melodic-automation-lanes · Nov 3, 2026
diff --git a/.changes/code-metrics/work-resolve-issue-issue-12619-41570586663-1-3b93eb62.md b/.changes/code-metrics/work-resolve-issue-issue-12619-41570586663-1-3b93eb62.md
@@ -0,0 +1,17 @@
+---
+bump: major
+---
+
+### Added
+
+- `/code-metrics:audit` is a router skill with three actions: `size` (lines per file),
+  `complexity` (per-function cyclomatic, cognitive and Halstead complexity) and `type-debt`
+  (typed-code percentage). Each action runs the same entry script as before, so the options,
+  report and exit codes are unchanged.
+
+### Removed
+
+- The `audit-size`, `audit-complexity` and `audit-type-debt` skills are gone. Run
+  `/code-metrics:audit size`, `/code-metrics:audit complexity` or `/code-metrics:audit type-debt`
+  instead. The report `skill` field and the `dispatch.sh` id keep their old values, so reports
+  taken before and after still compare.
diff --git a/.changes/discipline/work-resolve-issue-issue-12619-41570586663-1-ebd4a40c.md b/.changes/discipline/work-resolve-issue-issue-12619-41570586663-1-ebd4a40c.md
@@ -0,0 +1,7 @@
+---
+bump: none
+---
+
+No release: the `script-the-deterministic-work` trigger probe now names `code-metrics:audit` as a
+competitor in place of the removed `code-metrics:audit-size`. Probe data only; the skill does not
+change.
diff --git a/.changes/performance/work-resolve-issue-issue-12619-41570586663-1-d276eaa6.md b/.changes/performance/work-resolve-issue-issue-12619-41570586663-1-d276eaa6.md
@@ -0,0 +1,6 @@
+---
+bump: none
+---
+
+No release: the `target` trigger probe now names `code-metrics:audit` as a competitor in place of
+the removed `code-metrics:audit-complexity`. Probe data only; the skill does not change.
diff --git a/.changes/review/work-resolve-issue-issue-12619-41570586663-1-83b4eac3.md b/.changes/review/work-resolve-issue-issue-12619-41570586663-1-83b4eac3.md
@@ -0,0 +1,9 @@
+---
+bump: patch
+---
+
+### Changed
+
+- The size-crossing step in `quality-gate` code mode and `fanout` default mode now runs
+  `/code-metrics:audit size`, since code-metrics replaced `audit-size` with the `audit` router.
+  It still runs only when the code-metrics audit skill is installed.
diff --git a/.changes/skill-quality/work-resolve-issue-issue-12619-41570586663-1-8a92d296.md b/.changes/skill-quality/work-resolve-issue-issue-12619-41570586663-1-8a92d296.md
@@ -0,0 +1,6 @@
+---
+bump: none
+---
+
+No release: three `check-skill.test.sh` fixtures now cite `/code-metrics:audit complexity` in place
+of the removed `/code-metrics:audit-complexity`. Test fixtures only; the checker does not change.
diff --git a/.changes/verification/work-resolve-issue-issue-12619-41570586663-1-621885c4.md b/.changes/verification/work-resolve-issue-issue-12619-41570586663-1-621885c4.md
@@ -0,0 +1,9 @@
+---
+bump: patch
+---
+
+### Changed
+
+- `measure metrics` names `/code-metrics:audit complexity --json` and `/code-metrics:audit size --json`
+  for the complexity and size rows, since code-metrics replaced its `audit-complexity` and
+  `audit-size` skills with the `audit` router.
diff --git a/docs/catalog.md b/docs/catalog.md
@@ -63,7 +63,7 @@ plugin manifests and kept in sync by CI. Never hand-edit it; the category vocabu
 - [`mcp-tools`](../plugins/mcp-tools): Two MCP audits. audit scores the tool definitions of a server you build against MCP-specification, Anthropic tool-design, and Claude-Code client criteria in a per-tool PASS/WARN/FAIL scorecard (Python, TypeScript, .NET). audit-posture inventories the MCP servers your Claude Code configuration runs and flags supply-chain risks such as floating package versions, without running any server.
 - [`review`](../plugins/review): Code-review toolkit: nine agents, read-only over the reviewed code, plus orchestration skills for the quality gate and fan-out, a pull-request change digest with an interactive view (/review:explain-change), a fan-out sweep workflow (/review:fanout-sweep), and CI lane commands (/review:code-review, /review:security-review) for org reusable workflows.
 - [`codebase-health`](../plugins/codebase-health): Repo-wide drift audit between docs, config, code, and architecture: verifies every factual claim against reality via parallel subagent fan-out, severity-rates findings, and reports read-only, delegating remediation to the implementation/verification lanes. Audit dimensions are configurable through a tracked .claude/codebase-health.md config file written by the setup skill.
-- [`code-metrics`](../plugins/code-metrics): Read-only code measures for a change, with cited references and no verdict: lines per file (audit-size), cyclomatic, cognitive, and Halstead complexity (audit-complexity), duplication (audit-duplication), per-function coverage and CRAP from existing lcov, Cobertura, coverage.py, or Go artifacts (audit-coverage), TypeScript and Python type debt (audit-type-debt), metric literacy (principles), and setup. Uses only collectors already installed; never installs or runs tests.
+- [`code-metrics`](../plugins/code-metrics): Read-only code measures for a change, with cited references and no verdict: lines per file (audit size), cyclomatic, cognitive, and Halstead complexity (audit complexity), duplication (audit-duplication), per-function coverage and CRAP from existing lcov, Cobertura, coverage.py, or Go artifacts (audit-coverage), TypeScript and Python type debt (audit type-debt), metric literacy (principles), and setup. Uses only collectors already installed; never installs or runs tests.
 - [`discipline`](../plugins/discipline): Correctors that re-anchor a rule, audit work in flight, and fix drift: do-your-research, follow-our-standards, point-dont-copy, reason-dont-recite, tighten-your-output, recheck-against-upstream, pick-for-the-problem, mind-your-maxims, script-the-deterministic-work, use-your-skills, reuse-or-replace, scrutinize-dont-coast. sweep-all runs them as one batch. wait-what re-pitches a message that did not land. hold-my-hand shows work one phase at a time. be-ambitious raises one request's ambition.
 - [`ai-slop`](../plugins/ai-slop): Detects and removes AI-writing tells (slop) in tracked markdown, commit messages, PR bodies and interface copy: em dashes, emoji formatting, AI vocabulary, negative parallelisms, chatbot phrases, filler, hedging, citation artifacts and model-era phrases, from a catalog based on Wikipedia's Signs of AI writing plus a graded model-vocabulary inventory. Read-only audit by default (deterministic detector plus judgment rubric); an explicit fix action rewrites findings behind a semantic-diff guard.
 - [`overengineering`](../plugins/overengineering): Evidence-earned-keep audit of agent hooks and instructions, git hooks, CI lanes and gate scripts, branch protections, forge apps, and integrations. audit treats each as a retirement candidate until evidence earns its keep, argues in cost of carry, caps security-class retirements at FLAG-FOR-HUMAN, and writes a diffable findings file. realign simplifies behind a per-item human gate. delta reports changes since the last run. justify asks whether one artifact's reason still holds.

diff --git a/docs/skill-cheat-sheet.md b/docs/skill-cheat-sheet.md
@@ -240,12 +240,10 @@ owned by [docs/catalog-taxonomy.md](catalog-taxonomy.md).
 | [`/attribution:audit`](../plugins/attribution/skills/audit/SKILL.md) | `attribution` | Find prose copied from external sources and convert it into pointers |
 | [`/bash-format:check`](../plugins/bash-format/skills/check/SKILL.md) | `bash-format` | Report whether shfmt, shellcheck and node are installed. Never installs. |
 | [`/biome-format:check`](../plugins/biome-format/skills/check/SKILL.md) | `biome-format` | Report whether biome and node are installed. Never installs. |
-| [`/code-metrics:audit-complexity`](../plugins/code-metrics/skills/audit-complexity/SKILL.md) | `code-metrics` | Per-function complexity beside a cited reference, no verdict |
+| [`/code-metrics:audit`](../plugins/code-metrics/skills/audit/SKILL.md) | `code-metrics` | Lines, complexity and typed-code numbers beside cited references, no verdict |
 | [`/code-metrics:audit-coverage`](../plugins/code-metrics/skills/audit-coverage/SKILL.md) | `code-metrics` | Coverage and CRAP read from build artifacts, no verdict |
 | [`/code-metrics:audit-duplication`](../plugins/code-metrics/skills/audit-duplication/SKILL.md) | `code-metrics` | Clone groups minus the replication the repo declares, no verdict |
-| [`/code-metrics:audit-size`](../plugins/code-metrics/skills/audit-size/SKILL.md) | `code-metrics` | Lines per file beside a cited reference, no verdict |
 | [`/code-metrics:audit-suppressions`](../plugins/code-metrics/skills/audit-suppressions/SKILL.md) | `code-metrics` | Suppressions with their rule ids and reasons, no verdict |
-| [`/code-metrics:audit-type-debt`](../plugins/code-metrics/skills/audit-type-debt/SKILL.md) | `code-metrics` | Typed-code percentage per file and per lane, with no standard behind it |
 | [`/code-metrics:principles`](../plugins/code-metrics/skills/principles/SKILL.md) | `code-metrics` | What each code measure can and cannot tell you |
 | [`/code-tidying:audit-dead-code`](../plugins/code-tidying/skills/audit-dead-code/SKILL.md) | `code-tidying` | Whole-repo dead-code hunt across four labeled lanes with adjudicated candidates |
 | [`/code-tidying:tidy`](../plugins/code-tidying/skills/tidy/SKILL.md) | `code-tidying` | Proactively hunt one lane for safe structural tidyings and ship a structure-only PR |

diff --git a/docs/test-wall-clock-baseline.md b/docs/test-wall-clock-baseline.md
@@ -173,12 +173,12 @@ and is empty until one is made.
 | `plugins/code-metrics/scripts/persist-report.test.sh` | 0 | |
 | `plugins/code-metrics/scripts/python-resolve.test.sh` | 0 | |
 | `plugins/code-metrics/scripts/tool-free-path.test.sh` | 8 | |
-| `plugins/code-metrics/skills/audit-complexity/scripts/audit-complexity.test.sh` | 17 | |
 | `plugins/code-metrics/skills/audit-coverage/scripts/audit-coverage.test.sh` | 60 | |
 | `plugins/code-metrics/skills/audit-duplication/scripts/audit-duplication.test.sh` | 40 | |
-| `plugins/code-metrics/skills/audit-size/scripts/audit-size.test.sh` | 16 | |
 | `plugins/code-metrics/skills/audit-suppressions/scripts/audit-suppressions.test.sh` | 10 | |
-| `plugins/code-metrics/skills/audit-type-debt/scripts/audit-type-debt.test.sh` | 10 | |
+| `plugins/code-metrics/skills/audit/scripts/audit-complexity.test.sh` | 17 | |
+| `plugins/code-metrics/skills/audit/scripts/audit-size.test.sh` | 16 | |
+| `plugins/code-metrics/skills/audit/scripts/audit-type-debt.test.sh` | 10 | |
 | `plugins/code-metrics/skills/setup/scripts/setup-check.test.sh` | 21 | |
 | `plugins/code-tidying/scripts/added-lines.test.sh` | 1 | |
 | `plugins/code-tidying/scripts/allowed-tools-pairing.test.sh` | 0 | |