
+### 10G: Update Core Memory
+
+Apply only sender-approved memory candidates from the review loop:
+
+- Add approved reusable answers and topical takes to `core/answer-bank.md`.
+- Add approved wins, metrics, social proof, and permission notes to `core/wins-ledger.md`.
+- Add reusable stories and concrete lived examples to `core/story-bank.md`.
+- Add rejected phrasing, banned openings, and AI-tell corrections to `core/anti-ai-writing-style.md`.
+- Add durable post-selection and safety rules to `core/decision-rules.md`.
+- Append every approved/edit/reject/mark-private decision to `core/change-log.md`.
+- Add topic-specific snippets and unused interview material to `core/transcripts/INDEX.md` and the relevant topic file under `core/transcripts/topics/`.
+- Add approved post examples to `core/references/linkedin-posts/INDEX.md`; create or update a copied file under `core/references/linkedin-posts/` when the example should be reusable.
+
+Idempotency rules: stable source keys, copied path checks, no duplicate reference rows, and manual sections preserved.
+
 ### Quality Gate: Memory Saved
 
 - [ ] Proven searches updated for all keywords used
@@ -1079,6 +1122,8 @@ If any viral post authors from this session are worth tracking for future discov
 - [ ] New influencers tracked if discovered
 - [ ] `insights/post-sessions.md` updated with session summary
 - [ ] `insights/cross-skill.md` updated if any cross-skill learnings found
+- [ ] Approved memory candidates written to the smallest relevant core targets
+- [ ] Stable source keys used, no duplicate reference rows added, manual sections preserved
 
 </process>
 
@@ -1289,10 +1334,10 @@ The guy catching them: $6M ARR. 1 employee. $0 raised.
 
 ## Critical Rules
 
-1. **Never fabricate** stories, numbers, experience, or social proof. Every post must be grounded in the interview transcript or real sender data.
+1. **Never fabricate** stories, numbers, experience, or social proof. Every post must be grounded in the interview transcript, core identity memory, `story-bank.md`, `answer-bank.md`, `proof-ledger.md`, `wins-ledger.md`, `core/references/linkedin-posts/**`, or real sender data.
 2. **Don't proceed without gold** — the interview must surface a sharp contrarian take, real story, and specific numbers before ANY generation happens. Keep digging until the quality gate passes.
 3. **Insights summary before generation** — always present what was mined and let the sender choose angles before generating hooks. No silent assumptions.
-4. **Voice anchor at every stage** — reload the full voice specification before any generation step.
+4. **Voice anchor at every stage** — reload core memory and the full voice specification before any generation step.
 5. **Mobile-first always** — optimize for phone screens, not desktop.
 6. **No CTA, no emojis, no hype** — these are the strongest anti-patterns for this sender's audience.
 7. **Specificity is non-negotiable** — every post must have 3+ specific numbers.

package/skills/engage/SKILL.md

@@ -24,7 +24,7 @@ Orchestrate a complete engagement session that covers **one or more senders** in
 3. **SMART DISCOVERY** — two parallel agents (fresh-scanner + deep-scanner) using globalEngagedPostUrls for exclusion
 4. **STRATEGIC SHORTLIST + SENDER ASSIGNMENT** — merge, score, round-robin assign posts to senders (each post URL → exactly one sender)
 5. **INTERVIEW** — mine contrarian takes (interactive only, skipped in autonomous)
-6. **Draft per-sender comments** — each sender's batch uses that sender's voice profile
+6. **Draft per-sender comments** — each sender's batch uses composed core identity/company memory plus that sender's compatibility voice overrides
 7. **Load into per-sender campaigns** (paused) — one `add_to_comment_campaign` call per sender
 8. **SAVE SESSION INSIGHTS** — per-sender memory (proven searches, tracked people, style guide) + shared session log
 
@@ -59,8 +59,8 @@ Then proceed directly to Pre-Phase (Mode Detection). All auth, memory, and confi
 - `mcp__sellable__get_auth_status` - Verify token + workspace context
 - `mcp__sellable__bootstrap_engage` - Single-sender resolve + ensure comment campaign table + fetch engaged post URLs; persists defaults
 - `mcp__sellable__bootstrap_engage_multi` - Multi-sender resolve: parallel per-sender table creation + engaged post fetch + globalEngagedPostUrls union
-- `mcp__sellable__get_engage_memory` - Read memory from `.sellable/configs/` (style guide, proven searches, tracked people). Accepts optional `senderId` for per-sender configs.
-- `mcp__sellable__set_engage_style_guide` - Write style guide. Accepts optional `senderId` for per-sender configs.
+- `mcp__sellable__get_engage_memory` - Read backward-compatible engage memory plus optional core identity/company memory from `.sellable/configs/core/`. The `memory.styleGuide.markdown` blob is composed engage memory: core identity/company files first, then legacy comment/sender overrides. Accepts optional `senderId`.
+- `mcp__sellable__set_engage_style_guide` - Write a legacy compatibility style override. Accepts optional `senderId`; it does not replace core identity memory.
 - `mcp__sellable__record_engage_proven_search` - Update keyword stats. Accepts optional `senderId` for per-sender configs.
 - `mcp__sellable__upsert_engage_tracked_person` - Add/update tracked person. Accepts optional `senderId` for per-sender configs.
 - `mcp__sellable__copy_sender_config` - Copy all per-sender config files from one sender to another
@@ -141,7 +141,7 @@ _Interactive mode:_
 Sender "[name]" has no engage config yet.
 
