Skip to content

aiops: claude - Adapt Claude agents for repository workflows #260

Open

Description

@ashleyshaw

AI Ops Summary

Adapt Claude agents for lightspeedwp/ThisOneTimeOnAcidCom.

Build Summary

Delivery and remaining validation — 17 October 2026

Agent definitions and mappings for all 17 requested agents were delivered in aiops: claude - Configure agents, hooks, skills and cloud settings, merged into develop. Canonical-source verification, discovery, invocation, representative outputs and permission-boundary validation remain outstanding. Acceptance checkboxes remain unchanged; author-reported tests are not independently verified.

Verify canonical sources for all 17 agents listed on the parent. Implement suitable definitions under .claude/agents/ and document source mappings, adaptations and exclusions.

Linked Stories/Tasks/PRs/Epic

Parent: #218. Settings dependency: #259.

Milestones & Timeline

No milestone or deadline specified. Estimates remain unset.

Problem / Opportunity

Shared agents require repository-specific adaptation rather than unrelated WordPress or shared-governance assumptions.

Approach / Solution

Follow repository instructions and inspect canonical shared agent sources. Record adapt/exclude/missing decisions for every requested agent.

Acceptance Criteria

  • AI workflow/agent described
  • Problem/opportunity scoped
  • Success metric defined
  • Documentation updated
  • PR uses correct branch prefix (aiops/)
  • PR description updated with relevant details
  • Changelog entry prepared for PR (if applicable)
  • Labels/types match org standards
  • Every requested agent has a verified source mapping or an explicit missing-source finding.
  • Each agent has a documented adapt/exclude decision.
  • Implemented agents define responsibilities, inputs, outputs, tools and permission boundaries.
  • Instructions reflect this repository rather than unrelated WordPress or shared-governance assumptions.
  • Discovery, invocation and representative task results are validated.
  • No agent is authorised to modify protected files merely through its instructions.

Additional Context

Historical review observations — 16 October 2026

The review of implementation revision 149f089 identified the following specific adaptation concerns. These are historical observations, not verified defects in the merged implementation:

  • Changed responsibilities: the metadata agent focused on SEO/Open Graph rather than its source’s GitHub label/project-field consistency; the metrics agent focused on visitor analytics rather than issue/PR/project health. Verify the merged definitions and document deliberate replacements or restore applicable source responsibilities.
  • Label accuracy: labelling instructions referenced type:documentation, meta:needs-review and area:design, which were absent from the repository during review. Verify current availability before prescribing labels; do not create or substitute taxonomy automatically.
  • Editorial scope: content and discovery agents introduced potential-client, service/capability and client-case-study language despite the repository’s personal-art/book direction. Recheck merged instructions and document repository-appropriate adaptations or explicitly opt-in exclusions.

Record the checked revision, disposition and supporting evidence for each observation. Do not infer resolution from the merge alone.

Verify supported tool identifiers and least-privilege permissions for all 17 agents. Record discovery, invocation and permission-boundary results; correct remaining defects and document source adaptations.

Dependencies: settings foundations and access to canonical agent sources. Agent names and full baseline requirements remain on the parent. Branch-prefix policy requires repository verification. Preserve protected files, including CHANGELOG.md unless separately authorised.


Definition of Ready (DoR)

  • AI ops goal described
  • Area/action mapped
  • Acceptance criteria listed
  • Estimate added

Definition of Done (DoD)

  • All acceptance criteria met
  • Solution/automation verified
  • Documentation updated
  • PR uses correct branch prefix (aiops/)
  • PR uses the correct PR template based on type:aiops PR label or linked issue type or linked issue type:aiops label
  • Branch deleted after merge
  • Linked issue(s) updated with latest status and closed after merge,
  • The related epic should not be closed, instead updated with a comment to reflect the closed issue

Branch instructions

  • Repository: lightspeedwp/ThisOneTimeOnAcidCom.
  • Implementing target: this agent-adaptation issue, independently verified counterpart GitHub issue 260. Verify all 17 requested source mappings, adaptations, permissions, discovery, invocation and representative outputs.
  • Parent context: existing parent is coordination only. Retain hierarchy; omit its identifier/URL from branch names, PR metadata and coding prompts while association effects remain unconfirmed. Never use it as a native PR development or closing target.
  • Allowed closing targets: none currently. This provisional remediation plan does not establish the whole issue outcome.
  • Branch state: proposed new branch; not created. No suitable existing branch verified for reuse.
  • Branch: aiops/claude-agent-adaptation.
  • Base: develop, checked at 4ecdb26d9655a48bf000a7c89da2f70383edce87.
  • Classification: AI-agent workflow adaptation and permission boundaries, not application functionality or testing-only work.
  • Naming policy: local guide, validator and organisation strategy. aiops and the proposed pattern are supported by static inspection; validator not executed.
  • PR template: verified shared AI-ops template. Native inheritance/named-template loading remains unverified; do not create local template files, copy sample closing references or change shared templates.
  • Existing work: historical configuration PR is merged, not reusable active work. Open governance PR inventory additions remain separately owned; do not reuse its branch or duplicate inventories automatically.
  • Missing evidence: source mappings for all 17 agents and installed Claude metadata/tool compatibility remain incomplete. Root instructions contain stale prefix/runtime/test claims; follow checked naming sources without absorbing unrelated documentation repairs.
  • Constraints: planning only. Preserve unrelated changes; no automatic branch creation, reuse, rename, force-push, merge, deployment or execution. Settings/hooks, cloud provisioning, taxonomy and protected files remain outside scope.

Expected file changes

Provisional, not a complete implementation inventory. Every existing path below was read at 4ecdb26d9655a48bf000a7c89da2f70383edce87; existence is not edit approval.

Operation Path(s) Intended change Evidence Approval or dependency
Edit docs/claude-configuration.md Source/adaptation matrix distinguishing delivery from acceptance Read at checked revision Exact-content approval; serial shared-document ownership
Edit, conditional .claude/agents/metadata-agent.md Record deliberate SEO replacement versus source governance responsibilities Local and shared source read Owner disposition; no silent purpose change
Edit, conditional .claude/agents/metrics-agent.md Resolve visitor analytics versus repository-health responsibilities Local and shared source read Owner disposition
Edit, conditional .claude/agents/content-strategy-agent.md; .claude/agents/website-content-strategist-agent.md; .claude/agents/client-website-discovery-assistant-agent.md Reconcile client/service language with personal-art/book scope All read at checked revision Approve adaptations or exclusions
Edit, conditional .claude/agents/labeling-agent.md Explicit approval boundaries and verified label references Read at checked revision Read-only taxonomy verification; no label creation/application
Edit, conditional .claude/agents/changelog-agent.md; .claude/agents/release-agent.md; .claude/agents/pr-agent.md Protected-file, release and PR-association boundaries All read at checked revision Owner review; definitions confer no write authority
Create, proposed reports/claude/agent-acceptance.md Requirement/source/file/scenario/result/gap matrix New destination proposed; existence unchecked Confirm absence and approve; no invented passing results

Complete bounded discovery of remaining requested definitions and canonical sources before proposing further file edits. No moves or deletions proposed. Settings/privacy evidence precedes agent responsibility decisions, separately authorised operational validation and skills handoff. Do not edit pending settings/hook issues or absorb governance inventories. Shared documentation must be serialised across related work.

Activity

  1. linear-code commented on Oct 16, 2026

    @linear-code
  2. changed the title [-]Adapt Claude agents for repository workflows[/-] [+]aiops: claude - Adapt Claude agents for repository workflows[/+] on Oct 16, 2026
  3. self-assigned this
    on Oct 17, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Type

No type

Fields

Priority

Medium

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions