mzored · Oct 20, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,14 @@
 
 All notable changes to SkipHow 2.x and later appear in this file. Earlier release notes remain available on [GitHub Releases](https://github.com/mzored/SkipHow/releases).
 
+## 7.0.2 (2026-10-21)
+
+### Attribution matches the shipped files
+
+- The third-party notice said the kernel adapts the decision frontier from Matt Pocock's `grilling` skill. The frontier now lives in the `product` reference; the kernel keeps only a recommended answer for every owner question, all asked in one round. The notice now says so.
+- `SOURCES.json` was checked against the upstream files at the pinned revision, one by one. It now credits the four workflows that carry adapted ideas: `skiphow-bug` from `diagnosing-bugs`, `skiphow-longrun` from `implement-spec`, `skiphow-plan` from `to-tickets` and `grilling`, and `skiphow-simplify` from `improve-codebase-architecture`. It drops `setup-matt-pocock-skills`, `wizard`, and the `writing-for-agents` skill-mechanics file, because no shipped text carries an idea from them any longer. The upstream licence, copyright, and inspected revision are unchanged.
+- This is a patch release. Runtime instructions are unchanged.
+
 ## 7.0.1 (2026-10-18)
 
 ### Inherited rules and tooling are the CTO's to judge

diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-7.0.1
+7.0.2
diff --git a/evals/cases.json b/evals/cases.json
@@ -1,6 +1,6 @@
 {
   "corpus_version": 4,
-  "package_under_test": "7.0.1",
+  "package_under_test": "7.0.2",
   "purpose": "Synthetic cases for three separate instruments: activation, forced-activation CTO behavior, and host smoke. Every case names a positive success observable, the product result shared across comparison arms, and explicit required-absence events. Nothing here has been run.",
   "not_a_gate": "No model run gates a pull request. python scripts/check.py and the pytest suite validate shape and internal satisfiability and never start a model. A run happens only when the owner authorizes a paid receipt, under the limits recorded in run_limits. A deterministic check passing is never evidence of behavior.",
   "evidence_labels": {

diff --git a/evals/cto-cases.json b/evals/cto-cases.json
@@ -1,6 +1,6 @@
 {
   "instrument": "forced_activation_behavior",
-  "package_under_test": "7.0.1",
+  "package_under_test": "7.0.2",
   "suite_status": "not_run",
   "minimum_coverage": {
     "case_ids": [

diff --git a/evals/host-smoke.json b/evals/host-smoke.json
@@ -1,6 +1,6 @@
 {
   "instrument": "host_smoke",
-  "package_under_test": "7.0.1",
+  "package_under_test": "7.0.2",
   "scope": "external_candidate_receipts",
   "checks": {
     "clean_install": {

diff --git a/plugins/skiphow/.claude-plugin/plugin.json b/plugins/skiphow/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
 {
   "name": "skiphow",
-  "version": "7.0.1",
+  "version": "7.0.2",
   "description": "Adaptive virtual CTO for founders and product owners using Claude Code or Codex. Describe the product outcome; SkipHow owns the technical lifecycle through verified completion.",
   "author": {
     "name": "mzored",

diff --git a/plugins/skiphow/.codex-plugin/plugin.json b/plugins/skiphow/.codex-plugin/plugin.json
@@ -1,6 +1,6 @@
 {
   "name": "skiphow",
-  "version": "7.0.1",
+  "version": "7.0.2",
   "description": "Adaptive virtual CTO for founders and product owners using Claude Code or Codex. Describe the product outcome; SkipHow owns the technical lifecycle through verified completion.",
   "author": {
     "name": "mzored",

diff --git a/plugins/skiphow/SOURCES.json b/plugins/skiphow/SOURCES.json
@@ -21,17 +21,14 @@
             "skills/engineering/prototype/UI.md",
             "skills/engineering/research/SKILL.md",
             "skills/engineering/resolving-merge-conflicts/SKILL.md",
-            "skills/engineering/setup-matt-pocock-skills/SKILL.md",
             "skills/engineering/tdd/SKILL.md",
             "skills/engineering/tdd/mocking.md",
             "skills/engineering/tdd/tests.md",
             "skills/engineering/to-tickets/SKILL.md",
             "skills/engineering/triage/AGENT-BRIEF.md",
             "skills/engineering/wayfinder/SKILL.md",
-            "skills/engineering/wizard/SKILL.md",
             "skills/in-progress/implement-spec/SKILL.md",
             "skills/productivity/grilling/SKILL.md",
-            "skills/productivity/writing-for-agents/SKILL-MECHANICS.md",
             "skills/productivity/writing-for-agents/SKILL.md"
           ],
           "files": [
@@ -45,6 +42,43 @@
             "references/testing.md",
             "references/tracked-work.md"
           ]
+        },
+        {
+          "skill": "skiphow-bug",
+          "source_paths": [
+            "skills/engineering/diagnosing-bugs/SKILL.md"
+          ],
+          "files": [
+            "SKILL.md"
+          ]
+        },
+        {
+          "skill": "skiphow-longrun",
+          "source_paths": [
+            "skills/in-progress/implement-spec/SKILL.md"
+          ],
+          "files": [
+            "SKILL.md"
+          ]
+        },
+        {
+          "skill": "skiphow-plan",
+          "source_paths": [
+            "skills/engineering/to-tickets/SKILL.md",
+            "skills/productivity/grilling/SKILL.md"
+          ],
+          "files": [
+            "SKILL.md"
+          ]
+        },
+        {
+          "skill": "skiphow-simplify",
+          "source_paths": [
+            "skills/engineering/improve-codebase-architecture/SKILL.md"
+          ],
+          "files": [
+            "SKILL.md"
+          ]
         }
       ]
     }

