cfsa-antigravity 2.7.0 → 2.9.0

package/template/.agent/workflows/propagate-decision-apply.md

@@ -15,121 +15,54 @@ pipeline:
 
 # Propagate Decision — Apply
 
-Review and apply fixes for explicit contradictions one at a time, flag implicit assumptions for `/resolve-ambiguity`, run a consistency check on changed documents, and write the propagation record.
+Review and apply fixes for explicit contradictions one at a time, flag implicit assumptions, run consistency check, and write propagation record.
 
-> **Prerequisite**: `docs/audits/propagation-scan-[date].md` must exist. Run `/propagate-decision-scan` first if no scan report is found.
+> **Prerequisite**: `docs/audits/propagation-scan-[date].md` must exist. If not → run `/propagate-decision-scan` first.
 
 ---
 
 ## 1. Explicit contradictions (one at a time)
 
-Read .agent/skills/resolve-ambiguity/SKILL.md and follow its methodology.
-
-For each explicit contradiction from the scan report, display:
-
-```
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-Contradiction 1 of X
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-Document: docs/plans/ia/03-payments.md
-Section:  Data Model
-Current:  PostgreSQL array types used for tag storage
-Locked:   MySQL (no native array type)
-Fix to:   Replace with JSON column type per MySQL conventions
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-[Y] Apply fix and move to next
-[n] Skip this item
-[skip] Skip entire document
-[stop-and-save] Save progress and stop for later resumption
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-```
-
-- **Y** — Apply the fix to the source document and move to the next contradiction
-- **n** — Skip this item (leave it unchanged, record as skipped)
-- **skip** — Skip all remaining contradictions in this document
-- **stop-and-save** — Save progress to the scan file (mark which items are done/skipped) and stop. The user can re-run `/propagate-decision-apply` later to resume from where they left off.
-
-> After applying a fix (`[Y]`) to a **spec document** (any file under `docs/plans/ia/`, `docs/plans/be/`, or `docs/plans/fe/`), append a row to that spec's `## Changelog` table recording: today's date, `'Decision propagation: [decision type] — [brief description of fix]'`, `/propagate-decision-apply`, and the section(s) updated. If the spec does not yet have a `## Changelog` section, add one before appending. Skip changelog updates for non-spec documents (e.g., architecture design, vision, engineering standards).
+Read `.agent/skills/resolve-ambiguity/SKILL.md` for methodology.
+
+Read `.agent/skills/prd-templates/references/decision-propagation.md` → **Contradiction Display Format**.
+
+For each explicit contradiction from the scan report: display using the format and wait for user response (Y/n/skip/stop-and-save).
+
+After applying a fix to a spec document (`docs/plans/ia/`, `docs/plans/be/`, or `docs/plans/fe/`): append `## Changelog` row. If no `## Changelog` exists, add one from the template in `.agent/skills/prd-templates/references/be-spec-template.md`.
 
 ---
 
 ## 2. Implicit assumptions (one at a time)
 
-For each implicit assumption from the scan report, display:
-
-```
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-Assumption 1 of X
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-Document: docs/plans/be/auth-spec.md
-Section:  Middleware
-Current:  "the auth provider"
-Issue:    Does not specify Supabase Auth — could be misinterpreted
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-[Y] Flag for /resolve-ambiguity
-[n] Ignore (not ambiguous enough to matter)
-[skip] Skip entire document
-[stop-and-save] Save progress and stop for later resumption
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-```
-
-- **Y** — Add the item to `docs/audits/propagation-ambiguity-[date].md` for later `/resolve-ambiguity` use
-- **n** — Ignore this item (record as ignored)
-- **skip** — Skip all remaining assumptions in this document
-- **stop-and-save** — Same behavior as Step 1
+Read `.agent/skills/prd-templates/references/decision-propagation.md` → **Assumption Display Format**.
+
+For each implicit assumption: display using the format and wait for user response. Y → add to `docs/audits/propagation-ambiguity-[date].md`.
 
 ---
 
 ## 3. Consistency check on changed documents
 
-For every document that received at least one fix in Step 1:
+For every document that received fixes:
+1. Re-read full document — verify fix applied correctly
+2. Check for remaining old-value references
+3. Check for internal contradictions introduced by fixes
+4. Check cross-references between changed documents
 
-1. **Re-read the full document** — verify the fix was applied correctly
-2. **Check for remaining references to old values** — the fix may have changed one section but the same old value may appear elsewhere in the document
-3. **Check for internal contradictions introduced by fixes** — the fix may conflict with other content in the same document
-4. **Check cross-references between changed documents** — if two documents were both fixed, verify they are now consistent with each other
-
-Report any issues found. **Do not auto-fix** — present them to the user for review. If new contradictions were introduced, add them to the scan report for a subsequent apply pass.
+Report issues. **Do not auto-fix** — present to user.
 
 ---
 
 ## 4. Write propagation record
 
-Read .agent/skills/technical-writer/SKILL.md and follow its methodology.
-
-Write `docs/audits/propagation-[type]-[date].md` recording:
+Read `.agent/skills/technical-writer/SKILL.md` for methodology.
 
-- **Decision type** that was propagated
-- **Source document** containing the locked decision
-- **Documents scanned** (count and list)
-- **Explicit contradictions found** (count)
-- **Fixes applied** (count and list)
-- **Fixes skipped** (count and list with reasons)
-- **Implicit assumptions flagged** (count)
-- **Implicit assumptions ignored** (count)
-- **Consistency check results** (pass/fail with details)
-- **Timestamp** of the propagation run
+Write `docs/audits/propagation-[type]-[date].md` recording: decision type, source document, documents scanned, contradictions found/fixed/skipped, assumptions flagged/ignored, consistency results, timestamp.
 
 ---
 
 ## 5. Propose next steps
 
-Display the completion summary:
-
-```
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-Propagation Complete
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-Fixed:   X contradictions across Y documents
-Flagged: X implicit assumptions for /resolve-ambiguity
-Skipped: X items
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-Recommended next steps:
-1. Run `/resolve-ambiguity` to address the X flagged assumptions
-   (see docs/audits/propagation-ambiguity-[date].md)
-2. Run `/remediate-pipeline` to audit all layers with the corrected specs
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-```
-
-If no assumptions were flagged, omit recommendation 1.
+Read `.agent/skills/prd-templates/references/decision-propagation.md` → **Completion Summary Format** and present.
+
+If no assumptions flagged → omit `/resolve-ambiguity` recommendation.

package/template/.agent/workflows/propagate-decision-scan.md

@@ -17,131 +17,60 @@ pipeline:
 
 Pre-scan all 6 decision types for downstream contradictions, present a selection menu, run a full scan on the selected types, and write the impact report.
 
-> **Prerequisite**: At least one instruction file must be filled (not `{{PLACEHOLDER}}`). If all instruction files are still template placeholders, there are no locked decisions to propagate — run `/bootstrap-agents` first.
+> **Prerequisite**: At least one instruction file must be filled (not `{{PLACEHOLDER}}`). If all are still placeholders → **STOP**: run `/bootstrap-agents` first.
 
 ---
 
 ## 1. Pre-scan all decision types
 
-Read all six decision sources and do a quick surface scan of downstream documents:
-
-| Decision Type | Source Document | Downstream Scope |
-|--------------|-----------------|-------------------|
-| **structure** | `.agent/instructions/structure.md` | All IA shards, BE specs, FE specs |
-| **tech-stack** | `.agent/instructions/tech-stack.md` + architecture doc | All IA shards, BE specs, FE specs |
-| **auth-model** | Architecture doc (auth/security section) | All BE specs with middleware, all FE specs with auth flows |
-| **data-placement** | `docs/plans/data-placement-strategy.md` | All IA shards with data models, all BE specs with storage |
-| **patterns** | `.agent/instructions/patterns.md` | All IA shards, BE specs with implementation patterns, FE specs with component patterns |
-| **error-architecture** | Architecture doc `## Error Architecture` section — all 5 sub-sections (`### Global Error Envelope`, `### Error Propagation Chain`, `### Unhandled Exception Strategy`, `### Client Fallback Contract`, `### Error Boundary Strategy`) — located at `docs/plans/*-architecture-design.md` | All BE specs (`docs/plans/be/`) — error envelope conformance, propagation chain rules. All FE specs (`docs/plans/fe/`) — client fallback contract per surface, error boundary placement. |
+Read `.agent/skills/prd-templates/references/decision-propagation.md` → **Decision Type Sources** table.
 
 For each decision type:
 1. Read the source document to extract the current locked value
-2. Quick-scan downstream documents for any reference to that decision topic
-3. Note the count of downstream references found (matches + mismatches — the full scan in Step 3 will determine which are conflicts)
+2. Quick-scan downstream documents for references to that decision topic
+3. Note count of downstream references found
 
 ---
 
 ## 2. Present selection menu
 
-Show the pre-scan findings per decision type:
-
-```
-Decision propagation pre-scan:
+Read `.agent/skills/prd-templates/references/decision-propagation.md` → **Selection Menu Format**. Present with actual counts from Step 1.
 
-[1] structure — structure.md — inconsistencies detected in X documents
-[2] tech-stack — tech-stack.md — inconsistencies detected in X documents
-[3] auth-model — architecture doc — inconsistencies detected in X documents
-[4] data-placement — data-placement-strategy.md — inconsistencies detected in X documents
-[5] patterns — patterns.md — inconsistencies detected in X documents
-[6] error-architecture — architecture doc ## Error Architecture — inconsistencies detected in X documents
+If `[A]` selected → run full scan on all 6 types, filter to those with findings.
 
-[A] All with inconsistencies
-[Q] Quit — no propagation needed
-```
+If called with specific argument (e.g., `/propagate-decision structure`) → skip menu, proceed directly.
 
-If the user selects `[A]`, run the full scan (Step 3) on all 6 types first, then filter to only those with at least one explicit contradiction or implicit assumption.
+**STOP** — do not proceed until the user selects.
 
-If called with a specific argument (e.g., `/propagate-decision structure`), skip the menu and proceed directly with that decision type.
-
-**Do not proceed until the user selects.**
+**Zero-findings shortcut**: If the pre-scan in Step 1 found zero downstream references across ALL decision types → skip the menu entirely: "No downstream references found for any decision type. All pipeline documents are consistent with locked decisions. No propagation needed." Exit workflow.
 
 ---
 
 ## 3. Full scan on selected types
 
-For each selected decision type, scan every downstream document in the scope defined by the table in Step 1:
-
-1. **Read the locked value** from the source document
-2. **Search each downstream document** for references to the decision topic
-3. **For each reference found**, record the line number and classify it as one of:
-   - **Explicit contradiction** — The document states a value that directly conflicts with the locked decision (e.g., document says "PostgreSQL" but tech stack locks "MySQL")
-   - **Implicit assumption** — The document references the topic but uses vague or underspecified language that neither confirms nor contradicts the locked decision (e.g., says "the database" without naming it)
-   - **Consistent** — The document correctly uses the locked value
-
-Record all explicit contradictions and implicit assumptions with their document path, line number, current text, and the locked value they should reflect.
-
-### error-architecture scan
-
-**Source extraction:**
-- Locate `docs/plans/*-architecture-design.md` using the glob (not a hardcoded path).
-- Read the `## Error Architecture` section and extract the locked decisions from all five sub-sections, in particular the canonical field names from `### Global Error Envelope` (e.g., `code`, `message`, `details`, `request_id`).
+For each selected decision type, scan every downstream document in the scope (per Decision Type Sources table):
 
-**BE spec conformance** — scan every file in `docs/plans/be/`:
-- Check whether the spec references the global error envelope by its locked name and uses the canonical field names exactly as locked in `### Global Error Envelope`.
-- Check whether the spec references the propagation chain rules — which layer catches, logs, and surfaces errors — as defined in `### Error Propagation Chain`.
-- Classify findings:
-  - **Explicit contradiction** — spec defines its own error shape with field names or structure that directly conflicts with the locked envelope.
-  - **Implicit assumption** — spec mentions "error handling" or "error response" without naming the canonical envelope shape or field names.
-  - **Consistent** — spec correctly names and uses the locked envelope.
+1. Read the locked value from source
+2. Search each downstream document for references
+3. Classify each reference as: **explicit contradiction** / **implicit assumption** / **consistent**
+4. Record: document path, line number, current text, locked value
 
-**FE spec conformance** — scan every file in `docs/plans/fe/`:
-- Check whether the spec references the client fallback contract appropriate for its surface type, as defined in `### Client Fallback Contract`.
-- Check whether the spec references error boundary placement per `### Error Boundary Strategy`.
-- Apply the same three-way classification (explicit contradiction / implicit assumption / consistent).
-
-All findings are recorded in the standard format (document path, line number, current text, locked value) for inclusion in the impact report built in Step 4.
+For **error-architecture** type: read `.agent/skills/prd-templates/references/decision-propagation.md` → **Error-Architecture Scan Procedure** and follow it.
 
 ---
 
 ## 4. Build and write impact report
 
-Read .agent/skills/technical-writer/SKILL.md and follow its methodology.
-
-Write `docs/audits/propagation-scan-[date].md` with:
-
-### Explicit Contradictions
-
-| Document | Line | Current Text | Locked Value | Decision Type |
-|----------|------|--------------|--------------|---------------|
-| `src/auth/tokens.ts` | 47 | `jwt.sign(payload, secret)` | Supabase Auth (no custom JWT) | auth-model |
-| ... | ... | ... | ... | ... |
+Read `.agent/skills/technical-writer/SKILL.md` for writing standards.
 
-### Implicit Assumptions
+Read `.agent/skills/prd-templates/references/decision-propagation.md` → **Impact Report Format**.
 
-| Document | Line | Current Text | Concern | Decision Type |
-|----------|------|--------------|---------|---------------|
-| `docs/plans/be/auth-spec.md` | 23 | "the auth provider" | Does not name the locked auth provider | auth-model |
-| ... | ... | ... | ... | ... |
-
-### Summary
-
-- **Explicit contradictions**: X items across Y documents
-- **Implicit assumptions**: X items across Y documents
-- **Consistent references**: X items (no action needed)
+Write `docs/audits/propagation-scan-[date].md` using the format.
 
 ---
 
 ## 5. Present summary and confirm
 
-Present the summary counts to the user:
-
-> **Propagation scan complete.**
->
-> - **X explicit contradictions** found — these directly conflict with locked decisions and should be fixed
-> - **Y implicit assumptions** found — these are vague references that could be flagged for `/resolve-ambiguity`
->
-> Review the full report at `docs/audits/propagation-scan-[date].md`.
->
-> Run `/propagate-decision-apply` to review and apply fixes one at a time.
+Present summary counts. Reference the full report path.
 
-**STOP — do not proceed to apply until the user explicitly confirms.**
+**STOP** — do not proceed to apply until user confirms.

package/template/.agent/workflows/remediate-pipeline-execute.md

@@ -102,7 +102,12 @@ Read `.agent/skills/resolve-ambiguity/SKILL.md` for the resolution methodology.
 2. Apply approved mechanical fixes.
 3. Apply user-resolved judgment calls. Re-check if mechanical fixes changed.
 
-Add summary to report. If >70% of docs scored ❌ on majority of dimensions, recommend rewriting layer from scratch.
+Add summary to report.
+
+**Layer restart threshold**: If >70% of documents scored ❌ on majority of dimensions:
+- Calculate the exact percentage and present: "Layer [name]: [X]% of documents scored ❌ on [Y]% of dimensions. This exceeds the 70% restart threshold."
+- Present options: "(1) Restart this layer from scratch using the upstream layer as input, (2) Continue remediating document by document despite low baseline."
+- **STOP** — wait for user decision before proceeding.
 
 ### Persist fix metadata
 

package/template/.agent/workflows/validate-phase-quality.md

@@ -19,6 +19,12 @@ pipeline:
 
 Run all code quality checks for a completed implementation phase.
 
+**Prerequisite**: All slices in the phase must be complete.
+1. Read `.agent/progress/phases/phase-N.md`
+2. Verify every slice shows `complete` status
+3. If any slice is not complete → **STOP**: "Phase N has incomplete slices: [list]. Complete them via `/implement-slice` before running validation."
+
+
 ---
 
 ## 0. Load validation skills
@@ -44,6 +50,11 @@ This is an optimization, not a requirement. Sequential validation is always corr
 
 Run the Test Cmd from `.agent/instructions/commands.md`. All tests must pass. Zero tolerance.
 
+**Test failure early-exit**: If tests fail, do NOT proceed to steps 2-5. Instead:
+1. Capture the failing test output
+2. Identify which slice(s) the failing tests belong to
+3. **STOP**: "Validation blocked — [N] tests failing in slice(s) [names]. Fix via `/implement-slice` and re-run `/validate-phase`."
+
 ## 2. Check coverage
 
 Run the Test Coverage Cmd from `.agent/instructions/commands.md`.
@@ -148,8 +159,8 @@ Read `.agent/skills/prd-templates/references/spec-coverage-sweep.md` and follow
 
 ---
 
-### Propose next step
+### Next step
 
-Code quality gates complete. Next: Run `.agent/workflows/validate-phase-readiness.md` for production readiness checks.
+**STOP** — do NOT proceed to any other workflow. The only valid next step is `/validate-phase-readiness`.
 
-> If this shard was invoked standalone (not from `/validate-phase`), surface this via `notify_user`.
+> If invoked standalone, surface via `notify_user` and wait for user confirmation.

package/template/.agent/workflows/validate-phase-readiness.md

@@ -19,7 +19,7 @@ pipeline:
 
 Run all production readiness checks for a completed implementation phase.
 
-**Prerequisite**: Code quality gates (from `/validate-phase-quality` or equivalent) must pass first.
+**Prerequisite**: Code quality gates (from `/validate-phase-quality` or equivalent) must pass first. If quality gate results do not exist or any check failed → **STOP**: run `/validate-phase-quality` first.
 
 ---
 

package/template/.agent/workflows/verify-infrastructure.md

@@ -42,6 +42,8 @@ Read the current phase plan (e.g., `docs/plans/phases/phase-1.md`) to identify w
 
 Set the report filename now: `docs/audits/verify-infrastructure-YYYY-MM-DD-HHMM[-auth].md`.
 
+**Re-run detection**: Check if a previous verification report exists for this trigger (search `docs/audits/` for `verify-infrastructure-*[-auth].md`).\n- If a previous report exists and shows `✅ PASS` → ask: \"A passing verification report already exists (`[filename]`). Re-run all checks or skip?\"\n- If a previous report exists and shows `❌ FAIL` → proceed automatically (re-verification needed).\n- If no previous report exists → proceed normally.
+
 ---
 
 ## 0.6. Initialize report

package/template/.agent/workflows/write-architecture-spec-deepen.md

@@ -19,7 +19,9 @@ pipeline:
 
 Run iterative deepening passes, write the completed spec, update indexes, run the ambiguity gate, and present for review.
 
