@cratis/pi 7.78.0 → 7.80.0

package/package/corpus/agents/code-reviewer.md

@@ -161,21 +161,6 @@ When checking unused code, references, or naming, use semantic navigation if the
 
 ## Output format
 
-Start with a **summary**:
-> **Review result: ✅ Approved / ⚠️ Approved with comments / ❌ Changes requested**
-
-Then list issues grouped by file:
-
-```
-### <file path>
-
-**[BLOCKING]** … or **[SUGGESTION]** …
-> Line N: `problematic code`
-> Because: explanation
-> Fix:
-> ```
-> corrected code
-> ```
-```
-
-End with a checklist of passed / failed items so the developer knows what was verified.
+Read and use `.cratis/ai/rules/review-reports.md` when writing conclusions.
+Apply the domain-specific classification in the Report section of
+`.cratis/ai/skills/cratis-code-review/SKILL.md`.

package/package/corpus/agents/coordinator.md

@@ -143,8 +143,7 @@ For implementation, the applicable changed-lane gates must pass. Mark unrelated
 - [ ] `npx tsc -b` — zero TypeScript errors (if frontend present)
 - [ ] Public-facing changes (clients, SDKs, public APIs) include associated documentation updates
 - [ ] `Documentation/verify-markdown.sh` passes when documentation is added or changed
-- [ ] `code-reviewer` finds no blocking issues
-- [ ] `security-reviewer` finds no vulnerabilities
+- [ ] Code and security reviews approve the scoped change; combine their reports using `.cratis/ai/rules/review-reports.md`, preserving each reviewer's findings and scope limits
 - [ ] PR description follows the pull request template and the release-note contract in `pull-requests.md`; test and review notes are in a PR comment
 
 ---

package/package/corpus/agents/orchestrator.md

@@ -167,8 +167,7 @@ For implementation, the applicable changed-lane gates must pass. Mark unrelated
 - [ ] `npx tsc -b` — zero TypeScript errors (if frontend present)
 - [ ] Public-facing changes (clients, SDKs, public APIs) include associated documentation updates
 - [ ] `Documentation/verify-markdown.sh` passes when documentation is added or changed
-- [ ] `code-reviewer` finds no blocking issues
-- [ ] `security-reviewer` finds no vulnerabilities
+- [ ] Code and security reviews approve the scoped change; combine their reports using `.cratis/ai/rules/review-reports.md`, preserving each reviewer's findings and scope limits
 - [ ] All documentation is complete and accurate (if required)
 - [ ] PR description follows the pull request template and the release-note contract in `pull-requests.md`; test and review notes are in a PR comment
 

package/package/corpus/agents/performance-reviewer.md

@@ -71,39 +71,8 @@ Your responsibility is to identify performance problems in changed code before t
 
 ---
 
-## Risk classification
-
-| Label | Meaning |
-| ------- | --------- |
-| 🔴 High | Will cause measurable degradation at moderate load — must fix before merge |
-| 🟡 Medium | Could degrade under load or at scale — should fix soon |
-| 🟢 Low | Minor inefficiency or style issue — fix when convenient |
-
----
-
 ## Output format
 
-Start with a **summary**:
-> **Performance Review: ✅ No issues / ⚠️ Minor findings / ❌ Blocking issues found**
-
-Group findings by category:
-
-```
-### MongoDB / Read Models
-
-🟡 **Medium** — `<AppSourceRoot>/Projects/Listing/AllProjects.cs`
-> The query does not specify a sort order or index hint, which will result in a
-> collection scan once the `projects` collection grows.
-> Fix: Add `.SortBy(m => m.Name)` and ensure an index on `Name` exists in the
-> MongoDB collection initialization.
-```
-
-End with a summary table:
-
-| Category | Status |
-| ---------- | -------- |
-| Chronicle / Event Sourcing | ✅ / ⚠️ / ❌ |
-| MongoDB / Read Models | ✅ / ⚠️ / ❌ |
-| ASP.NET Core / Commands & Queries | ✅ / ⚠️ / ❌ |
-| React / TypeScript | ✅ / ⚠️ / ❌ |
-| General .NET | ✅ / ⚠️ / ❌ |
+Read and use `.cratis/ai/rules/review-reports.md` when writing conclusions.
+Apply the domain-specific risk mapping in the Report section of
+`.cratis/ai/skills/cratis-performance-review/SKILL.md`.

package/package/corpus/agents/planner.md

@@ -136,9 +136,9 @@ For an implemented application slice, require the applicable changed-lane gates
 - [ ] All TypeScript specs pass (`yarn test`) if applicable
 - [ ] Public-facing changes (clients, SDKs, public APIs) include associated documentation updates
 - [ ] `Documentation/verify-markdown.sh` passes when documentation is added or changed
-- [ ] Code review by `code-reviewer` finds no blocking issues
+- [ ] Code review by `code-reviewer` approves the scoped change using `.cratis/ai/rules/review-reports.md`
 - [ ] In an opted-in repository: `.play` changes were reviewed by `screenplay-reviewer`, and no modeled business rule or model-owned behavior exists only in code (infrastructure, client, adapter, code-attachment/handler code and authorized gap-fill governed by the `.play` slice and specs are allowed)
-- [ ] Security review by `security-reviewer` finds no vulnerabilities
+- [ ] Security review by `security-reviewer` approves the scoped change; combine the review reports using `.cratis/ai/rules/review-reports.md`, preserving each reviewer's findings and scope limits
 - [ ] PR description follows the pull request template and the release-note contract in `pull-requests.md`; test and review notes are in a PR comment
 
 ---

package/package/corpus/agents/repository-investigation-reviewer.md

@@ -42,4 +42,11 @@ You independently review a completed Cratis repository investigation. Your resul
 7. Pre-existing failures are distinguished from failures caused by the investigated behavior.
 8. Failed, missing, or inconclusive evidence remains failed, blocked, or inconclusive.
 
-Return only the requested typed review envelope. Request a bounded correction when a correctable evidence gap exists; otherwise report the exact blocker.
+## Output format
+
+Use `.cratis/ai/rules/review-reports.md` for conclusions, including its
+typed-envelope mapping. Return only the requested typed review
+envelope; preserve its schema and blocked or inconclusive states. A material
+unsupported conclusion or inconsistent repository mode prevents acceptance;
+a non-blocking recommendation is advisory. Request a bounded correction when
+a correctable evidence gap exists; otherwise report the exact blocker.

package/package/corpus/agents/security-reviewer.md

@@ -79,42 +79,8 @@ Your responsibility is to perform a structured **security review** of all change
 
 ---
 
-## Risk classification
-
-Assign each finding one of:
-
-| Label | Meaning |
-|-------|---------|
-| 🔴 Critical | Must be fixed before merge — exploitable without significant effort |
-| 🟡 Medium | Should be fixed soon — exploitable under specific conditions |
-| 🟢 Low | Improvement or defense-in-depth — fix when convenient |
-
----
-
 ## Output format
 
-Start with a **summary**:
-> **Security Review: ✅ No issues / ⚠️ Low-risk findings / ❌ Blocking issues found**
-
-Then list findings grouped by category:
-
-```
-### Input Validation & Injection
-
-🔴 **Critical** — `Projects/Registration/RegisterProject.cs`
-> Line 14: `var path = Path.Combine(root, command.FileName);`
-> A path traversal attack is possible if `FileName` contains `../` sequences.
-> Fix: Validate that the resolved path stays within the expected root directory.
-```
-
-End with a summary table:
-
-| Category | Status |
-|----------|--------|
-| Input Validation | ✅ / ⚠️ / ❌ |
-| Auth / Authz | ✅ / ⚠️ / ❌ |
-| Data Exposure | ✅ / ⚠️ / ❌ |
-| Secrets | ✅ / ⚠️ / ❌ |
-| Dependencies | ✅ / ⚠️ / ❌ |
-| Event Sourcing | ✅ / ⚠️ / ❌ |
-| Frontend | ✅ / ⚠️ / ❌ |
+Read and use `.cratis/ai/rules/review-reports.md` when writing conclusions.
+Apply the domain-specific risk mapping in the Report section of
+`.cratis/ai/skills/cratis-security-review/SKILL.md`.

package/package/corpus/harnesses/copilot/instructions/review-reports.instructions.md

@@ -0,0 +1,68 @@
+---
+applyTo: ".cratis/ai/skills/cratis-code-review/**,.cratis/ai/skills/cratis-security-review/**,.cratis/ai/skills/cratis-performance-review/**,.cratis/ai/agents/**,.cratis/ai/prompts/**"
+paths:
+  - ".cratis/ai/skills/cratis-code-review/**"
+  - ".cratis/ai/skills/cratis-security-review/**"
+  - ".cratis/ai/skills/cratis-performance-review/**"
+  - ".cratis/ai/agents/**"
+  - ".cratis/ai/prompts/**"
+---
+<!-- cratis-ai: generated Copilot instructions. Do not edit; rules/ is the source. -->
+
+<!-- Copyright (c) Cratis. All rights reserved. -->
+<!-- Licensed under the MIT license. See LICENSE file in the project root for full license information. -->
+
+# Shared review reports
+
+Use this report shape for code, security, performance, and repository-investigation
+reviews. Domain-specific risk labels refine findings, not the report or verdict
+vocabulary. Review the change within the declared scope, not unrelated existing debt.
+
+## Report shape
+
+Keep these sections in order, writing `None` when a section has no entries:
+
+- **Blockers** — findings that must be fixed before merge. Each names a file and
+  line or evidence reference, the problem, its concrete consequence, and a proposed
+  correction. A blocker names a consequence, not a rule number: "returns HTTP 500
+  instead of a validation error" explains harm; "violates rule 4" does not.
+- **Suggestions** — non-blocking improvements, with their benefit and any relevant
+  conditions. Do not turn a preference or a hypothetical risk into a merge gate.
+- **Dismissed (with reason)** — candidate findings considered and rejected, each
+  with the evidence or reasoning for dismissal so another reviewer need not raise
+  it again. Do not invent candidates to populate this section.
+- **Verdict** — one of the values below, scoped to the evidence actually examined.
+
+An empty Blockers section is a valid, complete review. Never manufacture a finding
+to make a review look useful. Reserve **[BLOCKING]** exclusively for
+must-fix-before-merge findings; suggestions and dismissed findings never carry it.
+
+Every review includes a **Not examined:** line naming the paths, surfaces, checks,
+and axes not examined, including anything that could not be reached. Name what was
+not measured: code-shape inspection is not a benchmark, a build is not behavioral
+proof, and an unexamined surface is not verified. State `None` only when the entire
+declared scope was examined; otherwise give concrete limits and remaining checks.
+
+## Verdict vocabulary
+
+| Verdict | Meaning |
+| --- | --- |
+| **Approved** | No blockers or suggestions within the examined scope; required review checks are complete. |
+| **Approved with suggestions** | No blockers; non-blocking suggestions remain and required review checks are complete. |
+| **Changes requested** | At least one blocker must be corrected before merge. |
+| **Incomplete** | No confirmed blocker, but missing or inconclusive required evidence prevents approval. |
+
+Skipped optional axes belong on the Not examined line and do not alone prevent a
+scoped approval. Missing required evidence does. When blockers and evidence gaps
+coexist, use Changes requested and record the gaps on the Not examined line; never
+reinterpret a failed or blocked gate as passing.
+
+When combining reviews, retain one report per reviewer with the shared sections
+and scope line, then give one combined verdict. Any blocker means Changes requested;
+otherwise any Incomplete review means Incomplete; otherwise any remaining suggestion
+means Approved with suggestions; otherwise use Approved. Do not drop dismissals or
+scope limits when combining reports.
+
+When a workflow requires a typed review envelope, preserve its schema and express
+these sections, verdict meanings, and scope limits through its existing fields.
+Do not append a competing Markdown report or invent envelope fields.

package/package/corpus/harnesses/pi/agents/code-reviewer.md

@@ -158,21 +158,6 @@ When checking unused code, references, or naming, use semantic navigation if the
 
 ## Output format
 
-Start with a **summary**:
-> **Review result: ✅ Approved / ⚠️ Approved with comments / ❌ Changes requested**
-
-Then list issues grouped by file:
-
-```
-### <file path>
-
-**[BLOCKING]** … or **[SUGGESTION]** …
-> Line N: `problematic code`
-> Because: explanation
-> Fix:
-> ```
-> corrected code
-> ```
-```
-
-End with a checklist of passed / failed items so the developer knows what was verified.
+Read and use `.cratis/ai/rules/review-reports.md` when writing conclusions.
+Apply the domain-specific classification in the Report section of
+`.cratis/ai/skills/cratis-code-review/SKILL.md`.

package/package/corpus/harnesses/pi/agents/coordinator.md

@@ -139,8 +139,7 @@ For implementation, the applicable changed-lane gates must pass. Mark unrelated
 - [ ] `npx tsc -b` — zero TypeScript errors (if frontend present)
 - [ ] Public-facing changes (clients, SDKs, public APIs) include associated documentation updates
 - [ ] `Documentation/verify-markdown.sh` passes when documentation is added or changed
-- [ ] `code-reviewer` finds no blocking issues
-- [ ] `security-reviewer` finds no vulnerabilities
+- [ ] Code and security reviews approve the scoped change; combine their reports using `.cratis/ai/rules/review-reports.md`, preserving each reviewer's findings and scope limits
 - [ ] PR description follows the pull request template and the release-note contract in `pull-requests.md`; test and review notes are in a PR comment
 
 ---

package/package/corpus/harnesses/pi/agents/orchestrator.md

@@ -163,8 +163,7 @@ For implementation, the applicable changed-lane gates must pass. Mark unrelated
 - [ ] `npx tsc -b` — zero TypeScript errors (if frontend present)
 - [ ] Public-facing changes (clients, SDKs, public APIs) include associated documentation updates
 - [ ] `Documentation/verify-markdown.sh` passes when documentation is added or changed
-- [ ] `code-reviewer` finds no blocking issues
-- [ ] `security-reviewer` finds no vulnerabilities
+- [ ] Code and security reviews approve the scoped change; combine their reports using `.cratis/ai/rules/review-reports.md`, preserving each reviewer's findings and scope limits
 - [ ] All documentation is complete and accurate (if required)
 - [ ] PR description follows the pull request template and the release-note contract in `pull-requests.md`; test and review notes are in a PR comment
 

package/package/corpus/harnesses/pi/agents/performance-reviewer.md

@@ -68,39 +68,8 @@ Your responsibility is to identify performance problems in changed code before t
 
 ---
 
-## Risk classification
-
-| Label | Meaning |
-| ------- | --------- |
-| 🔴 High | Will cause measurable degradation at moderate load — must fix before merge |
-| 🟡 Medium | Could degrade under load or at scale — should fix soon |
-| 🟢 Low | Minor inefficiency or style issue — fix when convenient |
-
----
-
 ## Output format
 
-Start with a **summary**:
-> **Performance Review: ✅ No issues / ⚠️ Minor findings / ❌ Blocking issues found**
-
-Group findings by category:
-
-```
-### MongoDB / Read Models
-
-🟡 **Medium** — `<AppSourceRoot>/Projects/Listing/AllProjects.cs`
-> The query does not specify a sort order or index hint, which will result in a
-> collection scan once the `projects` collection grows.
-> Fix: Add `.SortBy(m => m.Name)` and ensure an index on `Name` exists in the
-> MongoDB collection initialization.
-```
-
-End with a summary table:
-
-| Category | Status |
-| ---------- | -------- |
-| Chronicle / Event Sourcing | ✅ / ⚠️ / ❌ |
-| MongoDB / Read Models | ✅ / ⚠️ / ❌ |
-| ASP.NET Core / Commands & Queries | ✅ / ⚠️ / ❌ |
-| React / TypeScript | ✅ / ⚠️ / ❌ |
-| General .NET | ✅ / ⚠️ / ❌ |
+Read and use `.cratis/ai/rules/review-reports.md` when writing conclusions.
+Apply the domain-specific risk mapping in the Report section of
+`.cratis/ai/skills/cratis-performance-review/SKILL.md`.

package/package/corpus/harnesses/pi/agents/planner.md

@@ -132,9 +132,9 @@ For an implemented application slice, require the applicable changed-lane gates
 - [ ] All TypeScript specs pass (`yarn test`) if applicable
 - [ ] Public-facing changes (clients, SDKs, public APIs) include associated documentation updates
 - [ ] `Documentation/verify-markdown.sh` passes when documentation is added or changed
-- [ ] Code review by `code-reviewer` finds no blocking issues
+- [ ] Code review by `code-reviewer` approves the scoped change using `.cratis/ai/rules/review-reports.md`
 - [ ] In an opted-in repository: `.play` changes were reviewed by `screenplay-reviewer`, and no modeled business rule or model-owned behavior exists only in code (infrastructure, client, adapter, code-attachment/handler code and authorized gap-fill governed by the `.play` slice and specs are allowed)
-- [ ] Security review by `security-reviewer` finds no vulnerabilities
+- [ ] Security review by `security-reviewer` approves the scoped change; combine the review reports using `.cratis/ai/rules/review-reports.md`, preserving each reviewer's findings and scope limits
 - [ ] PR description follows the pull request template and the release-note contract in `pull-requests.md`; test and review notes are in a PR comment
 
 ---

package/package/corpus/harnesses/pi/agents/repository-investigation-reviewer.md

@@ -40,4 +40,11 @@ You independently review a completed Cratis repository investigation. Your resul
 7. Pre-existing failures are distinguished from failures caused by the investigated behavior.
 8. Failed, missing, or inconclusive evidence remains failed, blocked, or inconclusive.
 
-Return only the requested typed review envelope. Request a bounded correction when a correctable evidence gap exists; otherwise report the exact blocker.
+## Output format
+
+Use `.cratis/ai/rules/review-reports.md` for conclusions, including its
+typed-envelope mapping. Return only the requested typed review
+envelope; preserve its schema and blocked or inconclusive states. A material
+unsupported conclusion or inconsistent repository mode prevents acceptance;
+a non-blocking recommendation is advisory. Request a bounded correction when
+a correctable evidence gap exists; otherwise report the exact blocker.

package/package/corpus/harnesses/pi/agents/security-reviewer.md

@@ -76,42 +76,8 @@ Your responsibility is to perform a structured **security review** of all change
 
 ---
 
-## Risk classification
-
-Assign each finding one of:
-
-| Label | Meaning |
-|-------|---------|
-| 🔴 Critical | Must be fixed before merge — exploitable without significant effort |
-| 🟡 Medium | Should be fixed soon — exploitable under specific conditions |
-| 🟢 Low | Improvement or defense-in-depth — fix when convenient |
-
----
-
 ## Output format
 
-Start with a **summary**:
-> **Security Review: ✅ No issues / ⚠️ Low-risk findings / ❌ Blocking issues found**
-
-Then list findings grouped by category:
-
-```
-### Input Validation & Injection
-
-🔴 **Critical** — `Projects/Registration/RegisterProject.cs`
-> Line 14: `var path = Path.Combine(root, command.FileName);`
-> A path traversal attack is possible if `FileName` contains `../` sequences.
-> Fix: Validate that the resolved path stays within the expected root directory.
-```
-
-End with a summary table:
-
-| Category | Status |
-|----------|--------|
-| Input Validation | ✅ / ⚠️ / ❌ |
-| Auth / Authz | ✅ / ⚠️ / ❌ |
-| Data Exposure | ✅ / ⚠️ / ❌ |
-| Secrets | ✅ / ⚠️ / ❌ |
-| Dependencies | ✅ / ⚠️ / ❌ |
-| Event Sourcing | ✅ / ⚠️ / ❌ |
-| Frontend | ✅ / ⚠️ / ❌ |
+Read and use `.cratis/ai/rules/review-reports.md` when writing conclusions.
+Apply the domain-specific risk mapping in the Report section of
+`.cratis/ai/skills/cratis-security-review/SKILL.md`.

package/package/corpus/product-sync.json

@@ -171,9 +171,9 @@
         }
       ],
       "synced": {
-        "version": "4.212.4",
-        "date": "2026-10-17",
-        "by": "Cratis/AI#772"
+        "version": "4.213.0",
+        "date": "2026-10-18",
+        "by": "Cratis/AI#771"
       },
       "covers": {
         "skills": [
@@ -201,7 +201,7 @@
         ],
         "rules": []
       },
-      "notes": "Cratis/AI#772: standalone Screenplay 4.212.4 pinned; regenerated compiler contract is byte-identical to the v4.212.4 release asset. Source-checked joined-event automap/no automap overrides and level fallback in executable binding; PLAY0380 covers only all inside children/nested. No new render/runtime probe. Prior: Cratis/AI#769: standalone Screenplay 4.212.3 pinned; regenerated compiler contract is byte-identical to the v4.212.3 release asset. Source-checked both compilers and projection documentation for PLAY0801 DuplicateEventInProjectionScope: shared from/removal/clear set, separate join set, fresh sets per children/nested/variant level, and no two-row update through repeated from blocks with different keys. No new render/runtime probe. Prior: Cratis/AI#768: standalone Screenplay 4.212.2 pinned; regenerated compiler contract is byte-identical to the v4.212.2 release asset (unchanged from the previous contract). Source-checked v4.212.0 split-model dotted note targets, open-workspace applicationIdentity and complete add/reanchor substitutions; unbound container identities are not claimed. v4.212.1 aligns PLAY0535 collection fields, optional parameters and single-result identity inference. v4.212.2 counts read-only query denials for SPEC004, not SPEC006. No new render/runtime probe. Prior: Cratis/AI#762 and #761: source-checked v4.210.0 and v4.211.0 contracts for PLAY0800 CommandHandlerRequiresAttachment (required typed subject, permanent code-attachment requirement, other PLAY0268 families unchanged), independent reference remove/add batches, located same-text ambiguity conflicts and string MCP conflict/move-report document fields. v4.211.1 mapping changes inspected but excluded from this guidance update at the user's request; no typed PLAY0273 property/type arguments are claimed. Standalone Screenplay 4.211.1 and its compiler contract pinned; the contract is a byte-identical copy of the v4.211.1 release asset. No new render/runtime probe. Prior: Standalone 4.205.0 and byte-identical compiler contract pinned. Cratis/AI#746: Uuid ==/!= in command require and produces when (ESM v28): same-concept rule, bare Uuid against a concept, canonical literals, protected read paths in require only; PLAY0268 (different concepts, ordering, Uuid validation and concept rules, read paths in produces when) and PLAY0273 (non-canonical literal) checked against the 4.205.0 compiler, v28 selection read from the MCP executable-model view; Stage admits exact v1-v21 and v23-v26 pairs so v28 is refused STAGE-ESM-016, not probed against a Stage image; CLI 3.74.0 renders through v26. Prior: Standalone 4.204.0 and byte-identical compiler contract pinned. Cratis/AI#702 and #691: PLAY0690 reducer identity (Screenplay 4.170.0, native compiler only) and the screenplay.json validation gate (Screenplay 4.165.0; cratis screenplay validate reads it from CLI 3.65.0) are taught and probed against the 4.204.0 compiler. Cratis/AI#743: flat composite read-model keys (ESM v27): untyped projection key blocks on root from and remove with, equality-filter lists, single-instance by blocks and per-part fixtures, with PLAY0661/PLAY0662/PLAY0268 refusals checked against the 4.204.0 compiler; Stage origin/main still refuses v27 with STAGE-ESM-016 (stage-rendering.md); Stage v4.135.0 v26 admission (Host and executor run date comparisons; renderer STAGE-ESM-046) was source-checked for this sync; no render or runtime probe. Prior: Standalone 4.201.0 and byte-identical compiler contract pinned. Cratis/AI#733: the ui profile root template, shell options, appearance and new screens default (PLAY0788-PLAY0799, quick fix for the legacy layout line, ui-profiles MCP tool, 44 tools). Cratis/AI#735: chronological Date/DateTime ordering in command conditions and command/property literal validation (ESM v26), UTC tick precision and pre-rule offset validation; then matching remains ordinal. Source-checked Screenplay v4.199.0 commands, diagnostics, interoperability and specifications documentation plus decision 0087. Stage v4.127.1 still refuses v26 with STAGE-ESM-016 (stage-rendering.md and SemanticVersionFeatures.Supports); no render/runtime probe. Cratis/AI#576: prior mechanical compiler catch-up. Language batch #717/#722/#723/#724/#720/#728/#734 teaches atomic reaction batches (v22), described payload handlers (v23), portable linear matching, ordinal text rules (v24), protected command reads (v25), diagnostic arguments and event-source invokes mappings. Facts read at Screenplay v4.198.0 and introducing tags; Stage v4.127.0 admits exact v1-v21 and v23-v25 pairs but refuses v22/v26 and mixed pairs (STAGE-ESM-016), protected reads (044), atomic mode (043) and described handlers (STAGE-IMPL-002), even Stub mode. Stage text rules execute/render; no new renderer/runtime probe or Stage pin uplift. Cratis/AI#706: application navigation regions (module inherit, extend or override), toolbar slice buttons, blueprint template references and sample data packs in cratis-screenplay-ui-composition (references/application-shell.md), with the canonical shell vector and the rejection codes PLAY0710-PLAY0722 and PLAY0740-PLAY0765. Examples moved to the executable-state rules since 4.164: translator reactions in an Automation slice beside the Translate slice (PLAY0694) and the first record of a capture key appended with `when added`. Earlier: Standalone 4.164.0 and byte-identical compiler contract pinned. Cratis/AI#663: one origin per capture (PLAY0687). #668: executable no-event/redelivery v17. #684: concept query-argument validation in every version and query-error assertions v18. #681: executable refusal branches and refusal values v19. #666: proposal summary/severity counts and exact structural source proposals. Generated-concept rules select v20 with PLAY0688/0689 proofs and derived-matches repair; generated secrets and preview strategies remain refused. Release-baseline from-esm admission reads storedName. Standalone binding is not renderer admission: Stage 4.103.0 admits v1-v17 and v19; CLI 3.62.0 bundles Screenplay 4.159.0 / Stage 4.99.0 and renders through v16. Prior evidence remains unless superseded; no new renderer, Docker or browser probe."
+      "notes": "Cratis/AI#771: standalone Screenplay 4.213.0 pinned; regenerated compiler contract is byte-identical to the v4.213.0 release asset and unchanged from 4.212.4. Reviewed the full v4.212.4-v4.213.0 delta against tagged decision 0093 and MCP reference: pre-binding container identities and stable binding/migration continuity, own-slice member substitutions, containerIdentities completeness/ambiguity/collision refusals, retained ambiguous notes, explicit semanticRenames/retirements, binding fixes through MCP, exact reopen exception, notes/identity rollback and exact-ID re-add anchoring. No grammar, binder, ESM or diagnostic-code changes; no new render/runtime probe. Prior: Cratis/AI#772: standalone Screenplay 4.212.4 pinned; regenerated compiler contract is byte-identical to the v4.212.4 release asset. Source-checked joined-event automap/no automap overrides and level fallback in executable binding; PLAY0380 covers only all inside children/nested. No new render/runtime probe. Prior: Cratis/AI#769: standalone Screenplay 4.212.3 pinned; regenerated compiler contract is byte-identical to the v4.212.3 release asset. Source-checked both compilers and projection documentation for PLAY0801 DuplicateEventInProjectionScope: shared from/removal/clear set, separate join set, fresh sets per children/nested/variant level, and no two-row update through repeated from blocks with different keys. No new render/runtime probe. Prior: Cratis/AI#768: standalone Screenplay 4.212.2 pinned; regenerated compiler contract is byte-identical to the v4.212.2 release asset (unchanged from the previous contract). Source-checked v4.212.0 split-model dotted note targets, open-workspace applicationIdentity and complete add/reanchor substitutions; unbound container identities are not claimed. v4.212.1 aligns PLAY0535 collection fields, optional parameters and single-result identity inference. v4.212.2 counts read-only query denials for SPEC004, not SPEC006. No new render/runtime probe. Prior: Cratis/AI#762 and #761: source-checked v4.210.0 and v4.211.0 contracts for PLAY0800 CommandHandlerRequiresAttachment (required typed subject, permanent code-attachment requirement, other PLAY0268 families unchanged), independent reference remove/add batches, located same-text ambiguity conflicts and string MCP conflict/move-report document fields. v4.211.1 mapping changes inspected but excluded from this guidance update at the user's request; no typed PLAY0273 property/type arguments are claimed. Standalone Screenplay 4.211.1 and its compiler contract pinned; the contract is a byte-identical copy of the v4.211.1 release asset. No new render/runtime probe. Prior: Standalone 4.205.0 and byte-identical compiler contract pinned. Cratis/AI#746: Uuid ==/!= in command require and produces when (ESM v28): same-concept rule, bare Uuid against a concept, canonical literals, protected read paths in require only; PLAY0268 (different concepts, ordering, Uuid validation and concept rules, read paths in produces when) and PLAY0273 (non-canonical literal) checked against the 4.205.0 compiler, v28 selection read from the MCP executable-model view; Stage admits exact v1-v21 and v23-v26 pairs so v28 is refused STAGE-ESM-016, not probed against a Stage image; CLI 3.74.0 renders through v26. Prior: Standalone 4.204.0 and byte-identical compiler contract pinned. Cratis/AI#702 and #691: PLAY0690 reducer identity (Screenplay 4.170.0, native compiler only) and the screenplay.json validation gate (Screenplay 4.165.0; cratis screenplay validate reads it from CLI 3.65.0) are taught and probed against the 4.204.0 compiler. Cratis/AI#743: flat composite read-model keys (ESM v27): untyped projection key blocks on root from and remove with, equality-filter lists, single-instance by blocks and per-part fixtures, with PLAY0661/PLAY0662/PLAY0268 refusals checked against the 4.204.0 compiler; Stage origin/main still refuses v27 with STAGE-ESM-016 (stage-rendering.md); Stage v4.135.0 v26 admission (Host and executor run date comparisons; renderer STAGE-ESM-046) was source-checked for this sync; no render or runtime probe. Prior: Standalone 4.201.0 and byte-identical compiler contract pinned. Cratis/AI#733: the ui profile root template, shell options, appearance and new screens default (PLAY0788-PLAY0799, quick fix for the legacy layout line, ui-profiles MCP tool, 44 tools). Cratis/AI#735: chronological Date/DateTime ordering in command conditions and command/property literal validation (ESM v26), UTC tick precision and pre-rule offset validation; then matching remains ordinal. Source-checked Screenplay v4.199.0 commands, diagnostics, interoperability and specifications documentation plus decision 0087. Stage v4.127.1 still refuses v26 with STAGE-ESM-016 (stage-rendering.md and SemanticVersionFeatures.Supports); no render/runtime probe. Cratis/AI#576: prior mechanical compiler catch-up. Language batch #717/#722/#723/#724/#720/#728/#734 teaches atomic reaction batches (v22), described payload handlers (v23), portable linear matching, ordinal text rules (v24), protected command reads (v25), diagnostic arguments and event-source invokes mappings. Facts read at Screenplay v4.198.0 and introducing tags; Stage v4.127.0 admits exact v1-v21 and v23-v25 pairs but refuses v22/v26 and mixed pairs (STAGE-ESM-016), protected reads (044), atomic mode (043) and described handlers (STAGE-IMPL-002), even Stub mode. Stage text rules execute/render; no new renderer/runtime probe or Stage pin uplift. Cratis/AI#706: application navigation regions (module inherit, extend or override), toolbar slice buttons, blueprint template references and sample data packs in cratis-screenplay-ui-composition (references/application-shell.md), with the canonical shell vector and the rejection codes PLAY0710-PLAY0722 and PLAY0740-PLAY0765. Examples moved to the executable-state rules since 4.164: translator reactions in an Automation slice beside the Translate slice (PLAY0694) and the first record of a capture key appended with `when added`. Earlier: Standalone 4.164.0 and byte-identical compiler contract pinned. Cratis/AI#663: one origin per capture (PLAY0687). #668: executable no-event/redelivery v17. #684: concept query-argument validation in every version and query-error assertions v18. #681: executable refusal branches and refusal values v19. #666: proposal summary/severity counts and exact structural source proposals. Generated-concept rules select v20 with PLAY0688/0689 proofs and derived-matches repair; generated secrets and preview strategies remain refused. Release-baseline from-esm admission reads storedName. Standalone binding is not renderer admission: Stage 4.103.0 admits v1-v17 and v19; CLI 3.62.0 bundles Screenplay 4.159.0 / Stage 4.99.0 and renders through v16. Prior evidence remains unless superseded; no new renderer, Docker or browser probe."
     },
     {
       "id": "scene",

package/package/corpus/prompts/code-review.prompt.md

@@ -7,3 +7,4 @@ description: Review a proposed change for correctness, maintainability, and secu
 
 Review the proposed change for correctness, maintainability, and security.
 Focus on actionable findings and minimize false positives.
+Read and use `.cratis/ai/rules/review-reports.md` when writing the report.

package/package/corpus/prompts/review-pr.prompt.md

@@ -21,15 +21,11 @@ Produce a structured review of a pull request against all Cratis standards.
 
 ## Output
 
-```
-## Pull Request Review — #<number>
-### Summary — <2–3 sentences>
-### Architecture & Quality — ✅ / ⚠️ / ❌   <findings>
-### Security — ✅ / ⚠️ / ❌   <findings>
-### Spec Coverage — ✅ / ⚠️ / ❌
-### Documentation — ✅ / ⚠️ / ❌
-### Overall — ✅ Approved / ⚠️ Approved with comments / ❌ Changes requested
-**Blocking** (violates a MUST): 1. …    **Suggestions**: 1. …
-```
-
-Be specific — file, line, and corrected code for every blocking issue.
+Read and use `.cratis/ai/rules/review-reports.md` before writing the report.
+Open with the PR number and a short summary. Keep one report per reviewer using
+the shared Blockers / Suggestions / Dismissed (with reason) / Verdict sections
+and Not examined line. Include specification-coverage and documentation checks
+in the relevant reviewer's scope, with any missing evidence made explicit.
+
+End with one **Combined verdict** using the shared aggregation rule, preserving
+each reviewer's findings, dismissals, and scope limits.

package/package/corpus/prompts/review-skill.prompt.md

@@ -9,6 +9,6 @@ Read [authoring-skills.md](../rules/authoring-skills.md), then apply its section
 checklist to the requested skill folder under `.cratis/ai/skills/`. Check routing
 against neighboring skills and workflow correctness against the owning product.
 
