taketomarket 0.1.0

package/workflows/reference-mgmt/positioning-check.md

@@ -0,0 +1,339 @@
+<purpose>
+Positioning drift audit workflow for /ttm-positioning-check. Samples recent assets
+across all campaigns within a configurable time window (default 30 days per D-01),
+evaluates each against GATE-01 positioning drift checks, generates a structured
+audit report, and appends the results to .marketing/DRIFT-LOG.md.
+
+This workflow can be invoked manually or auto-suggested by the ship workflow
+after every 3rd campaign ships since the last audit (per D-02).
+</purpose>
+
+<required_reading>
+@${CLAUDE_PLUGIN_ROOT}/references/context-loading.md
+@${CLAUDE_PLUGIN_ROOT}/gates/gate-evaluation.md
+@${CLAUDE_PLUGIN_ROOT}/references/positioning-check-report.md
+</required_reading>
+
+<constraints>
+## POSITIONING.md is READ-ONLY
+
+**Do NOT modify `.marketing/POSITIONING.md` during this workflow.**
+
+POSITIONING.md is an architectural invariant. If you detect positioning drift:
+- In verify: use the Escalate option to launch /ttm-positioning-shift
+- In other workflows: flag the issue and recommend running /ttm-positioning-check
+
+Only /ttm-positioning-shift and /ttm-init may modify POSITIONING.md.
+</constraints>
+
+<process>
+
+## Text-Mode Detection
+
+**Text mode (`--text` flag):** Set `TEXT_MODE=true` if `--text` is present in `$ARGUMENTS`
+or if the runtime is not Claude Code. When TEXT_MODE is active, replace every
+`AskUserQuestion` call with a plain-text numbered list.
+
+Detection:
+```bash
+if echo "$ARGUMENTS" | grep -q -- '--text'; then TEXT_MODE=true; fi
+```
+
+If `AskUserQuestion` tool is not available in the current runtime, set `TEXT_MODE=true`.
+
+When TEXT_MODE is active, replace each AskUserQuestion with a plain-text numbered list:
+```
+[HEADER]
+[QUESTION]
+  1. [OPTION_1_LABEL] -- [OPTION_1_DESCRIPTION]
+  2. [OPTION_2_LABEL] -- [OPTION_2_DESCRIPTION]
+  ...
+Type the number of your choice:
+```
+
+---
+
+## Step 1: Load Context
+
+```
+takeToMarket > LOADING CONTEXT FOR POSITIONING AUDIT
+```
+
+**Load Tier 1 summaries** from all 9 reference files (lines 1 to `<!-- END_SUMMARY -->`):
+- `.marketing/POSITIONING.md`
+- `.marketing/BRAND.md`
+- `.marketing/ICP.md`
+- `.marketing/CHANNELS.md`
+- `.marketing/STATE.md` (frontmatter only)
+- `.marketing/CALENDAR.md`
+- `.marketing/COMPETITORS.md`
+- `.marketing/METRICS.md`
+- `.marketing/LEARNINGS.md`
+
+**Load Tier 2 (full content)** for drift evaluation:
+- `.marketing/POSITIONING.md` (needed for all 3 GATE-01 checks)
+
+If `.marketing/POSITIONING.md` does not exist: Error:
+"No POSITIONING.md found. Run /ttm-init first to set up your marketing workspace."
+Exit.
+
+---
+
+## Step 2: Parse Time Window
+
+Parse optional `--since` argument from $ARGUMENTS. Default: `30d` (per D-01).
+
+```bash
+WINDOW=$(echo "$ARGUMENTS" | grep -oP '(?<=--since\s)\S+' || echo "30d")
+```
+
+Extract number and unit:
+- Format: `Nd` where N is a number and d = days
+- Example: `30d` = last 30 days, `90d` = last 90 days, `7d` = last 7 days
+- Calculate cutoff date from current date minus N days
+
+Display:
+```
+takeToMarket > AUDIT WINDOW: last ${WINDOW}
+```
+
+---
+
+## Step 3: Enumerate Campaigns and Assets
+
+```
+takeToMarket > ENUMERATING CAMPAIGNS
+```
+
+Run campaign enumeration via CLI:
+```bash
+CAMPAIGNS_JSON=$(node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" campaign list --since ${WINDOW} --raw)
+```
+
+Parse the JSON result. Expected format: `{ "campaigns": [...], "count": N }`
+
+If count is 0:
+```
+takeToMarket > NO CAMPAIGNS FOUND
+
+No campaigns with assets in the last ${WINDOW}. Nothing to audit.
+```
+Exit.
+
+**Per Pitfall 2:** The CLI already excludes archived campaigns from the results.
+
+For each campaign in the result:
+1. Read the campaign's ASSETS/ directory:
+   ```
+   Glob: .marketing/CAMPAIGNS/${SLUG}/ASSETS/*
+   ```
+2. Collect all asset files found
+3. Also read `.marketing/CAMPAIGNS/${SLUG}/DEVIATIONS.md` if it exists
+   - Filter for rows where Gate = `positioning_drift` (GATE-01 deviations per D-13)
+   - Store these as accepted deviations for the cross-reference section
+
+Display:
+```
+takeToMarket > FOUND ${ASSET_COUNT} assets across ${CAMPAIGN_COUNT} campaigns
+```
+
+---
+
+## Step 4: Evaluate Each Asset Against GATE-01
+
+```
+takeToMarket > EVALUATING POSITIONING DRIFT
+```
+
+For each collected asset:
+
+1. Read the full asset content from disk
+2. Evaluate against GATE-01's 3 checks (from @gate-evaluation.md):
+
+   **Check 1: Differentiator Alignment**
+   Does the asset restate or naturally extend the primary differentiator from
+   POSITIONING.md? Or does it introduce a different claim?
+   - PASS: Asset reinforces the primary differentiator
+   - WARN: Asset is neutral -- neither reinforces nor contradicts
+   - FAIL: Asset introduces a different/competing claim
+
+   **Check 2: Proof Point Sourcing**
+   Are all factual claims in the asset backed by proof points in the POSITIONING.md
+   proof point library?
+   - PASS: All claims backed by POSITIONING.md proof points
+   - WARN: Some claims present but not all sourced
+   - FAIL: Claims contradict or fabricate proof points
+
+   **Check 3: Must-Not-Say Compliance**
+   Does the asset contain any terms from the POSITIONING.md must-not-say list?
+   - PASS: No must-not-say terms found
+   - WARN: Terms appear in non-customer-facing context
+   - FAIL: Must-not-say terms in customer-facing copy
+
+3. Record per-check result: PASS / WARN / FAIL with evidence
+4. Calculate per-asset drift %: (WARN count + FAIL count) / 3 * 100
+
+**IMPORTANT per RESEARCH.md Pitfall 1:** Drift = (WARN + FAIL checks) / total checks.
+Both WARN and FAIL contribute equally to the drift percentage calculation.
+
+Display progress for each asset:
+```
+  [${INDEX}/${TOTAL}] ${ASSET_NAME} (${CAMPAIGN_SLUG}): ${DRIFT_PCT}% drift
+```
+
+---
+
+## Step 5: Calculate Aggregates
+
+After evaluating all assets:
+
+- **Total assets evaluated:** count of all sampled assets
+- **Aggregate drift %:** total (WARN + FAIL results) / (total assets * 3) * 100
+- **Count by drift category:**
+  - Differentiator Alignment: count of WARN + FAIL on Check 1 across all assets
+  - Proof Point Sourcing: count of WARN + FAIL on Check 2 across all assets
+  - Must-Not-Say Violations: count of WARN + FAIL on Check 3 across all assets
+- **Cross-reference accepted deviations** from DEVIATIONS.md files collected in Step 3 (per D-13)
+
+---
+
+## Step 5b: Bleeding Analysis
+
+```
+takeToMarket > ANALYZING MUST-NOT-SAY BLEEDING
+```
+
+From the per-asset evaluation results collected in Step 4, extract all assets where
+Check 3 (Must-Not-Say Compliance) returned WARN or FAIL.
+
+For each must-not-say violation:
+
+1. **Classify the asset as customer-facing or non-customer-facing:**
+   - Customer-facing: landing pages, blog posts, ad copy, social posts, email campaigns,
+     any asset intended for external audience consumption
+   - Non-customer-facing: internal briefs, research docs, planning notes, strategy docs
+   - When ambiguous, classify as customer-facing (conservative default per
+     @positioning-check-report.md Bleeding Analysis rules)
+
+2. **Determine bleeding status:**
+   - Check 3 = FAIL (customer-facing asset): Mark as **BLEEDING** (Critical)
+   - Check 3 = WARN (non-customer-facing asset): Mark as **NOT BLEEDING** (Advisory)
+
+3. **Extract the specific must-not-say term and surrounding context** (10 words before
+   and after the term occurrence) for inclusion in the Bleeding Analysis report section.
+
+Calculate bleeding metrics:
+- **BLEEDING_COUNT:** Number of assets with Check 3 = FAIL (customer-facing violations)
+- **MNS_VIOLATION_COUNT:** Total assets with Check 3 = WARN or FAIL
+- **BLEEDING_RATE:** BLEEDING_COUNT / MNS_VIOLATION_COUNT * 100 (0% if no violations)
+
+Display:
+```
+  Bleeding: ${BLEEDING_COUNT} of ${MNS_VIOLATION_COUNT} must-not-say violations in customer-facing materials
+```
+
+These values feed into the Bleeding Analysis section of the report generated in Step 7.
+
+---
+
+## Step 6: Trend Comparison
+
+Read `.marketing/DRIFT-LOG.md`. Find the most recent entry with Event = `audit`.
+
+**If a prior audit entry exists (per D-03):**
+1. Parse the Details column to extract the prior aggregate drift percentage
+   - Expected format: `"Nd audit: X% drift, Y findings across Z assets"`
+   - Extract X as the prior drift percentage
+2. Calculate delta: current aggregate drift % - prior aggregate drift %
+3. Determine trend:
+   - Delta > +5%: UP (drift increasing -- positioning adherence worsening)
+   - Delta < -5%: DOWN (drift decreasing -- positioning adherence improving)
+   - Delta between -5% and +5%: STABLE (no significant change)
+4. Set TREND_ARROW and TREND_DETAIL for the report
+
+**If no prior audit entry exists:**
+- Set TREND_ARROW = ""
+- Set TREND_DETAIL = "First audit -- no trend data available."
+
+---
+
+## Step 7: Generate Report
+
+Follow the report format from @positioning-check-report.md.
+
+Generate the full audit report including:
+- Header with audit window and asset count
+- Aggregate drift percentage with trend arrow
+- Per-asset results table (asset x check matrix with drift %)
+- Drift type breakdown (count per category)
+- Bleeding analysis (must-not-say violations classified by asset type with bleeding count and rate)
+- Findings detail for every WARN and FAIL result
+- Accepted deviations cross-reference
+- Trend comparison (if prior audit exists)
+- Recommendations based on aggregate drift thresholds
+
+**Display the report to stdout** (per A1 -- this is a cross-campaign audit,
+not scoped to a single campaign directory).
+
+---
+
+## Step 8: Log to DRIFT-LOG.md
+
+Append the audit results to `.marketing/DRIFT-LOG.md` via CLI:
+
+```bash
+node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" drift-log append \
+  --event-type audit \
+  --source "/ttm-positioning-check" \
+  --details "${WINDOW} audit: ${AGGREGATE_DRIFT}% drift, ${DRIFT_COUNT} findings across ${ASSET_COUNT} assets" \
+  --affected ${ASSET_COUNT}
+```
+
+**IMPORTANT:** Always use the CLI for DRIFT-LOG.md writes. Never write to the file
+directly. The CLI handles append-only semantics, marker-based insertion, and
+consistent formatting.
+
+Display:
+```
+takeToMarket > AUDIT LOGGED TO .marketing/DRIFT-LOG.md
+```
+
+---
+
+## Step 9: Completion Banner
+
+```
+========================================
+takeToMarket > POSITIONING AUDIT COMPLETE
+========================================
+
+Window: last ${WINDOW} | Assets audited: ${ASSET_COUNT}
+Aggregate drift: ${AGGREGATE_DRIFT}% ${TREND_ARROW}
+Campaigns covered: ${CAMPAIGN_COUNT}
+
+Drift logged to: .marketing/DRIFT-LOG.md
+
+Next steps:
+- Run /ttm-fix [campaign-slug] to address specific FAIL results
+- Run /ttm-positioning-shift if aggregate drift > 30% warrants a positioning change
+```
+
+</process>
+
+<success_criteria>
+- [ ] All assets from campaigns within the time window evaluated against GATE-01's 3 checks
+- [ ] Per-asset drift percentage calculated (WARN+FAIL / 3 * 100)
+- [ ] Aggregate drift percentage calculated across all sampled assets
+- [ ] Drift categorized by type (differentiator, proof point, must-not-say)
+- [ ] Bleeding analysis classifies must-not-say violations by asset type (customer-facing vs non-customer-facing)
+- [ ] Accepted deviations cross-referenced from campaign DEVIATIONS.md files
+- [ ] Trend comparison shown if a prior audit exists in DRIFT-LOG.md
+- [ ] Report displayed to stdout in the standard format
+- [ ] Audit results appended to DRIFT-LOG.md via CLI
+- [ ] Recommendations provided based on aggregate drift thresholds
+</success_criteria>
+
+<output>
+- Audit report displayed to stdout (cross-campaign, no file written)
+- `.marketing/DRIFT-LOG.md` updated with audit entry via CLI
+</output>

package/workflows/reference-mgmt/positioning-shift.md

@@ -0,0 +1,368 @@
+<purpose>
+Controlled positioning shift workflow for /ttm-positioning-shift. Requires explicit
+reasoning for the change, collects new positioning fields, generates a migration plan
+for active campaigns, sets deprecation schedule for shipped assets, presents a
+before/after diff for mandatory human approval, and atomically updates POSITIONING.md
+with History table archival. Logs all changes to .marketing/DRIFT-LOG.md.
+</purpose>
+
+<required_reading>
+@${CLAUDE_PLUGIN_ROOT}/references/context-loading.md
+@${CLAUDE_PLUGIN_ROOT}/templates/reference-files/positioning.md
+@${CLAUDE_PLUGIN_ROOT}/templates/migration-plan.md
+</required_reading>
+
+<constraints>
+## This Workflow WRITES to POSITIONING.md
+
+This is one of only two workflows authorized to modify `.marketing/POSITIONING.md`
+(the other is `/ttm-init`). All writes are gated behind mandatory human approval
+in Step 4. Never write to POSITIONING.md without explicit "Approve" from the user.
+</constraints>
+
+<process>
+
+## Text-Mode Detection
+
+**Text mode (`--text` flag):** Set `TEXT_MODE=true` if `--text` is present in `$ARGUMENTS`
+or if the runtime is not Claude Code. When TEXT_MODE is active, replace every
+`AskUserQuestion` call with a plain-text numbered list.
+
+Detection:
+```bash
+if echo "$ARGUMENTS" | grep -q -- '--text'; then TEXT_MODE=true; fi
+```
+
+If `AskUserQuestion` tool is not available in the current runtime, set `TEXT_MODE=true`.
+
+When TEXT_MODE is active, replace each AskUserQuestion with a plain-text numbered list:
+```
+[HEADER]
+[QUESTION]
+  1. [OPTION_1_LABEL] -- [OPTION_1_DESCRIPTION]
+  2. [OPTION_2_LABEL] -- [OPTION_2_DESCRIPTION]
+  ...
+Type the number of your choice:
+```
+
+---
+
+## Step 1: Load Context
+
+```
+takeToMarket > LOADING CONTEXT
+```
+
+**Load Tier 1 summaries** from all 9 reference files (lines 1 to `<!-- END_SUMMARY -->`):
+- `.marketing/POSITIONING.md`
+- `.marketing/BRAND.md`
+- `.marketing/ICP.md`
+- `.marketing/CHANNELS.md`
+- `.marketing/STATE.md` (frontmatter only)
+- `.marketing/CALENDAR.md`
+- `.marketing/COMPETITORS.md`
+- `.marketing/METRICS.md`
+- `.marketing/LEARNINGS.md`
+
+**Load Tier 2 (full content)** for before/after diff:
+- `.marketing/POSITIONING.md` (full -- needed for field comparison and History table)
+
+If `.marketing/POSITIONING.md` does not exist, error:
+"POSITIONING.md not found. Run /ttm-init first to set up your marketing system."
+Exit.
+
+Parse the current POSITIONING.md into structured fields:
+- `CURRENT_CATEGORY` -- from `**Category:**` line
+- `CURRENT_DIFFERENTIATOR` -- from `**Primary differentiator:**` line
+- `CURRENT_AUDIENCE` -- from `**Target audience:**` line
+- `CURRENT_PROOF_POINTS` -- from `## Proof Point Library` table rows
+- `CURRENT_MUST_NOT_SAY` -- from `## Must-Not-Say Terms` table rows
+- `CURRENT_HISTORY` -- from `### Positioning History` table rows
+
+---
+
+## Step 2: Check for Active Campaigns (per D-08, D-09, D-10)
+
+```bash
+ACTIVE_JSON=$(node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" campaign list --active --raw)
+ACTIVE_COUNT=$(echo "$ACTIVE_JSON" | node -e "process.stdin.resume();let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>console.log(JSON.parse(d).count))")
+```
+
+If ACTIVE_COUNT > 0:
+Display warning:
+```
+takeToMarket > ACTIVE CAMPAIGNS DETECTED
+
+${ACTIVE_COUNT} campaign(s) have active assets that may conflict with
+a positioning change. A migration plan will be generated.
+
+Campaigns: [list campaign slugs and phases from ACTIVE_JSON]
+```
+
+If ACTIVE_COUNT == 0:
+Display:
+```
+takeToMarket > NO ACTIVE CAMPAIGNS
+
+No active campaigns detected. Shift will apply to all future campaigns.
+A migration plan is not required, but a deprecation schedule for
+previously shipped assets may still be needed.
+```
+
+---
+
+## Step 3: Collect Shift Information (per D-06)
+
+### 3a: Reasoning
+
+Using AskUserQuestion (text-mode fallback):
+- header: "Positioning Shift Reasoning"
+- question: "Why is this positioning change needed? Provide specific reasoning (market shift, customer feedback, competitive pressure, etc.)"
+- type: free text
+
+Record the reasoning as `SHIFT_REASONING`.
+
+### 3b: New Positioning Fields
+
+Collect ALL structured positioning fields (matching POSITIONING.md template).
+For each field, show the CURRENT value and ask for the NEW value.
+
+**Field 1: Primary Differentiator**
+
+Using AskUserQuestion (text-mode fallback):
+- header: "Primary Differentiator"
+- question: "Current: ${CURRENT_DIFFERENTIATOR}\n\nEnter the NEW primary differentiator phrase (or type 'keep' to keep current):"
+- type: free text
+
+Record as `NEW_DIFFERENTIATOR`. If "keep", use `CURRENT_DIFFERENTIATOR`.
+
+**Field 2: Category**
+
+Using AskUserQuestion (text-mode fallback):
+- header: "Market Category"
+- question: "Current: ${CURRENT_CATEGORY}\n\nEnter the NEW market category (or type 'keep' to keep current):"
+- type: free text
+
+Record as `NEW_CATEGORY`. If "keep", use `CURRENT_CATEGORY`.
+
+**Field 3: Target Audience**
+
+Using AskUserQuestion (text-mode fallback):
+- header: "Target Audience"
+- question: "Current: ${CURRENT_AUDIENCE}\n\nEnter the NEW target audience (or type 'keep' to keep current):"
+- type: free text
+
+Record as `NEW_AUDIENCE`. If "keep", use `CURRENT_AUDIENCE`.
+
+**Field 4: Proof Points**
+
+Display current proof points table. Ask:
+- header: "Proof Points"
+- question: "Current proof points shown above.\n\nProvide the NEW proof points as a numbered list. Each item: claim | source\n(or type 'keep' to keep current):"
+- type: free text
+
+Record as `NEW_PROOF_POINTS`. If "keep", use `CURRENT_PROOF_POINTS`.
+
+**Field 5: Must-Not-Say Terms**
+
+Display current must-not-say terms table. Ask:
+- header: "Must-Not-Say Terms"
+- question: "Current terms shown above.\n\nProvide the NEW must-not-say terms. Each item: term | reason\n(or type 'keep' to keep current):"
+- type: free text
+
+Record as `NEW_MUST_NOT_SAY`. If "keep", use `CURRENT_MUST_NOT_SAY`.
+
+**Validate at least one field changed.** If ALL fields are "keep", display:
+"No fields changed. Nothing to shift. Exiting."
+Exit.
+
+### 3c: Migration Plan for Active Campaigns (per D-04, only if ACTIVE_COUNT > 0)
+
+For each active campaign from `ACTIVE_JSON`:
+
+1. List all assets in `.marketing/CAMPAIGNS/<slug>/ASSETS/` or from MANIFEST.json
+2. Quick-evaluate each asset against the NEW positioning using GATE-01 3-check logic:
+   - Does the asset align with the NEW differentiator?
+   - Are claims backed by NEW proof points?
+   - Does the asset avoid NEW must-not-say terms?
+3. For each asset, recommend one of:
+   - **re-verify**: Asset may still pass under new positioning (minor drift)
+   - **re-produce**: Asset fundamentally conflicts with new positioning
+   - **accept-as-is**: Asset is channel/format where positioning is less critical
+
+Present the migration plan per campaign using the `templates/migration-plan.md` format.
+
+Ask user to confirm or override each recommendation:
+Using AskUserQuestion (text-mode fallback):
+- header: "Migration Plan Review"
+- question: "Review the migration plan above. Do you accept these recommendations?"
+- options:
+  - label: "Accept all" -- Keep all recommendations as-is
+  - label: "Override" -- Change specific recommendations (will prompt per asset)
+  - label: "Cancel" -- Abandon the shift entirely
+
+**On "Override":** For each asset, ask user to select action (re-verify / re-produce / accept-as-is).
+**On "Cancel":** Display "Positioning shift cancelled. No changes made." Exit.
+**On "Accept all":** Continue.
+
+### 3d: Deprecation Schedule (per D-05)
+
+Ask user to set deprecation timeline for shipped assets:
+Using AskUserQuestion (text-mode fallback):
+- header: "Deprecation Schedule"
+- question: "Set a deadline for updating old-positioning assets (e.g., 90 days from now, or a specific date like 2025-06-01). Type 'skip' if no shipped assets need updating:"
+- type: free text
+
+If not "skip":
+Record `DEPRECATION_DEADLINE`.
+
+For each campaign with shipped assets (from campaign list):
+- List shipped assets
+- Record deprecation entry: asset, campaign, old positioning element, required update, deadline
+
+---
+
+## Step 4: Present Before/After Diff and Approval Gate (per D-06, D-07)
+
+Build a summary of all changed fields. Only show fields that actually changed.
+
+Display the complete change for review:
+
+```
+takeToMarket > POSITIONING SHIFT APPROVAL
+
+## Current Positioning
+**Category:** [CURRENT_CATEGORY]
+**Primary Differentiator:** [CURRENT_DIFFERENTIATOR]
+**Target Audience:** [CURRENT_AUDIENCE]
+**Proof Points:** [current count] points
+**Must-Not-Say:** [current count] terms
+
+## Proposed Positioning
+**Category:** [NEW_CATEGORY]
+**Primary Differentiator:** [NEW_DIFFERENTIATOR]
+**Target Audience:** [NEW_AUDIENCE]
+**Proof Points:** [new count] points
+**Must-Not-Say:** [new count] terms
+
+## What Changed
+[field-by-field diff showing only changed fields]
+[For each changed field: "- [FIELD]: [old value] -> [new value]"]
+
+## Reasoning
+[SHIFT_REASONING]
+
+## Impact
+- Active campaigns affected: [ACTIVE_COUNT]
+- Migration actions needed: [count of re-verify + re-produce actions]
+- Deprecation items: [count]
+- Deprecation deadline: [DEPRECATION_DEADLINE or "N/A"]
+```
+
+Using AskUserQuestion (text-mode fallback):
+- header: "Approve Positioning Shift"
+- question: "Review the changes above. This will update POSITIONING.md and affect all future campaigns."
+- options:
+  - label: "Approve" -- Apply the new positioning
+  - label: "Revise" -- Go back and modify the proposed positioning
+  - label: "Cancel" -- Abandon the shift entirely
+
+**On "Revise":** Loop back to Step 3b to re-collect fields.
+**On "Cancel":** Display "Positioning shift cancelled. No changes made." Exit.
+**On "Approve":** Proceed to Step 5.
+
+---
+
+## Step 5: Apply Changes (per D-07)
+
+### 5a: Archive Old Positioning in History Table
+
+Read current POSITIONING.md. Find the `### Positioning History` table.
+Append a new row:
+```
+| [ISO date] | [summary of what changed] | [user's reasoning, sanitized to 100 chars] |
+```
+
+**Sanitization (per T-06-09, Pitfall 3):** Strip pipes (`|`), backticks, newlines from the
+reasoning text. Replace with spaces. Limit to 100 characters. This prevents Markdown table
+delimiter breakage.
+
+### 5b: Update POSITIONING.md Fields
+
+Update the `<!-- _SUMMARY -->` block with new Category, Primary Differentiator, Target Audience.
+Update the `## Proof Point Library` table with new proof points.
+Update the `## Must-Not-Say Terms` table with new terms.
+
+**CRITICAL:** Preserve the `<!-- _SUMMARY -->` and `<!-- END_SUMMARY -->` delimiters exactly
+as they are. All other workflows depend on these markers for Tier 1 context loading.
+
+Write the updated POSITIONING.md atomically via the Write tool.
+
+### 5c: Log Shift to DRIFT-LOG.md (per T-06-10)
+
+```bash
+CHANGED_FIELDS="[list of field names that changed, e.g., differentiator, category]"
+SANITIZED_REASONING=$(echo "${SHIFT_REASONING}" | head -c 100 | tr '|`\n' '   ')
+
+node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" drift-log append \
+  --event-type shift \
+  --source "/ttm-positioning-shift" \
+  --details "Changed: ${CHANGED_FIELDS}. Reasoning: ${SANITIZED_REASONING}" \
+  --affected ${ACTIVE_COUNT}
+```
+
+### 5d: Log Deprecation Entries
+
+For each deprecation item collected in Step 3d:
+```bash
+node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" drift-log deprecation \
+  --asset "[asset name]" \
+  --campaign "[campaign slug]" \
+  --old-element "[changed positioning element]" \
+  --required-update "[what needs updating]" \
+  --deadline "[ISO date]"
+```
+
+If no deprecation items were collected (user typed "skip" in 3d), skip this step.
+
+---
+
+## Step 6: Completion Banner
+
+```
+takeToMarket > POSITIONING SHIFT COMPLETE
+
+Old positioning archived in POSITIONING.md History table.
+New positioning is now active for all future campaigns.
+
+Changes logged: .marketing/DRIFT-LOG.md
+Deprecation items: [count] (deadline: [DEPRECATION_DEADLINE or "N/A"])
+Active campaigns: [ACTIVE_COUNT] -- review migration plan above
+
+Next steps:
+[If active campaigns]: Re-run /ttm-verify <slug> for campaigns marked "re-verify"
+[If deprecation items]: Update shipped assets before [DEPRECATION_DEADLINE]
+[Always]: Run /ttm-positioning-check periodically to monitor drift
+```
+
+</process>
+
+<success_criteria>
+- [ ] User provided explicit reasoning for the positioning change
+- [ ] All 5 structured positioning fields collected (differentiator, category, audience, proof points, must-not-say)
+- [ ] Active campaigns detected and migration plan generated (if any exist)
+- [ ] Deprecation schedule set for shipped assets (if any exist)
+- [ ] Before/after diff presented showing all changed fields
+- [ ] Human approval gate passed (Approve/Revise/Cancel with Approve required)
+- [ ] Old positioning archived in POSITIONING.md History table before update
+- [ ] History table entry sanitized (no pipes, backticks, newlines; max 100 chars)
+- [ ] POSITIONING.md _SUMMARY and END_SUMMARY delimiters preserved
+- [ ] Shift event appended to DRIFT-LOG.md via CLI
+- [ ] Deprecation entries appended to DRIFT-LOG.md via CLI
+- [ ] Completion banner displayed with next steps
+</success_criteria>
+
+<output>
+- `.marketing/POSITIONING.md` (updated with new positioning and History table entry)
+- `.marketing/DRIFT-LOG.md` (shift event appended + deprecation entries)
+</output>