-**Prerequisite**: Read the shard file at `docs/plans/ia/[shard-name].md`. Sections should be filled in from the design shard (not skeleton placeholders). If sections are still skeleton placeholders, the design shard has not completed — run `/write-architecture-spec-design` first before running this shard.
+**Prerequisite**: Read the shard file at `docs/plans/ia/[shard-name].md`. Sections should be filled in from the design shard (not skeleton placeholders).
+
+**Skeleton detection**: If the file contains `<!-- TODO -->` markers, `[TBD]` placeholders, or sections with only a heading and no body text → the design shard has not completed. **STOP**: run `/write-architecture-spec-design` first.
 
 ---
 
@@ -73,6 +75,10 @@ Add any new security edge cases or access rules. Present findings to the user.
 If any pass produces significant new content, do another pass — the new content
 may reveal further edge cases. Stop when a pass produces no meaningful additions.
 
+**Pass loop guard**: Track total pass count.
+- Passes 4-5 → normal. Continue if producing meaningful additions.
+- **After pass 5** → **STOP**: "5 deepening passes completed. Still producing new content. Present remaining gaps to user: continue deepening or accept current spec depth?"
+
 ## 9. Write the spec to `docs/plans/ia/[shard-name].md`
 
 Read .agent/skills/technical-writer/SKILL.md for the spec writing step.
@@ -91,7 +97,7 @@ to mark this shard's IA column as complete in `.agent/progress/spec-pipeline.md`
 ## 11.5. Bootstrap Tech Stack Skills (if applicable)
 
 If the shard you just completed is `00-architecture-design.md` (which definitively chooses the project's tech stack):
-Read `.agent/workflows/bootstrap-agents.md` and execute its utility instructions immediately to fill placeholders and provision skills based on the finalized tech stack.
+Read `.agent/workflows/bootstrap-agents.md` and execute its utility instructions immediately to fill placeholders and provision skills based on the finalized tech stack. **HARD GATE**: Follow the bootstrap verification protocol (`.agent/skills/prd-templates/references/bootstrap-verification-protocol.md`). Confirm all tech stack placeholders are filled and all triggered skills are installed before proceeding.
 
 ## 12. Ambiguity gate
 

package/template/.agent/workflows/write-architecture-spec-design.md

@@ -80,10 +80,7 @@ If the sub-feature count is **< 10**, proceed directly to Step 1c.
 
 Read `.agent/skills/brainstorming/SKILL.md` and use it to explore any remaining ambiguous sub-features — those marked `[Architecture-only]` that the user hasn't explicitly confirmed, or any sub-feature whose scope boundary (what's in, what's out) is still unclear after 1b.
 
-> **Authoring pattern for Steps 2–7**: After designing each section, (1) present it to the user with the targeted review questions listed below, (2) refine based on their feedback, (3) write the completed section to `docs/plans/ia/[shard-name].md` immediately — do not batch writes until Step 8.
-
-> [!IMPORTANT]
-> **Write-as-you-go is mandatory.** Each section (Steps 2–7) must be written to `docs/plans/ia/[shard-name].md` immediately after user confirmation. If the conversation truncates, all confirmed sections must survive on disk. Never hold confirmed content in-memory waiting for a later write step.
+> **Authoring pattern for Steps 2–7**: (1) Present each section with review questions, (2) follow decision confirmation protocol (`.agent/skills/prd-templates/references/decision-confirmation-protocol.md`), (3) write to `docs/plans/ia/[shard-name].md` immediately per write verification protocol (`.agent/skills/prd-templates/references/write-verification-protocol.md`). Write-as-you-go is mandatory — never batch writes.
 
 ## 2. Map all interactions
 
@@ -93,9 +90,9 @@ For each feature in the shard, document:
 - What events are emitted
 - Error states and edge cases
 
-**Review questions**: "Does this capture all the ways a user touches this domain?" / "Are there admin/system-initiated actions I'm missing?" / "What happens in each failure case?"
+**Review questions**: "All ways a user touches this domain?" / "Admin/system-initiated actions missing?" / "What happens in each failure case?"
 
