Skip to content

Concise skills rollout: harness-config (10 skills, 9 model-invoked) #6555

Open
0 of 2 issues completed
Open

Description

@kyle-sexton

Part of #6476. Rewrite harness-config's skills to the skill criteria in one draft PR, following the per-plugin runbook (/playbooks:skill-authoring, reference/rewrite-a-plugin.md). The runbook and the rewrite protocol it cites decide what ships; this issue holds only what is specific to the plugin.

The plugin today

  • Skills: audit, audit-automation-gaps, audit-instructions, audit-pass, audit-permission-grants, audit-permission-state, audit-prompting-postures, draft-auto-mode-rules, setup (user-invoked), unhobble.
  • Outcome eval cases under evals/: 0. Probe files under probes/: 0.

Done when

  • The PR merges with a per-skill decision table in its body, and every shipped description and body was measured.
  • Any skill left unmeasured, and why, is named in the PR.

Needs a person

  • Approve the eval spend for this plugin (the /evals:plugin-eval estimate) before the measured passes.
  • Review the draft PR and mark it ready.

Generated by Claude Code

Activity

  1. added
    needs-triageNot yet classified. Floor until a type and one priority tier are set.
    on Oct 7, 2026
  2. github-actions commented on Oct 7, 2026

    @github-actions
    Contributor

    Proposed work class: work-class: structural
    Basis: automated intake triage; the lanes App applied this class.

    Size: Large
    Complexity: Medium
    Uncertainty: Known
    Flags: none
    Blocked by: none

    Understood: this is the harness-config part of the concise-skills rollout (#6476). It rewrites the plugin's 10 skills to the skill criteria, following the per-plugin runbook. The latest comment says the owner rules already cover the eval spend, so no cost decision is open. The work is too big for one change. It should be split into sub-issues, with outcome eval cases first and then rewrite slices of a few skills each, as that comment's criteria describe. I found no likely duplicates among the open issues.

    Automated triage, applied by the lanes App.

  3. added
    needs-humanHuman-in-the-loop required; autonomous sessions must not resolve items carrying this.
    on Oct 7, 2026
  4. added theissue type on Oct 12, 2026
  5. removed
    needs-triageNot yet classified. Floor until a type and one priority tier are set.
    on Oct 12, 2026
  6. kyle-sexton commented on Oct 22, 2026

    @kyle-sexton
    MemberAuthor

    Parked (owner decision 2026-10-21): no eval spend until #7719 resumes hardening. This stays open and resumes then.

  7. removed
    needs-humanHuman-in-the-loop required; autonomous sessions must not resolve items carrying this.
    on Oct 25, 2026
  8. added
    needs-triageNot yet classified. Floor until a type and one priority tier are set.
    priority: mediumReal value, no hard deadline; normal backlog flow.
    and removed
    needs-triageNot yet classified. Floor until a type and one priority tier are set.
    on Oct 25, 2026
  9. added
    status: readyTriaged, unblocked, and fully specified; eligible to pick up.
    work-class: structuralRefactors, migrations, contract changes; cross-cutting and hard to reverse.
    status: needs-decisionAwaiting a human or maintainer judgment call.
    and removed
    status: readyTriaged, unblocked, and fully specified; eligible to pick up.
    on Oct 25, 2026
  10. melodic-automation-lanes commented on Oct 25, 2026

    @melodic-automation-lanes
    Contributor

    Not admitted to the issue lane yet: Size large: the split into sub-issues at intake is pending (owner Q93).

  11. melodic-automation-lanes commented on Oct 25, 2026

    @melodic-automation-lanes
    Contributor

    The latest triage verdict holds nothing: the issue is at status: ready.

  12. melodic-automation-lanes commented on Oct 25, 2026

    @melodic-automation-lanes
    Contributor

    Refinement. A read-only run explored this repository, searched its issues and pull requests, and read the allowed docs to draft what follows. On an issue a listed human filed, it counts as the issue's spec once posted, while unedited; it is still model text, so check it.

    Intended outcome: Rewrite the 10 harness-config skills to the skill criteria in one draft PR with a per-skill decision table, every description and body measured, once eval spend is approved.

    Dependencies

    • #​7719: owner parked eval spend until hardening resumes
    • #​6476: parent rollout

    Related work

    Open questions

    1. Should the lane hold this issue until #​7719 resumes hardening and the owner approves the /evals:plugin-eval spend?
      RECOMMENDED: Yes, hold; do not start measured passes until the owner records eval spend approval. Basis: kyle-sexton comment 2026-10-22: parked, no eval spend until #​7719 resumes hardening
    2. Should the body gain a task list so the criteria are checkable, with the two person-only items (approve eval spend, mark PR ready) split out?
      RECOMMENDED: Yes: add task items for the PR merging with a per-skill decision table, every shipped description and body measured, and any unmeasured skill named with a reason. Basis: judgment

    Sources read

    • /home/runner/work/claude-code-plugins/claude-code-plugins/.base/plugins/harness-config/skills: lists 10 skills (audit, audit-automation-gaps, audit-instructions, audit-pass, audit-permission-grants, audit-permission-state, audit-prompting-postures, draft-auto-mode-rules, setup, unhobble), matching the issue

    Automated refinement by the lanes App. Answer with a comment whose first line is **Decision recorded.**.

  13. kyle-sexton commented on Oct 26, 2026

    @kyle-sexton
    MemberAuthor

    This was generated by AI.

    Releasing the hold: no owner question is open. The refinement asked about eval spend or who runs the eval. Owner rules settle both. Evals run on the subscription login or not at all, never with an API key, and none start while the rate limit is near (Q110). Subscription and prepaid spend are not induced cost (Q46, Q91). Under the owner's 2026-10-26 stop rule (C14), an eval or host run is no longer an owner step, so an agent session runs it. The label comes off and intake triage runs again. Criteria:

    • The issue is split into sub-issues with blocked-by edges before any run (Q93/Q94): outcome eval cases for harness-config first, then rewrite slices of a few skills each.
    • Each rewrite slice's PR carries a per-skill decision table, and every shipped description or body change is backed by a valid measured pass on the subscription.
    • Any skill left unmeasured is named in its PR with the reason.
    • The parent closes when every slice has merged.
  14. github-actions commented on Oct 26, 2026

    @github-actions
    Contributor

    The triage sweep dispatched intake triage for this issue (attempt 1 of 2).

  15. melodic-automation-lanes commented on Oct 26, 2026

    @melodic-automation-lanes
    Contributor

    Split at intake (owner Q93). This issue is Size Large, so its done-when is split into 2 sub-issues, each holding its task-list lines as written.

    Automated split by the lanes App. Admission waits on this issue while a sub-issue is open; work-unblock closes it as completed once every sub-issue is closed by a merge or a listed human.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    priority: mediumReal value, no hard deadline; normal backlog flow.status: readyTriaged, unblocked, and fully specified; eligible to pick up.work-class: structuralRefactors, migrations, contract changes; cross-cutting and hard to reverse.

    Type

    Fields

    No fields configured for Task.

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions