feat(triage): hand one log per cluster to the tune skill

Every cluster's failing run is also a timing sample. New step 9 hands one job log per cluster to the tune skill: the job of the cluster that ran furthest, because its timings cover the most phases. Tune works under its own rules and the session's limits, and its candidates run through funnels of their own, separate from the cluster's fix sidetree, so they never delay or block the fix. A log the failure cut short is tuned for the phases it covers, naming those it does not reach. "Follow the run" becomes step 10; observe's reference to step 1 is unchanged.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

skills/triage/SKILL.md

@@ -5,8 +5,8 @@ description: >
   real fix. Trigger when a build, test, or deploy pipeline has one or more failed
   jobs. Applies the dialectic skill to every failing job independently, the
   coordinate skill to every failure cluster, and the funnel skill to every
-  cluster, so each cluster is fixed in its own worktree. Portable across
+  cluster, so each cluster is fixed in its own worktree, and hands one log per
-  projects.
+  cluster to the tune skill. Portable across projects.
 ---
 
 Drive a red pipeline to green by root cause, not by guesswork. Treat every
@@ -55,10 +55,11 @@ root cause is proven.
 5. **One funnel per cluster.** Hand every cluster you claimed in step 3 to the
    `funnel` skill: one agent per cluster, working in its own worktree on its own
    branch created from the exact current HEAD, with that cluster as its only
-   concern, the artifact paths of step 4 in its brief and a hard time cap. Steps 6 to 8 run inside that sidetree, so no
+   concern, the artifact paths of step 4 in its brief and a hard time cap.
-   cluster's edits land under another cluster's work or under a running gate or
+   Steps 6 to 8 run inside that sidetree, so no cluster's edits land under
-   deploy. Run clusters in parallel only when their fixes touch different files
+   another cluster's work or under a running gate or deploy. Run clusters in
-   and the machine has room. A split cluster (step 7) gets a funnel of its own.
+   parallel only when their fixes touch different files and the machine has
+   room. A split cluster (step 7) gets a funnel of its own.
 6. **Dialectic per cluster.** For EACH cluster, invoke the `dialectic` skill:
    form a thesis about the root cause from evidence (the job log, its artifacts,
    the code at the run's commit, git history), attack it with independent
@@ -78,7 +79,14 @@ root cause is proven.
    honestly instead of fixing around it. Report every fix, every proposal, and
    every abandoned attempt to the same agents through the `coordinate` skill,
    then remove the sidetree.
-9. **Follow the run.** While the run is still in progress, re-check it
+9. **Tune one log per cluster.** For each cluster, hand one job log to the
+   `tune` skill: the cluster's job that ran furthest, because its timings cover
+   the most phases. `tune` looks for performance potential in it under its own
+   rules and the session's limits. Its candidates run through funnels of their
+   own, separate from the cluster's fix sidetree, and never delay or block the
+   fix. A log the failure cut short is tuned for the phases it covers; say which
+   phases it does not reach.
+10. **Follow the run.** While the run is still in progress, re-check it
    periodically and triage each newly failed job as it appears. The run is done
    only when it has finished and every failure has a verified fix.