-Report blocking findings separately from suggestions, with the file and concrete
-consequence. Name any evaluation runs or verification not performed. Return findings
-first, then proposed edits; do not edit during the review.
+Read and use `.cratis/ai/rules/review-reports.md` when writing the report.
+Name any evaluation runs or verification not performed on the scope line.
+Include proposed edits with the findings; do not edit during the review.

package/package/corpus/rules/general.md

@@ -161,6 +161,7 @@ A claim is only as good as the signal behind it — a build result, a test run,
 | Reviewing or explaining a `.play` model | the **cratis-screenplay-model-review** skill |
 | Turning an existing system into a model | the **cratis-screenplay-legacy-extraction** skill |
 | Rendering or gap-filling an accepted model | the **cratis-screenplay-render-and-gap-fill** skill, then **cratis-stage-rendering-and-sandbox** for renderer facts |
+| Code, security, performance and repository-investigation review reports | `review-reports.md` |
 | Authoring or reviewing skills, rules, agents or prompts | `authoring-skills.md` |
 | Step-by-step recipes | `.cratis/ai/skills/` |
 

package/package/corpus/rules/review-reports.md

@@ -0,0 +1,67 @@
+---
+applyTo: ".cratis/ai/skills/cratis-code-review/**,.cratis/ai/skills/cratis-security-review/**,.cratis/ai/skills/cratis-performance-review/**,.cratis/ai/agents/**,.cratis/ai/prompts/**"
+paths:
+  - ".cratis/ai/skills/cratis-code-review/**"
+  - ".cratis/ai/skills/cratis-security-review/**"
+  - ".cratis/ai/skills/cratis-performance-review/**"
+  - ".cratis/ai/agents/**"
+  - ".cratis/ai/prompts/**"
+---
+
+<!-- Copyright (c) Cratis. All rights reserved. -->
+<!-- Licensed under the MIT license. See LICENSE file in the project root for full license information. -->
+
+# Shared review reports
+
+Use this report shape for code, security, performance, and repository-investigation
+reviews. Domain-specific risk labels refine findings, not the report or verdict
+vocabulary. Review the change within the declared scope, not unrelated existing debt.
+
+## Report shape
+
+Keep these sections in order, writing `None` when a section has no entries:
+
+- **Blockers** — findings that must be fixed before merge. Each names a file and
+  line or evidence reference, the problem, its concrete consequence, and a proposed
+  correction. A blocker names a consequence, not a rule number: "returns HTTP 500
+  instead of a validation error" explains harm; "violates rule 4" does not.
+- **Suggestions** — non-blocking improvements, with their benefit and any relevant
+  conditions. Do not turn a preference or a hypothetical risk into a merge gate.
+- **Dismissed (with reason)** — candidate findings considered and rejected, each
+  with the evidence or reasoning for dismissal so another reviewer need not raise
+  it again. Do not invent candidates to populate this section.
+- **Verdict** — one of the values below, scoped to the evidence actually examined.
+
+An empty Blockers section is a valid, complete review. Never manufacture a finding
+to make a review look useful. Reserve **[BLOCKING]** exclusively for
+must-fix-before-merge findings; suggestions and dismissed findings never carry it.
+
+Every review includes a **Not examined:** line naming the paths, surfaces, checks,
+and axes not examined, including anything that could not be reached. Name what was
+not measured: code-shape inspection is not a benchmark, a build is not behavioral
+proof, and an unexamined surface is not verified. State `None` only when the entire
+declared scope was examined; otherwise give concrete limits and remaining checks.
+
+## Verdict vocabulary
+
+| Verdict | Meaning |
+| --- | --- |
+| **Approved** | No blockers or suggestions within the examined scope; required review checks are complete. |
+| **Approved with suggestions** | No blockers; non-blocking suggestions remain and required review checks are complete. |
+| **Changes requested** | At least one blocker must be corrected before merge. |
+| **Incomplete** | No confirmed blocker, but missing or inconclusive required evidence prevents approval. |
+
+Skipped optional axes belong on the Not examined line and do not alone prevent a
+scoped approval. Missing required evidence does. When blockers and evidence gaps
+coexist, use Changes requested and record the gaps on the Not examined line; never
+reinterpret a failed or blocked gate as passing.
+
+When combining reviews, retain one report per reviewer with the shared sections
+and scope line, then give one combined verdict. Any blocker means Changes requested;
+otherwise any Incomplete review means Incomplete; otherwise any remaining suggestion
+means Approved with suggestions; otherwise use Approved. Do not drop dismissals or
+scope limits when combining reports.
+
+When a workflow requires a typed review envelope, preserve its schema and express
+these sections, verdict meanings, and scope limits through its existing fields.
+Do not append a competing Markdown report or invent envelope fields.

package/package/corpus/skills/cratis-code-review/SKILL.md

@@ -169,28 +169,13 @@ degradations a reviewer can see without measuring:
 
 ## Step 7 — Report
 
-Open with one line:
+Read and use `.cratis/ai/rules/review-reports.md` when writing the report.
 
-> **Review result: Approved / Approved with comments / Changes requested**
-
-Then, per file:
-
-```
-### <file path>
-
-**[BLOCKING]** Line N: `problematic code`
-Because: <the consequence, not the rule number>
-Fix:
-<corrected code>
-```
-
-Close with what passed and what must change. Two rules make the report usable:
-
-- **A blocking finding names a consequence.** "Violates the style guide" is not
-  a reason. "Throws on a recoverable path, so the caller sees a 500 instead of a
-  validation error" is.
-- **Say what you did not review.** A report listing only findings reads as if
-  everything was checked. Name the files, the paths, and the axes you skipped.
+Correctness regressions, broken contracts, and missing specification coverage
+that leaves changed behavior unverified belong in Blockers when they require
+correction before merge. Style preferences and maintainability improvements
+without such a consequence belong in Suggestions. Apply the shared verdict
+vocabulary to those findings.
 
 ## What breaks
 

package/package/corpus/skills/cratis-code-review/verification.json

@@ -0,0 +1,10 @@
+{
+  "skill": "cratis-code-review",
+  "input": "Report a code review with no blockers and one non-blocking maintainability suggestion.",
+  "fixtures": [],
+  "assertions": [
+    { "kind": "skill-contains", "value": ".cratis/ai/rules/review-reports.md" },
+    { "kind": "skill-contains", "value": "Correctness regressions, broken contracts" },
+    { "kind": "skill-contains", "value": "Style preferences and maintainability improvements" }
+  ]
+}

package/package/corpus/skills/cratis-performance-review/SKILL.md

@@ -121,25 +121,23 @@ behavior this file does not already state.
 
 ## Step 6 — Report
 
-Open with one line:
+Read and use `.cratis/ai/rules/review-reports.md` when writing the report.
+Keep the performance risk label on each finding:
 
-> **Performance review: No issues / Minor findings / Blocking issues found**
-
-Group findings by the section that produced them, and classify each:
-
-| Risk | Meaning |
+| Risk | Shared classification |
 | --- | --- |
-| **High** | Measurable degradation at moderate load — fix before merge |
-| **Medium** | Degrades under load or as data grows |
-| **Low** | Minor inefficiency |
+| **High** | Blockers: degradation at moderate load requiring correction before merge |
+| **Medium** | Suggestions: degradation under load or as data grows |
+| **Low** | Suggestions: minor inefficiency |
 
-Close with a per-section summary table.
+Use the shared verdict vocabulary, not a separate performance verdict. If a
+scale-dependent degradation must be corrected before merge, classify it as High
+and state the relevant scale rather than leaving a blocker under Medium.
 
 **Say what the finding costs and at what scale.** "This is slow" is not
 actionable; "this scans the whole collection on every page load, so it is fine
-at hundreds of rows and not at tens of thousands" is. And **name what you did
-not measure** — a review of code shape is not a benchmark, and reporting it as
-one overstates the evidence.
+at hundreds of rows and not at tens of thousands" is. Distinguish measured cost
+from code-shape inference; use the shared scope line to name unmeasured behavior.
 