 Options:
-1. Create fresh — I'll interview [name] to build their voice profile
+1. Create fresh — I'll run the new core `interview` flow to build identity/company memory, then use engage compatibility memory for this sender
 2. Copy from [first sender with config] — Start with their config, customize later
 3. Skip [name] this session — Only run engage for senders with configs
 ```
@@ -168,15 +168,18 @@ For EACH sender, call `fetch_linkedin_posts({ linkedinUrl: sender.senderLinkedin
 
 For EACH sender, call `get_engage_memory({ senderId })`:
 
-- This reads from `senders/{senderId}/styleguide-core.md`, `senders/{senderId}/proven-searches.md`, `senders/{senderId}/influencers.md`
-- Falls back to flat configs if sender dir doesn't exist
+- Treat `memory.styleGuide.markdown` as composed engage memory, not a flat-only style file.
+- Primary memory comes from `.sellable/configs/core/about-me.md`, `my-company.md`, `anti-ai-writing-style.md`, `proof-ledger.md`, `wins-ledger.md`, `story-bank.md`, `answer-bank.md`, `context-modes.md`, and `decision-rules.md` when present.
+- Legacy sender files under `senders/{senderId}/` and flat `writing/*`, `audience/*`, and `faqs/*` are compatibility fallbacks and overrides.
+- If core identity/company memory and legacy voice memory are both missing, tell the user to run the new core `interview` flow before drafting.
 
 ### Step 0.5: Read shared writing configs [REQUIRED]
 
 Read (built-in Read tool):
 
 - `./.sellable/configs/writing/comments.md` (comment-specific rules, quality gate, approved examples)
-- Per-sender `styleguide-core.md` is already loaded via `get_engage_memory` above
+- The composed engage memory is already loaded via `get_engage_memory` above. Treat the legacy writing style guide as fallback/source material, not as the primary voice source.
+- If present and useful for final gates, skim `./.sellable/configs/core/anti-ai-writing-style.md` and `./.sellable/configs/core/proof-ledger.md`.
 
 ### Step 0.6: Read cross-skill context [OPTIONAL]
 
@@ -191,7 +194,7 @@ Read (lightweight — local files only, no API calls):
 
 Build keywords from ALL senders' combined expertise:
 
-- Extract expertise topics from each sender's style guide (Core Thesis, Key Beliefs)
+- Extract expertise topics from composed engage memory: core identity/company memory first, then sender/legacy compatibility sections
 - Cross-reference with proven searches from all senders — sort by hit rate, take top 5
 - Check cross-skill insights for trending topics
 - Add 3-5 exploratory keywords NOT already in proven searches
@@ -322,7 +325,7 @@ Two agents run in parallel, each optimized for a different time horizon. **Both
 
 **Interactive mode:** This phase always runs unless the user explicitly says "skip."
 
-### Mode: Light Interview (style guide exists for at least one sender)
+### Mode: Light Interview (core or compatibility memory exists for at least one sender)
 
 Pick the 2-3 most interesting posts from the approved shortlist. Use `AskUserQuestion` for 2 rounds:
 
@@ -340,13 +343,29 @@ Push for specifics once. If still vague, accept and move on.
 
 - Extract contrarian takes
 - Map each take to specific posts AND the assigned sender
-- Update relevant sender's style guide via `set_engage_style_guide({ markdown, senderId })`
+- Save sender-specific compatibility notes through `set_engage_style_guide({ markdown, senderId })` when the note is only about comment voice or this sender's override.
 - Reflect back extracted takes for confirmation
 
-### Mode: Full Interview (no style guide for any sender — required, cannot skip)
+### Core Write-Back From Light Interviews and Corrections
 
-3-4 rounds via `AskUserQuestion` (same as before — voice capture, heuristics, etc.).
-Persist style guide for the primary sender, copy to others if appropriate.
+When an interview answer, comment correction, or approved draft reveals durable memory, propose a small write-back before saving it. The user must choose **approve, edit, reject, or mark private** for each candidate answer or correction. Do not upsert every answer automatically.
+
+Use the smallest relevant core target:
+
+- `core/answer-bank.md` for strong reusable answers, objection responses, positioning explanations, and "how I think about X" language.
+- `core/wins-ledger.md` for wins/social-proof receipts, metrics, named customer/logo permission notes, and dated proof.
+- `core/story-bank.md` for reusable stories, founder anecdotes, post/comment hooks, and specific lived examples.
+- `core/anti-ai-writing-style.md` for banned wording, fake-depth patterns, or context-specific phrasing that made a draft sound AI-written.
+- `core/decision-rules.md` for durable strategy rules, public/private safety rules, and correction heuristics.
+- `core/change-log.md` for every approved correction, rejected proposal worth remembering, private mark, and downstream prompt/operator note.
+- `core/transcripts/INDEX.md` plus a topic file under `core/transcripts/topics/` for topic-specific interview snippets or unused material that should stay transcript-first.
+- `core/references/linkedin-posts/INDEX.md` or another `core/references/**/INDEX.md` when an approved comment/post example should become a reference artifact.
+
+Write-backs must be idempotent: use stable source keys such as `engage-session:{date}:{senderId}:{postUrlHash}:{slug}`, check copied paths before adding references, create no duplicate reference rows, and keep manual sections preserved. If the user marks a candidate private, store only the minimum private-safe metadata and do not promote it into public proof, references, or examples.
+
+### Mode: Full Interview (no core or compatibility memory for any sender — required, cannot skip)
+
+Run the new core `interview` flow. Its output should populate `.sellable/configs/core/**` first, then engage can keep legacy compatibility overrides where needed.
 
 ## Phase 4: Draft Comments Per Sender [REQUIRED]
 
@@ -354,7 +373,7 @@ Group posts by assigned sender. Process each sender's batch separately.
 
 ### For Each Sender's Batch:
 
-1. **Load sender's voice profile** — their specific voice samples from Phase 0.3 + their per-sender style guide.
+1. **Load sender's voice profile** — their specific voice samples from Phase 0.3 + composed engage memory from `get_engage_memory`.
 
 2. **For each post** (internally, before showing):
 
@@ -363,6 +382,7 @@ Group posts by assigned sender. Process each sender's batch separately.
    - Draft using shared formatting rules from `comments.md` + sender-specific voice
    - Self-edit once
    - Quality gate (clarity, relevance, insight, coherence, cringe, substance)
+   - Anti-AI/proof final gate: check `anti-ai-writing-style.md` and `proof-ledger.md`; remove AI filler, fake depth, unsupported metrics, and proof claims that are unsafe for a public comment.
 
 3. **Present batch:**
 
@@ -412,7 +432,7 @@ If any post authors from the shortlist are worth tracking, call `upsert_engage_t
 
 ### 6C: Save Session Insights to Style Guide (per sender)
 
-For each sender that had comments drafted, update their style guide via `set_engage_style_guide({ markdown, senderId })`:
+For each sender that had comments drafted, update their compatibility style guide via `set_engage_style_guide({ markdown, senderId })`:
 
 ```markdown
 ## Engage Session — [date]
@@ -435,6 +455,8 @@ For each sender that had comments drafted, update their style guide via `set_eng
 - Deep (1-7d): [keywords]
 ```
 
+Also route durable insights through the core write-back contract above. Compatibility style guides can store engage-specific voice overrides, but reusable answers, wins, stories, correction history, transcript snippets, and reference examples belong in `core/answer-bank.md`, `core/wins-ledger.md`, `core/story-bank.md`, `core/change-log.md`, `core/transcripts/INDEX.md`, and the relevant `core/references/**/INDEX.md`.
+
 ### 6D: Save Unused Post Angles (Top 9-10 Only)
 
 Only keep the strongest unused angles for next session.

package/skills/engage/core/README.md

@@ -2,22 +2,28 @@
 
 ## Where Data Lives
 
-All engage memory lives in `.sellable/configs/` at the project root — the single source of truth for both user customization and MCP tool memory.
+Engage memory lives in `.sellable/configs/` at the project root. The primary identity/company layer is now `.sellable/configs/core/`; legacy writing, discovery, audience, FAQ, and sender files remain compatibility layers and fallbacks.
 
-| Data            | Config File                                      | MCP Tool                                             |
-| --------------- | ------------------------------------------------ | ---------------------------------------------------- |
-| Style guide     | `.sellable/configs/writing/styleguide-core.md`   | `get_engage_memory` / `set_engage_style_guide`       |
-| Comment rules   | `.sellable/configs/writing/comments.md`          | (read via `get_engage_memory`)                       |
-| Proven searches | `.sellable/configs/discovery/proven-searches.md` | `get_engage_memory` / `record_engage_proven_search`  |
-| Tracked people  | `.sellable/configs/discovery/influencers.md`     | `get_engage_memory` / `upsert_engage_tracked_person` |
-| Post filters    | `.sellable/configs/discovery/post-filters.md`    | (read by skill via Read tool)                        |
-| ICP             | `.sellable/configs/audience/icp.md`              | (read by skill via Read tool)                        |
+| Data            | Config File                                                                       | MCP Tool                                             |
+| --------------- | --------------------------------------------------------------------------------- | ---------------------------------------------------- |
+| Core identity   | `.sellable/configs/core/about-me.md`                                              | `get_engage_memory`                                  |
+| Company truth   | `.sellable/configs/core/my-company.md`                                            | `get_engage_memory`                                  |
+| Anti-AI rules   | `.sellable/configs/core/anti-ai-writing-style.md`                                 | `get_engage_memory`                                  |
+| Proof/wins      | `.sellable/configs/core/proof-ledger.md`, `.sellable/configs/core/wins-ledger.md` | `get_engage_memory`                                  |
+| Stories/answers | `.sellable/configs/core/story-bank.md`, `.sellable/configs/core/answer-bank.md`   | `get_engage_memory`                                  |
+| Context modes   | `.sellable/configs/core/context-modes.md`                                         | `get_engage_memory`                                  |
+| Style override  | `.sellable/configs/writing/styleguide-core.md` or sender override                 | `get_engage_memory` / `set_engage_style_guide`       |
+| Comment rules   | `.sellable/configs/writing/comments.md`                                           | (read via `get_engage_memory`)                       |
+| Proven searches | `.sellable/configs/discovery/proven-searches.md`                                  | `get_engage_memory` / `record_engage_proven_search`  |
+| Tracked people  | `.sellable/configs/discovery/influencers.md`                                      | `get_engage_memory` / `upsert_engage_tracked_person` |
+| Post filters    | `.sellable/configs/discovery/post-filters.md`                                     | (read by skill via Read tool)                        |
+| ICP             | `.sellable/configs/audience/icp.md`                                               | (read by skill via Read tool)                        |
 
 ## How Skills Update Configs
 
-- **Interview skill**: Populates style guide, comments, ICP, and tracked people from a voice-first conversation
-- **Engage skill**: Updates proven searches after each session, adds new tracked people when discovered
+- **Interview skill**: Populates primary `configs/core/**` identity/company memory, transcript references, answer bank, proof/wins ledgers, and anti-AI rules.
+- **Engage skill**: Reads composed core memory through `get_engage_memory`, updates proven searches after each session, adds new tracked people when discovered, and writes legacy sender style overrides only when the correction is engage-specific.
 
 ## Migration from JSON
 
-The old `proven-searches.json`, `tracked-people.json`, and `style-guide.template.md` files have been replaced. All data now lives as readable markdown in `.sellable/configs/`.
+The old `proven-searches.json`, `tracked-people.json`, and `style-guide.template.md` files have been replaced. All data now lives as readable markdown in `.sellable/configs/`. Legacy `writing/*`, `audience/*`, `faqs/*`, and `content/*` files are preserved as fallback/source material while downstream prompts move to core memory.

package/skills/generate-messages/SKILL.md

@@ -135,6 +135,13 @@ Dry mode validates message quality before campaign mint.
 
 Read:
 
+- `.sellable/configs/core/about-me.md`
+- `.sellable/configs/core/my-company.md`
+- `.sellable/configs/core/context-modes.md`
+- `.sellable/configs/core/proof-ledger.md`
+- `.sellable/configs/core/wins-ledger.md`
+- `.sellable/configs/core/anti-ai-writing-style.md`
+- `.sellable/configs/writing/outbound.md` and legacy `styleguide-core.md` as fallback/source material when present
 - `brief.md`
 - `lead-sample.json` from the find-leads step; this is the only allowed sample
   source for dry-mode message generation
@@ -831,8 +838,7 @@ The panel has three roles:
 
 Before drafting, answer these five questions explicitly:
 
-1. **Who is sending it?** Identify the sender voice and what the body must
-   make clear without a body-level self-introduction.
+1. **Who is sending it?** Identify the sender voice from core identity memory, context modes, and explicit campaign inputs. Legacy `styleguide-core.md` is fallback/source material, not the primary voice source. State what the body must make clear without a body-level self-introduction.
    - If explicit sender data exists in the brief or input artifacts, use it
      as context for voice, proof, and buyer relevance.
    - If the explicit sender is the founder/operator, use `I` / `we` when
@@ -859,6 +865,7 @@ Then choose the exact element pool that angle drafts are allowed to use:
 - 3-5 mechanism sentence options
 - 3-5 proof uses, each classified as `body-worthy`, `translated`,
   `CTA-asset`, `PS-worthy`, or `internal-only`
+  Prefer source-aware entries from `proof-ledger.md`, `wins-ledger.md`, or the campaign brief. Do not invent proof or upgrade dated proof.
 - 3-5 CTA options, including a single ask and A/B only if both choices
   are genuinely useful
 - 0-3 PS options, including `no PS` as a normal winning option
@@ -2470,11 +2477,12 @@ research → condense → 10 angle agents in parallel → finalizer combines bes
 
 ## Sender
 - Name: {name} | Company: {company} | Title: {title}
-- Core thesis: {1 line from styleguide-core.md}
+- Core thesis: {1 line from core identity/company memory or composed core memory}
 - Signature phrases: {3-5 key phrases}
 - Background: {1-2 lines}
 
 ## Voice + Outbound Rules (condensed — full files available via Read tool)
+- Use `.sellable/configs/core/context-modes.md` to choose the right context stance, then run an anti-AI audit against `.sellable/configs/core/anti-ai-writing-style.md` before returning copy.
 - Flow skeleton: opener → pain → **what the product IS** → **what it DOES** (one action per line, up to three) → deployment ease → CTA → optional PS
 - A cold reader must be able to state what the product does in one sentence after reading. Require a crisp `Product is an X that does Y` anchor before any action breakdown. Do not gesture at "that chain" / "the stack" / "that work"
 - Blank line between every sentence in the body. The body renders as a sequence of one-line paragraphs separated by blank lines, not as multi-sentence paragraphs. Target 6-10 one-line paragraphs
@@ -2532,14 +2540,16 @@ research → condense → 10 angle agents in parallel → finalizer combines bes
 7. After all 10 return, act as the Finalizer:
    - Combine the best opener, bridge, body, and CTA across all drafts
    - Credibility pass: must say something they haven't heard from 50 other people
-   - Voice-check against sender's signature phrases
+   - Voice-check against the sender's core identity, context mode, and signature phrases
+   - Proof-check every claim against `proof-ledger.md`, `wins-ledger.md`, or the campaign brief
+   - Run an anti-AI audit and cut phrasing that sounds synthesized, over-shaped, or proof-laundered
    - Reject generic fallback openers and abstract noun subjects when the
      specialist fallback can be made more concrete
    - Run full 12-gate check using the fallback REPLY framework as QA only, all must pass
 8. Return: { success: true, message: "...", research: [...], anglesExplored: 10 }
 ```
 
-**IMPORTANT:** Load `.sellable/configs/writing/outbound.md`, `styleguide-core.md`, and `.sellable/insights/cross-skill.md` ONCE in the lead agent, then pass **condensed** versions to any workers. Don't pass full file contents to every worker — that wastes context and causes overflow.
+**IMPORTANT:** Load `.sellable/configs/core/about-me.md`, `.sellable/configs/core/my-company.md`, `.sellable/configs/core/context-modes.md`, `.sellable/configs/core/proof-ledger.md`, `.sellable/configs/core/wins-ledger.md`, `.sellable/configs/core/anti-ai-writing-style.md`, `.sellable/configs/writing/outbound.md`, and `.sellable/insights/cross-skill.md` once in the lead agent. Use the legacy style guide fallback when present. Pass condensed versions to workers so context stays focused.
 
 ## Batch Approval