refactor: resolve SDLC stages with two owning skills #6282

Activity

1. kyle-sexton

   added

   status: needs-decisionAwaiting a human or maintainer judgment call.Awaiting a human or maintainer judgment call.

   priority: mediumReal value, no hard deadline; normal backlog flow.Real value, no hard deadline; normal backlog flow.

   work-class: structuralRefactors, migrations, contract changes; cross-cutting and hard to reverse.Refactors, migrations, contract changes; cross-cutting and hard to reverse.

   on Oct 4, 2026
2. github-actions commented on Oct 4, 2026

   

   github-actionsBot

   on Oct 4, 2026 – with GitHub Actions

   Contributor

   More actions

   Thanks for the report. Automated triage handed this issue to a maintainer.

   _{Automated triage. A maintainer reviews it.}
3. github-actions

   added

   needs-humanHuman-in-the-loop required; autonomous sessions must not resolve items carrying this.Human-in-the-loop required; autonomous sessions must not resolve items carrying this.

   on Oct 4, 2026
4. kyle-sexton commented on Oct 13, 2026

   

   kyle-sexton

   on Oct 13, 2026

   MemberAuthor

   More actions

   Decision recorded. The owner approved applying independently verified recommendations on 2026-10-12.

   • Where does /planning:plan route a performance (wall time, latency, throughput) goal? → /performance:goal when the performance plugin is enabled, else /verification:measure; code-metric goals stay with /verification:measure
     Basis: plugins/planning/skills/plan/SKILL.md:236; plugins/verification/skills/measure/SKILL.md:71; plugins/performance/skills/goal/SKILL.md:184

   Five SDLC stages had two owning skills with no routing between them. On main the pr-explainer stub is removed and attend-queue hands intake to triage (#6304), plan routes ticket splitting to /work-items:decompose and the workflow ladder has its own Decompose step, and architecture:improve hands an agreed shape to /planning:design; only the performance pair is unresolved: plan still routes performance goals only to /verification:measure.

   Verified by an independent fresh-context check (confirmed, risk low): gh issue view 6282; plan/SKILL.md:235-237, 440-442; verification/measure/SKILL.md:70-72; performance/goal/SKILL.md:183-185; session-flow workflow steps.md:116-118; architecture/improve/SKILL.md:90-92

   Admission to an agent lane stays with the work-class rules and owner ratification.
5. kyle-sexton

   removed

   status: needs-decisionAwaiting a human or maintainer judgment call.Awaiting a human or maintainer judgment call.

   on Oct 13, 2026
6. kyle-sexton commented on Oct 13, 2026

   

   kyle-sexton

   on Oct 13, 2026

   MemberAuthor

   More actions

   Owner batch-ratified this admission in an attended session on 2026-10-12: work-class: scoped. Rule: class C1-C3, no trust surface, the independent check confirmed the recorded decision, and no owner step remains.
7. kyle-sexton

   added

   work-class: scopedA briefed fix or small feature; blast radius bounded by the brief, tests exist.A briefed fix or small feature; blast radius bounded by the brief, tests exist.

   agent-readyFully specified and briefed; eligible for autonomous pickup from the frontier.Fully specified and briefed; eligible for autonomous pickup from the frontier.

   needs-humanHuman-in-the-loop required; autonomous sessions must not resolve items carrying this.Human-in-the-loop required; autonomous sessions must not resolve items carrying this.

   and removed

   needs-humanHuman-in-the-loop required; autonomous sessions must not resolve items carrying this.Human-in-the-loop required; autonomous sessions must not resolve items carrying this.

   agent-readyFully specified and briefed; eligible for autonomous pickup from the frontier.Fully specified and briefed; eligible for autonomous pickup from the frontier.

   work-class: scopedA briefed fix or small feature; blast radius bounded by the brief, tests exist.A briefed fix or small feature; blast radius bounded by the brief, tests exist.

   on Oct 13, 2026
8. kyle-sexton commented on Oct 13, 2026

   

   kyle-sexton

   on Oct 13, 2026

   MemberAuthor

   More actions

   Correction: this issue already carried work-class: structural, which batch ratification never admits. The admission above is reverted; it stays escalated for an attended decision.
9. kyle-sexton

   added the

   Task

   issue type on Oct 15, 2026
10. kyle-sexton

    removed

    needs-humanHuman-in-the-loop required; autonomous sessions must not resolve items carrying this.Human-in-the-loop required; autonomous sessions must not resolve items carrying this.

    work-class: structuralRefactors, migrations, contract changes; cross-cutting and hard to reverse.Refactors, migrations, contract changes; cross-cutting and hard to reverse.

    on Oct 17, 2026
11. kyle-sexton commented on Oct 17, 2026

    

    kyle-sexton

    on Oct 17, 2026

    MemberAuthor

    More actions

    Admitted in owner batch A1 (mechanical).
12. kyle-sexton

    added

    agent-readyFully specified and briefed; eligible for autonomous pickup from the frontier.Fully specified and briefed; eligible for autonomous pickup from the frontier.

    on Oct 17, 2026
13. melodic-automation-lanes

    added

    needs-humanHuman-in-the-loop required; autonomous sessions must not resolve items carrying this.Human-in-the-loop required; autonomous sessions must not resolve items carrying this.

    on Oct 17, 2026
14. melodic-automation-lanes commented on Oct 17, 2026

    

    melodic-automation-lanesBot

    on Oct 17, 2026

    Contributor

    More actions

    The work-resolve-issue lane did not start this issue: it needs a person to make it clearer first.

    Why, in the run's own words:

    The issue's "Decision needed" section leaves the choice open for all five pairs, so I can't pick it for you. For each pair, should there be (a) one owner with the other skill routing to it, or (b) a stated boundary in both descriptions? The pairs are: verification:measure vs performance:* (and which of them /planning:plan should route a performance goal to); plan / workflow ladder decomposition vs work-items:decompose; architecture:improve's Design-It-Twice interview vs planning:design; work-items:attend-queue vs work-items:triage for untriaged intake; review:pr-explainer stub vs review:explain-change. The pr-explainer stub also needs an explicit decision: remove it (and when, given it is a rename stub), or keep it. The acceptance criterion "Plan routes a performance goal to the owner chosen" depends on the first answer.

    What the run says it did not do:

    • All work: waiting on the owner/boundary decision for each of the five pairs and the pr-explainer removal decision

    Run: https://github.com/melodic-software/claude-code-plugins/actions/runs/39043271678

    To retry, answer the question here, remove needs-human and add agent-ready again.
15. melodic-automation-lanes

    removed

    agent-readyFully specified and briefed; eligible for autonomous pickup from the frontier.Fully specified and briefed; eligible for autonomous pickup from the frontier.

    on Oct 17, 2026
16. kyle-sexton commented on Oct 17, 2026

    

    kyle-sexton

    on Oct 17, 2026

    MemberAuthor

    More actions

    Owner decision 2026-10-17: parked. The lane's hand-back was correct; this stays needs-human until the owner takes it up.