 ## What breaks
 

package/package/corpus/skills/cratis-performance-review/verification.json

@@ -0,0 +1,12 @@
+{
+  "skill": "cratis-performance-review",
+  "input": "Report performance risks from code inspection without presenting unmeasured cost as a benchmark.",
+  "fixtures": [],
+  "assertions": [
+    { "kind": "skill-contains", "value": ".cratis/ai/rules/review-reports.md" },
+    { "kind": "skill-contains", "value": "**High** | Blockers:" },
+    { "kind": "skill-contains", "value": "**Medium** | Suggestions:" },
+    { "kind": "skill-contains", "value": "**Low** | Suggestions:" },
+    { "kind": "skill-contains", "value": "Distinguish measured cost" }
+  ]
+}

package/package/corpus/skills/cratis-screenplay-model-authoring/SKILL.md

@@ -11,24 +11,23 @@ Read [preferred syntax](../cratis-screenplay-toolchain/references/preferred-synt
 Prefer the Screenplay MCP tools to text/regex edits: the compiler owns declaration,
 reference, hierarchy and source evidence for the declarative document set.
 
-Screenplay remains experimental. **Valid source is not necessarily executable.**
-It does not generate or run an application; Stage owns rendering/runtime admission.
-When selecting construct syntax or distinguishing source validity from execution, read the [language reference](references/language-reference.md) for constructs,
-the executable profile and a complete compiled model.
+**Valid source is not necessarily executable.** Stage owns rendering/runtime
+admission. Read the [language reference](references/language-reference.md) for
+construct syntax, source-versus-execution states and a complete compiled model.
 
-For screens: discover UI schemas, propose/apply with revisions, then pass the
-same model root or workspace export to all checks. Workflow:
-`references/screen-authoring-workflow.md`; syntax/support:
-`cratis-screenplay-ui-composition`.
+For screens, read `references/screen-authoring-workflow.md`; use the
+same model root or workspace export for all checks. Syntax: `cratis-screenplay-ui-composition`.
 
 Record open modeling questions as `question` notes in committed
 `.screenplay/notes.json`, not chat or `description` text. Never put secrets or
 personal data in notes. Read [model notes](references/model-notes.md) when
 listing, recording or resolving questions: `list-model-notes`,
 `propose-model-notes`, `read-proposal view=notes`, refs and orphan review.
-Prefer dotted split-model targets; inspect `substitutions`, also for reanchor,
-and disclose broader owners. The reference covers typed `parts` targets from
-`open-workspace.applicationIdentity`.
+Application, Module, Feature and Slice notes anchor before binding; members
+still need binding and otherwise substitute their own slice. Inspect
+`containerIdentities` in `open-workspace` / `workspace-state` for missing or
+ambiguous identities; fix parse/placement errors first. Read the notes reference
+for refusals, `ambiguous: true`, typed targets and every `substitutions` entry.
 
 ## Choosing a strategy
 
@@ -61,8 +60,8 @@ explanatory Markdown belongs in repository documentation.
 is owned by the Cratis CLI, which preserves other servers and user configuration.
 
 The CLI-bundled MCP can be older than the standalone tool: discover schemas.
-Read [MCP loop](references/mcp-loop.md) for launch options. Use the supported
-channel, not another global tool, Docker or copied managed configuration.
+Read [MCP loop](references/mcp-loop.md) for supported launch channels; do not
+substitute a global tool, Docker or copied managed configuration.
 
 If MCP is unavailable, report it; regex edits are not compiler-validated AST
 editing. Existing standalone `screenplay mcp` users may retain that entry point.
@@ -93,9 +92,8 @@ editing. Existing standalone `screenplay mcp` users may retain that entry point.
    outlet declarations that provide context. A component binding with no traced
    data source is not a shortcut; fix the model source.
 
-Keep reads scoped to the relevant module, feature, slice or document. Do not
-request a whole merged AST when a bounded declaration/property query answers the
-question. Size-limit refusals require narrower reads, not truncation.
+Scope reads to the relevant container/document, not the whole merged AST.
+Size-limit refusals require narrower reads, not truncation.
 
 ## Application modes and described handler intent
 
@@ -111,11 +109,10 @@ Read [comparison sources](references/mcp-tools.md#semantic-revision-comparison)
 
 ## Make one coherent proposal
 
-**One edit strategy.** Discover what the server offers. Prefer typed,
-identity-preserving operations (`propose-rename`, `propose-repair`,
-`propose-extract-inline-event`, `propose-ast`). A bounded text edit is fine only for
-edits that leave catalog addresses unchanged (descriptions, rule and expression bodies, mappings
-between existing members), never a way around an MCP refusal. When `.screenplay/identities.json`
+**One edit strategy.** Prefer discovered identity-preserving operations
+(`propose-rename`, `propose-repair`, `propose-extract-inline-event`, `propose-ast`).
+Bounded text edits must leave catalog addresses unchanged (descriptions, rule
+bodies, existing-member mappings), never a way around an MCP refusal. When `.screenplay/identities.json`
 exists, adding, removing or renaming a declaration, command or read-model property, query,
 query argument or specification goes through MCP, and an `id` pin is not enough for a rename or move. A request naming
 a rename, move or removal is the approval: do not ask again at `apply`. Without MCP, text-rename
@@ -131,9 +128,10 @@ Others send an edit request ([MCP loop](references/mcp-loop.md)).
    identity state. `read-workspace` locates document identities.
 2. `read-ast` returns original occurrence handles and existing semantic IDs.
    Query `syntax-schema` for exact node members before constructing typed input.
-3. Prefer `propose-rename` for supported logical renames: it coordinates fragments,
-   repairs proven references and preserves assigned identities. Never substitute
-   global string replacement for an explicit refusal.
+3. Prefer `propose-rename` and `propose-move`: they carry identities and notes
+   even on unbound models. Manual `propose-ast` / `propose-source` renames need
+   `semanticRenames`; removal needs retirement and reports `orphanedNotes`.
+   Never substitute global string replacement for an explicit refusal.
 4. Prefer `propose-property` for property add/rename/remove, not hand-composed
    `propose-ast` batches. Inspect the chain and never guess past a refusal:
    [property links](references/property-links.md). Otherwise use `propose-source`
@@ -152,20 +150,17 @@ Others send an edit request ([MCP loop](references/mcp-loop.md)).
    identity-state change through `workspace-state`. Review `orphanedNotes` on
    source proposals; reanchor or resolve affected questions before applying
    ([notes and orphan impact](references/model-notes.md#source-proposals-can-orphan-notes)).
-7. Run `run-specifications` with `proposalId` before applying. Record V4 separately: PLAY0285
-   (impossible `then`) unbinds the whole model. Paging and read-only candidate semantics:
-   [MCP tool guide](references/mcp-tools.md#run-reference-specifications).
-
-   Requires Screenplay 4.145.0 or later (`screenplay --version`) for `proposalId`; earlier servers run only the current workspace.
+7. Run `run-specifications` with `proposalId` before applying; record V4 separately.
+   PLAY0285 unbinds the whole model. Read the [MCP tool guide](references/mcp-tools.md#run-reference-specifications)
+   for candidate paging and the required version.
 8. `apply` only the reviewed server-produced proposal within the user's requested
    change. The proposal ID and before revisions are required; stale state rejects.
-   When the user already requested apply, do it after checks without asking again;
-   otherwise show the proposal and ask once.
+   Apply after checks if requested; otherwise show the proposal and ask once.
 9. When the host draws views, `visualize-model` shows the board. It follows the files
    on disk while open, so after an apply do not re-request it; just say what changed.
 
-Handles are revision-bound occurrences, not durable IDs. Modules/features can
-span fragments; one header edit may not change all. After apply, fetch fresh handles/revisions.
+Handles are revision-bound, not durable IDs. Modules/features span fragments;
+after apply fetch fresh handles/revisions.
 
 On refusal, use `failureKind`, never message text ([failures/limits](references/mcp-loop.md#failures-use-failurekind-never-message-text)).
 After revision/disk/identity drift, reopen and re-propose. For `ApplyOutcomeUnknown`
@@ -188,6 +183,8 @@ Use `recommend-layout` for options and review an `expand-layout` proposal; layou
 
 ## Preserve state and recover explicitly
 
+Fix binding errors through MCP proposals, not outside MCP: reopening after an
+external fix can require reconciliation of a persisted partial catalog.
 Commit `.screenplay/identities.json` with the model; only `apply` writes it. Never delete or overwrite identity state, mint IDs on restart, or text-rename identity-affecting declarations. A pending journal blocks normal work: inspect `workspace-state` and use `recover-workspace` only for the identified interrupted operation. Only `apply` / `recover-workspace` write source/catalog. `readiness.authoringAccepted` says the source is valid Screenplay; `executableReady` is separate. Read [references/state-and-recovery.md](references/state-and-recovery.md) for root conflicts, journals and readiness.
 
 ## Code attachments
@@ -199,8 +196,8 @@ are not behavioral evidence.
 
 ## Verify and report honestly
 
-- Require zero source errors and investigate every warning.
-- Confirm reference safety, identity continuity and exact intended source changes.
+- Require zero source errors; investigate warnings, reference safety, identity
+  continuity and exact intended changes.
 - Report which of the four states you checked: **parsed**, **bound**,
   **reference-executed**, **target-executed**. When distinguishing source validity from execution, read the
   [language reference](references/language-reference.md#source-validity-is-not-execution);
@@ -209,9 +206,8 @@ are not behavioral evidence.
   clean run is not a bound or executable result.
 - Never drop or stub source contracts to bind; the bundled compiler and renderer can be older than the standalone tool. Read [references/language-reference.md](references/language-reference.md) for the ESM version at which each construct binds.
 
-- Distinguish authoring acceptance from `executableReady`; unsupported backend
-  capabilities are not a reason to drop source constructs or invent stubs.
-- If execution is intended, validate with the owning downstream runtime as well.
+- Unsupported capabilities never justify dropping constructs or inventing stubs.
+  Validate intended execution with the owning downstream runtime.
 - Model rejection cases as specifications; assertion presence is not execution.
 - Check installed `tools/list`/schemas rather than assuming a remembered tool count.
 
@@ -221,9 +217,9 @@ The ordinary CLI remains useful for whole-folder validation:
 cratis screenplay validate <model-folder> --warnings-as-errors
 ```
 
-Record screen MCP transcripts in `.ai-work/`; render/runtime checks must use the
-same source, never an app that silently drops authored UI. Use the Screenplay-owned canonical
-corpus fixture path instead of copying available `.play` fixtures here.
+Keep screen transcripts in `.ai-work/`; check the same source, never an app that
+silently drops authored UI. Use the Screenplay-owned canonical
+corpus fixture path instead of copying fixtures here.
 
 Never invent syntax or capabilities.
 
@@ -235,10 +231,10 @@ Never invent syntax or capabilities.
 | Commands, events, validation and concurrency | `cratis-screenplay-command-surface` |
 | Projections and reducers | `cratis-screenplay-projections` |
 | Read models, queries and screens | `cratis-screenplay-read-surface` |
-| Layouts, forms, contributions, navigation regions, slice buttons, template references, sample data, component bindings, toolbars, outlets, themes and localization | `cratis-screenplay-ui-composition` |
+| UI composition, bindings, navigation and themes | `cratis-screenplay-ui-composition` |
 | Captures, reactions and triggers | `cratis-screenplay-captures-and-reactions` |
 | Behavioral examples and assertions | `cratis-screenplay-specifications` |
 | Rendering/running an admitted model | `cratis-stage-rendering-and-sandbox` |
-| Lifecycle, verdicts V1 to V5 and the model-first decision | `cratis-screenplay-modeling-lifecycle` |
-| Compiler, CLI and MCP versions, diagnostics, capability tables | `cratis-screenplay-toolchain` |
+| Lifecycle and model-first decision | `cratis-screenplay-modeling-lifecycle` |
+| Compiler, CLI, MCP and diagnostics | `cratis-screenplay-toolchain` |
 | Event-model diagrams rather than .play source | `cratis-event-model-diagram` |

package/package/corpus/skills/cratis-screenplay-model-authoring/references/mcp-loop.md

@@ -281,9 +281,14 @@ Requires Screenplay 4.89.0 or later (`screenplay --version`) for `identityMigrat
 
 ## Identity state (`.screenplay/identities.json`)
 
-- `apply` persists identities with the `.play` changes (probed: the file survives
-  restarts without `export-workspace`). `open-workspace` and read-only commands
-  never create it. Commit both.
+- `apply` persists identities with source or notes-only changes; they survive
+  restarts without `export-workspace`. `open-workspace` and read-only commands
+  never create the file. Commit identity state with the model and notes.
+- Containers anchor before binding when all documents parse and place; inspect
+  `containerIdentities` in `open-workspace` / `workspace-state`. Fix binding
+  through MCP proposals, not external edits after persisting a partial catalog.
+  Read [state and recovery](state-and-recovery.md) for the exact unbound reopen
+  exception and [model notes](model-notes.md) for targeting refusal reasons.
 - A model only ever edited as text has **no persisted identities** until the first
   `apply`. Whether a first apply is the intended initialization is not documented
   beyond "after the first apply, keep `.screenplay/identities.json`"; ask before

package/package/corpus/skills/cratis-screenplay-model-authoring/references/mcp-tools.md

@@ -127,6 +127,32 @@ A folder is one application; a file selects only itself and its imports.
 
 ## Whole-source authoring
 
+Application notes already anchor before binding; Module, Feature and Slice
+identities materialize from the authoring hierarchy when every document parses
+and places. Binding keeps those IDs. Read `containerIdentities` in
+`open-workspace` / `workspace-state`: `complete`, `containers` (`address`,
+`reason`, `assigned`) and `documents` (`path`, `reason`). Reasons are `ambiguous`,
+`idCollision`, `incomplete`, `unparsed` and `unplaced`; incomplete documents stop
+all new assignments, not just their own. Fix parse/placement errors first.
+Notes tools refuse unavailable targets and descendants with the same reasons in
+all forms. Existing notes on ambiguous containers remain resolved with
+`ambiguous: true`; inspect them unfiltered or by existing `semanticId`.
+Unidentified members still need binding and substitute their own slice in
+`substitutions`, never silently promote to a feature/module. Details:
+[model notes](model-notes.md#anchors-and-independent-state).
+
+Requires Screenplay 4.213.0 (`screenplay --version`) for pre-binding container
+identities and reporting; upgrade older servers before relying on direct
+container anchoring.
+
+`propose-rename` and `propose-move` preserve assigned container identities and
+notes on unbound models, including before first binding. Manual `propose-ast` /
+`propose-source` renames need `semanticRenames`, removals need
+`retiredSemanticAddresses` and report `orphanedNotes`. Fix binding errors through
+MCP proposals so reopening does not require reconciliation after an external fix.
+Opening computes identities in memory only; even notes-only `apply` can persist
+them with notes under the same rollback journal.
+
 `propose-source` takes `expectedRevision`, `expectedCatalogRevision`, explicit
 `formatting` and `documents`. Default `validation: "Authoring"` accepts syntax-only
 models; `"Executable"` requires binding and never falls back. Default

package/package/corpus/skills/cratis-screenplay-model-authoring/references/model-notes.md

@@ -63,11 +63,38 @@ a Module (replace the Application key with that response's value):
 }
 ```
 
-A typed address needs an existing catalog identity; it refuses when none exists.
-Use the construct's current source handle instead. A target without an identity
-lands on the nearest identified slice, feature, module or application. On an
-unbound model, even a Slice can lack an identity and fall back to Application;
-opening the workspace does not guarantee container identities.
+Application notes anchor as `{ application: true }` before binding. Modules,
+nested Features and Slices gain deterministic catalog identities from the
+authoring hierarchy before the model binds, provided every document parses and
+places. Dotted, typed and source-handle targets anchor directly to those
+containers without substitution. Binding preserves their existing IDs and
+origins; never calculate an ID client-side.
+
+Commands, events, read models, projections, queries, specifications, reactions,
+captures and properties still need a bound model for their own identities. Until
+then, their notes land on their own slice, not the feature or module, and are
+reported in `substitutions`. Name the intended member in the text.
+
+Requires Screenplay 4.213.0 (`screenplay --version`) for pre-binding container
+identities and identity-problem reporting. Older servers can broaden container
+notes to an identified ancestor; upgrade before relying on direct anchoring.
+
+Inspect `containerIdentities` from `open-workspace` and `workspace-state` when
+identities are missing. It contains `complete`, `containers` entries with
+`address`, `reason`, `assigned`, and `documents` entries with `path`, `reason`.
+Container reasons are `ambiguous`, `idCollision` or `incomplete`; document reasons
+are `unparsed` or `unplaced`. Fix parse and import-placement errors first:
+**no new identities are assigned anywhere** until every document parses and
+places, even in otherwise valid documents. Existing assignments are retained.
+Unavailable containers and descendants refuse new note targeting with the same
+reason in every form, including semantic-ID anchors; do not bypass a refusal by
+requesting a broader owner. Repeated Module/Feature fragments count as one logical
+declaration; duplicate Slices do not.
+
+A container duplicated outside MCP keeps its identity and notes. Existing notes
+on it or its descendants stay resolved with `ambiguous: true`, not orphaned.
+Read them unfiltered or by their existing `semanticId`; new targeting on the
+ambiguous container or its descendants is refused.
 
 Always inspect `substitutions` for both `add` and `reanchor`, even when reanchor
 leaves the note unchanged. Each entry has the requested `target`, resolved
@@ -82,8 +109,12 @@ reporting. Older servers can refuse split targets, omit that field or silently
 broaden the anchor; use a catalog address/current handle and inspect the notes
 review's actual anchor, or upgrade before relying on these responses.
 
-Notes do not change source, workspace/catalog/semantic revisions, executable
-model bytes or compiler verdicts. Their own `notesRevision` is `nrev1:` plus the
+Notes do not change source, executable model bytes or compiler verdicts.
+Opening or proposing an unbound workspace can materialize container assignments
+in memory and advance its catalog revision. Opening never writes them; a
+notes-only `apply` can persist them in `.screenplay/identities.json` under the
+same journal as the sidecar. Rollback restores both the notes and exact earlier
+identity state. Notes retain an independent revision; their `notesRevision` is `nrev1:` plus the
 lowercase SHA-256 of canonical bytes; `nrev1:absent` is not an empty document.
 The file header uses `schema: "cratis.screenplay.notes"`, `schemaVersion: 1` and
 `applicationIdentity` in the catalog's representation. The server writes stable
@@ -205,12 +236,27 @@ stops being adequate.
 
 ## Source proposals can orphan notes
 
+Prefer `propose-rename` and `propose-move`: identities and notes follow containers
+on unbound models as on bound ones, including before their first binding. A
+manual `propose-ast` or `propose-source` rename needs explicit `semanticRenames`;
+removal needs `retiredSemanticAddresses`. Retirement is not a substitute for a
+rename when continuity is intended.
+
+Fix binding errors through MCP proposals. After a partial catalog is persisted,
+fixing binding outside MCP can add bound identities on reopen and require
+reconciliation; never discard state to bypass it.
+
 Review `orphanedNotes` IDs and `notes` status/reason/count on source, AST, rename,
 move and property proposals and their reviews. Retirement leaves a computed
 orphan with null current address and `orphanReason: "unknown"`; notes are never
 silently deleted. `orphanedNotes: null` with unreadable notes means unknown
 impact, not `[]`.
 
+Re-adding a retired address recreates its deterministic identity only when source
+is complete and unambiguous. Orphaned notes resolve again only for their exact
+former ID. An identity previously carried there by rename or assigned externally
+may differ; explicitly reanchor those notes.
+
 Before applying a source proposal, review each affected question: reanchor to a
 surviving element, or resolve with evidence and deliberately decide whether to
 retain its orphaned history. Resolution alone does not restore an anchor. Remove

package/package/corpus/skills/cratis-screenplay-model-authoring/references/state-and-recovery.md

@@ -10,6 +10,28 @@ Commit `.screenplay/identities.json` with the model. Only `apply` writes it;
 overwrite conflicting identity state, silently mint IDs on restart, or text-rename
 identity-affecting declarations in a model that has it.
 
+An unbound workspace materializes collision-free deterministic Module, Feature
+and Slice identities in memory when every document parses and places. Application
+notes already anchor before binding. Opening never writes state; `apply`,
+including a notes-only apply, persists these assignments. Binding preserves their
+IDs and origins, and rename/move proposals carry identities and notes before
+first binding. Read `containerIdentities` from `open-workspace` / `workspace-state`
+and the [notes guidance](model-notes.md#anchors-and-independent-state) for
+ambiguity, collision and incomplete-source refusals.
+
+Reopening persisted unbound state admits only deterministic container additions:
+every document must parse and place; every previous assignment must still be
+present in source; earlier IDs, origins, event revisions, document mappings and
+application metadata must be unchanged. Other drift still requires reconciliation.
+A supplied `workspaceJson` cannot replace different persisted identity authority.
+Fix binding errors through MCP proposals: an external fix after a partial catalog
+was persisted can add bound identities on reopen and require reconciliation.
+Never delete state to bypass that refusal.
+
+A notes apply journals the sidecar and any new container identities together;
+rollback restores exact earlier identity bytes as well as notes, including an
+earlier catalog without those containers.
+
 Default root discovery preserves ancestor identity state and journals. Inspect
 `rootBindingConflict` in `open-workspace`/`workspace-state` when several state roots
 compete; do not delete state or mint replacement identities. To recover a competing

package/package/corpus/skills/cratis-screenplay-model-authoring/verification.json

@@ -40,7 +40,23 @@
     { "kind": "skill-contains", "value": "`applicationIdentity` returned by `open-workspace`", "file": "references/model-notes.md" },
     { "kind": "skill-contains", "value": "Repeated Module/Feature headers", "file": "references/model-notes.md" },
     { "kind": "skill-contains", "value": "Always inspect `substitutions` for both `add` and `reanchor`", "file": "references/model-notes.md" },
-    { "kind": "skill-contains", "value": "even a Slice can lack an identity", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "before the model binds", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "Application, Module, Feature and Slice notes anchor before binding" },
+    { "kind": "skill-contains", "value": "Binding preserves their existing IDs and", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "their notes land on their own slice, not the feature or module", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "`containerIdentities`", "file": "references/mcp-tools.md" },
+    { "kind": "skill-contains", "value": "`ambiguous`, `idCollision` or `incomplete`", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "`unparsed` or `unplaced`", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "**no new identities are assigned anywhere**", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "reason in every form, including semantic-ID anchors", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "stay resolved with `ambiguous: true`, not orphaned", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "notes on unbound models, including before first binding", "file": "references/mcp-tools.md" },
+    { "kind": "skill-contains", "value": "`semanticRenames`", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "`retiredSemanticAddresses`", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "Fix binding errors through MCP proposals", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "rollback restores exact earlier identity bytes as well as notes", "file": "references/state-and-recovery.md" },
+    { "kind": "skill-contains", "value": "Orphaned notes resolve again only for their exact", "file": "references/model-notes.md" },
+    { "kind": "skill-contains", "value": "Requires Screenplay 4.213.0", "file": "references/model-notes.md" },
     { "kind": "skill-contains", "value": "older servers miss the read-only denial for SPEC004 and count it for SPEC006", "file": "references/mcp-tools.md" },
     { "kind": "skill-contains", "value": "`anchor`", "file": "references/model-notes.md" },
     { "kind": "skill-contains", "value": "`scope`", "file": "references/model-notes.md" },

package/package/corpus/skills/cratis-screenplay-toolchain/references/screenplay-contract.version

@@ -1 +1 @@
-4.212.4
+4.213.0

package/package/corpus/skills/cratis-security-review/SKILL.md

@@ -129,21 +129,18 @@ command's properties as well as grepping them.
 
 ## Step 7 — Report
 
-Open with one line:
+Read and use `.cratis/ai/rules/review-reports.md` when writing the report.
+Keep the security risk label on each finding:
 
-> **Security review: No issues / Low-risk findings / Blocking issues found**
-
-Group findings by the section that produced them, and classify each:
-
-| Risk | Meaning |
+| Risk | Shared classification |
 | --- | --- |
-| **Critical** | Must be fixed before merge |
-| **Medium** | Should be fixed soon; state what makes it not-critical |
-| **Low** | Fix when convenient |
+| **Critical** | Blockers: exploitable exposure requiring correction before merge |
+| **Medium** | Suggestions: conditional exposure; state what makes it non-critical |
+| **Low** | Suggestions: defense-in-depth improvement |
 
-Close with a per-section summary table, and **name what you did not review** —
-the paths, the surfaces, and the axes out of scope. A security report listing
-only findings reads as a clean bill of health for everything it never opened.
+Use the shared verdict vocabulary, not a separate security verdict. If a
+conditional exposure must be corrected before merge, classify it as Critical
+and explain the exploit conditions rather than leaving a blocker under Medium.
 
 ## What breaks
 

package/package/corpus/skills/cratis-security-review/verification.json

@@ -0,0 +1,11 @@
+{
+  "skill": "cratis-security-review",
+  "input": "Report security risks using the shared report and distinguish conditional exposure from a merge blocker.",
+  "fixtures": [],
+  "assertions": [
+    { "kind": "skill-contains", "value": ".cratis/ai/rules/review-reports.md" },
+    { "kind": "skill-contains", "value": "**Critical** | Blockers:" },
+    { "kind": "skill-contains", "value": "**Medium** | Suggestions:" },
+    { "kind": "skill-contains", "value": "**Low** | Suggestions:" }
+  ]
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cratis/pi",
-  "version": "7.78.0",
+  "version": "7.80.0",
   "description": "Configuration-aware Cratis AI integration for Pi",
   "type": "module",
   "files": [