chore(deps): update agent skills

.claude-plugin/marketplace.json

@@ -15,19 +15,19 @@
     {
       "name": "gitops-kubernetes",
       "description": "Flux CD debugging, knowledge, repository auditing, and tenant onboarding — skills plus the Flux MCP server and a read-only Flux troubleshooter agent for live-cluster debugging",
-      "version": "1.0.0",
+      "version": "1.0.1",
       "source": "./plugins/gitops-kubernetes"
     },
     {
       "name": "github",
       "description": "GitHub CLI, stacked PRs, Actions docs, and issue management skills",
-      "version": "1.0.2",
+      "version": "1.0.3",
       "source": "./plugins/github"
     },
     {
       "name": "agentic-engineering",
       "description": "The autonomous engineering system for repository portfolios — engineer, read-only surveyor, and meta-engineer agents; portfolio, product, spend, and improvement workflows; cross-tool instruction architecture and skill discovery; configured by the consumer AGENTS.md",
-      "version": "4.4.17",
+      "version": "4.4.18",
       "source": "./plugins/agentic-engineering"
     },
     {

.github/plugin/marketplace.json

@@ -15,19 +15,19 @@
     {
       "name": "gitops-kubernetes",
       "description": "Flux CD debugging, knowledge, repository auditing, and tenant onboarding — skills plus the Flux MCP server and a read-only Flux troubleshooter agent for live-cluster debugging",
-      "version": "1.0.0",
+      "version": "1.0.1",
       "source": "./plugins/gitops-kubernetes"
     },
     {
       "name": "github",
       "description": "GitHub CLI, stacked PRs, Actions docs, and issue management skills",
-      "version": "1.0.2",
+      "version": "1.0.3",
       "source": "./plugins/github"
     },
     {
       "name": "agentic-engineering",
       "description": "The autonomous engineering system for repository portfolios — engineer, read-only surveyor, and meta-engineer agents; portfolio, product, spend, and improvement workflows; cross-tool instruction architecture and skill discovery; configured by the consumer AGENTS.md",
-      "version": "4.4.17",
+      "version": "4.4.18",
       "source": "./plugins/agentic-engineering"
     },
     {

plugins/agentic-engineering/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "agentic-engineering",
   "description": "The autonomous engineering system for repository portfolios — engineer, read-only surveyor, and meta-engineer agents; portfolio, product, spend, and improvement workflows; cross-tool instruction architecture and skill discovery; configured by the consumer AGENTS.md",
-  "version": "4.4.17",
+  "version": "4.4.18",
   "author": {
     "name": "devantler-tech",
     "url": "https://github.com/devantler-tech"

plugins/agentic-engineering/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "agentic-engineering",
   "description": "The autonomous engineering system for repository portfolios — engineer, read-only surveyor, and meta-engineer agents; portfolio, product, spend, and improvement workflows; cross-tool instruction architecture and skill discovery; configured by the consumer AGENTS.md",
-  "version": "4.4.17",
+  "version": "4.4.18",
   "author": {
     "name": "devantler-tech",
     "url": "https://github.com/devantler-tech"

plugins/agentic-engineering/resources/provider-neutral.desired-state.json

@@ -66,7 +66,7 @@
         "enabledWhen": "Both optional consumer contract sections are present",
         "mode": "separate-schedule-or-on-demand",
         "definitionSha256": "4e5d1dac3307ac7151d40dababae48b1da7a68f927a11026f1f5f87424b336aa",
-        "skillSha256": "dccf7463ecf0e11a12f03ae5e26dedbdc0b2c668616de548c68c269a69240cfa"
+        "skillSha256": "be203a29321e789c0134f9cb9ad309b683cc406ac4de815fefe26bce2b397dbc"
       }
     },
     "runtime": {

plugins/agentic-engineering/skills/agent-improvement/SKILL.md

@@ -3,9 +3,9 @@ description: How a meta-engineer improves an autonomous AI engineer from the OUT
 license: Apache-2.0
 metadata:
     github-path: agent-improvement
-    github-ref: refs/tags/v1.11.2
+    github-ref: refs/tags/v1.11.7
     github-repo: https://github.com/devantler-tech/agent-skills
-    github-tree-sha: aa67318d2750e0dff85c29f675f0caae89f619ab
+    github-tree-sha: d72c62a065c767fee9a8dc1c2d7a55b6f901cce3
 name: agent-improvement
 ---
 # Agent-improvement loop
@@ -122,6 +122,30 @@ attributed to the tool that produced them; latency waste; guard firings and deni
 collisions; loader↔contract drift; per-session value-bearing and terminal outcomes; and post-merge
 outcomes.
 
+**Cover the whole corpus — delegated transcripts are usually stored separately.** Where the runtime
+records delegated work (subagents, sidechains, sub-sessions) in files stored separately from the
+parent session's — commonly nested beneath it rather than beside it — an enumeration that walks only
+the top level of the session store silently omits every one of them. That fails open on the
+observation plane: delegated work is where a guard's firings and a delegated survey's cost actually
+land, so a denial family occurring only inside subagents reads as *never occurring*, and a live
+regression scores as absent. Enumerate delegated transcripts explicitly, and **report coverage
+alongside every measurement** — files enumerated, and the share of records drawn from delegated
+sessions — so an omission is visible in the output instead of being inferred from a
+plausible-looking number. Before accepting that share, build an **independent expected
+delegated-session inventory** from runtime metadata that does not depend on the transcript walk — for
+example parent/child session IDs, dispatch records, or a runtime index — and report every expected
+session missing from the transcript walk. If no independent source exists, delegated coverage is
+**UNKNOWN**, never zero percent.
+
+**A control must vary the suspected filter, not merely the method.** Re-counting one file list with a
+second tool re-measures the same population: it confirms the parser and cannot reveal a population
+that was never enumerated. Before a count becomes a verdict, re-derive it once with the filter you
+most doubt removed — the enumeration root, the traversal depth, the time window, the record-type
+predicate. Re-derive a comparable count with the suspected filter removed, then reconcile the delta to
+the records that the filter intentionally excluded; an equivalent-cohort comparison may instead hold
+everything except that filter constant. Only an unexplained residual is a finding about the filter. A
+control that shares the enumeration is not a control.
+
 Supplement it with:
 
 - **Every instance's durable memory** — read for *what the agent believes*, compare against live state,
@@ -401,15 +425,25 @@ Two verifications, both required:
    sessions, dispatches, requests, or artifacts). Count only evidence generated at or after the
    verification-window start toward the post-change volume.
    A state metric whose outcome is decisive from one live inspection may omit the volume floor.
+   **Before any adverse verdict, prove the intervention is deployed.** A metric that did not move
+   has two causes taking opposite remedies: the diagnosis was wrong, or the change never reached the
+   runtime that generated the evidence. Establish deployment by reading the intervention's content at
+   the revision the consuming deployment loads; an upstream merge, a version string, or a green check
+   on the authoring pull request is not delivery, because a synced or vendored artifact reaches the
+   runtime only after every intermediate hop lands. An intervention that is not live is NOT-YET-DUE,
+   blocked on rollout, never NOT-WORKING, and the stalled rollout is itself the finding to pursue
+   rather than a reason to revert or reshape.
+
    The next run checks eligibility before applying a verdict:
-   - if either floor is unmet → record **NOT-YET-DUE**, keep the hypothesis open without applying a
+   - if either floor is unmet, or the intervention is not live at the consuming deployment's loaded
+     revision → record **NOT-YET-DUE**, keep the hypothesis open without applying a
      verdict, and continue with other authorised work;
    - metric moved in its expected direction and every declared companion floor held → close the
      hypothesis, keep the change;
-   - metric unchanged → the diagnosis was wrong. **Say so**, then revert or reshape — never layer a
-     second guess on an unverified first;
-   - metric moved in the wrong direction, or a companion safety or quality floor regressed → **revert
-     first, diagnose after**.
+   - metric unchanged **and the intervention proven live** → the diagnosis was wrong. **Say so**,
+     then revert or reshape — never layer a second guess on an unverified first;
+   - metric moved in the wrong direction, or a companion safety or quality floor regressed,
+     **and the intervention proven live** → **revert first, diagnose after**.
 
 While the hypothesis remains pending, continue only with work that cannot affect its tracked signature
 or metric; otherwise wait for evidence or choose a non-overlapping improvement.