diff --git a/plugins/skiphow/THIRD_PARTY_NOTICES.md b/plugins/skiphow/THIRD_PARTY_NOTICES.md
@@ -2,7 +2,7 @@
 
 SkipHow includes original adaptations of selected ideas from [`mattpocock/skills`](https://github.com/mattpocock/skills) at commit `6654f6b60cd9d5be8b54c6fafe44346dabeb3b76`.
 
-The eight adapted SkipHow references are `delegation`, `diagnosis`, `integration`, `product`, `review`, `technical-design`, `testing`, and `tracked-work`. Version 3.0.0 consolidated twenty-three references; version 7.0.0 rewrote them in plain language, split the former `verification` reference into `testing` and `review`, and folded the original `operations` playbook into `integration`, `testing`, `diagnosis`, and `tracked-work`. The owner kernel `SKILL.md` adapts the decision-frontier idea from the upstream `grilling` skill. SkipHow rewrites and narrows the source material for autonomous use by product owners. It does not vendor the upstream skill files. Exact source paths and adapted destination files are recorded in [`SOURCES.json`](SOURCES.json).
+The eight adapted SkipHow references are `delegation`, `diagnosis`, `integration`, `product`, `review`, `technical-design`, `testing`, and `tracked-work`. Version 3.0.0 consolidated twenty-three references; version 7.0.0 rewrote them in plain language, split the former `verification` reference into `testing` and `review`, and folded the original `operations` playbook into `integration`, `testing`, `diagnosis`, and `tracked-work`. The owner kernel `SKILL.md` keeps short forms of some of these ideas, including a recommended answer for every owner question, all asked in one round, from the upstream `grilling` skill. The decision frontier itself from `grilling`, asking only what can be put correctly now and asking again after the answers, lives in `product`. The `skiphow-bug`, `skiphow-longrun`, `skiphow-plan`, and `skiphow-simplify` workflows also carry adapted ideas. SkipHow rewrites and narrows the source material for autonomous use by product owners. It does not vendor the upstream skill files. Exact source paths and adapted destination files are recorded in [`SOURCES.json`](SOURCES.json).
 
 The upstream work is licensed under the MIT License:
 

diff --git a/site/evidence/index.html b/site/evidence/index.html
@@ -56,11 +56,11 @@ <h1>Claims stop where the receipts stop.</h1>
       </div>
     </section>
 
-    <section class="section" aria-labelledby="matrix-title" data-observed-package-series="2.x" data-current-package="7.0.1" data-current-observed-scenarios="0">
+    <section class="section" aria-labelledby="matrix-title" data-observed-package-series="2.x" data-current-package="7.0.2" data-current-observed-scenarios="0">
       <div class="shell">
         <p class="section-label">01 &middot; Historical observations</p>
         <h2 id="matrix-title">What controlled 2.x runs showed.</h2>
-        <p>Historical observations below: 2.x only. Current package: 7.0.1. Retained current-package CTO scenarios with Observed receipts: 0 of 12. Eight historical 4.0.1 Claude run records remain incomplete. Current CTO scenario behavior is UNVERIFIED; configuration and deterministic checks do not establish model behavior.</p>
+        <p>Historical observations below: 2.x only. Current package: 7.0.2. Retained current-package CTO scenarios with Observed receipts: 0 of 12. Eight historical 4.0.1 Claude run records remain incomplete. Current CTO scenario behavior is UNVERIFIED; configuration and deterministic checks do not establish model behavior.</p>
         <div class="comparison-wrap wide-comparison" role="region" aria-label="Historical 2.x evidence table" tabindex="0">
           <table>
             <thead>