-Write the completed `## Interactions` section to `docs/plans/ia/[shard-name].md` immediately after user confirmation.
+Write `## Interactions` to shard file immediately after confirmation. Follow write verification protocol.
 
 ## 3. Define contracts
 
@@ -107,9 +104,9 @@ For each interaction, define the contract shape:
 - Error shape (specific error codes)
 - Note: actual {{CONTRACT_LIBRARY}} schemas written in BE spec phase
 
-**Review questions**: "Are there fields I'm missing from these requests/responses?" / "Are these error codes specific enough?"
+**Review questions**: "Fields missing from requests/responses?" / "Error codes specific enough?"
 
-Write the completed `## Contracts` section to `docs/plans/ia/[shard-name].md` immediately after user confirmation.
+Write `## Contracts` to shard file immediately after confirmation. Follow write verification protocol.
 
 ## 4. Design data models
 
@@ -120,9 +117,9 @@ Read `.agent/skills/prd-templates/references/skill-loading-protocol.md` and load
 
 Define for each entity: tables/collections, fields, types, relationships, indexes, constraints and validation rules.
 
-**Review questions**: "Does this schema capture everything this domain needs to store?" / "Are the relationships and cardinalities correct?" / "Are there derived/computed fields I should account for?"
+**Review questions**: "Schema captures everything?" / "Relationships and cardinalities correct?" / "Derived/computed fields to account for?"
 
-Write the completed `## Data Models` section to `docs/plans/ia/[shard-name].md` immediately after user confirmation.
+Write `## Data Models` to shard file immediately after confirmation. Follow write verification protocol.
 
 > **Decision recording**: For non-trivial data model decisions (schema approach, denormalization trade-offs, index strategy), read `.agent/skills/session-continuity/protocols/06-decision-analysis.md` and follow the **Decision Effect Analysis Protocol**.
 
@@ -136,9 +133,9 @@ Read .agent/skills/security-scanning-security-hardening/SKILL.md and apply its a
 - Escalation paths (Guardian, Admin)
 - Admin-only operations
 
-**Review questions**: "Can you think of a scenario where a user should be blocked that this matrix allows?" / "Can you think of a scenario where a user should be allowed that this matrix blocks?"
+**Review questions**: "Scenario where a blocked user gets through?" / "Scenario where an allowed user is blocked?"
 
-Write the completed `## Access Control` section to `docs/plans/ia/[shard-name].md` immediately after user confirmation.
+Write `## Access Control` to shard file immediately after confirmation. Follow write verification protocol.
 
 > **Decision recording**: For access control architecture decisions (role hierarchy, ownership model, escalation paths), read `.agent/skills/session-continuity/protocols/06-decision-analysis.md` and follow the **Decision Effect Analysis Protocol**. Record to `memory/decisions.md`.
 
@@ -150,7 +147,7 @@ Read `.agent/skills/accessibility/references/ia-spec-checklist.md` and follow it
 
 **If surfaces are `api`, `cli`, or `extension` only:** Write `"Not applicable — no visual surfaces"` in the `## Accessibility` section.
 
-Write the completed `## Accessibility` section to `docs/plans/ia/[shard-name].md` immediately after user confirmation.
+Write `## Accessibility` to shard file immediately after confirmation. Follow write verification protocol.
 
 ## 6. Design event schemas (if applicable)
 
@@ -158,7 +155,7 @@ Write the completed `## Accessibility` section to `docs/plans/ia/[shard-name].md
 - Async vs sync processing
 - Retry semantics
 
-Write the completed `## Event Schemas` section to `docs/plans/ia/[shard-name].md` immediately after user confirmation (if applicable).
+Write `## Event Schemas` to shard file immediately after confirmation (if applicable). Follow write verification protocol.
 
 ## 7. Document edge cases