agent-loop-setup

Add an ATDD plan, required commands, and stop conditions to an existing tracker issue that already has acceptance criteria. Use after to-issues and before moving an issue to Ready for Agent. Do not use to implement tests or production code.

Implement exactly one already-claimed tracker issue that is in Active status and has acceptance criteria, ATDD plan, required commands, and stop conditions. Use after take-next-issue prints a /goal command. Finish by opening a PR with briefing or moving the issue to Needs Human.

Select and claim exactly one Ready for Agent tracker issue, validate that it is execution-ready, move it to Active, prepare the branch, and print the /goal command that will run execute-ready-issue. Do not use to implement code or open PRs.

Sequentially drain Linear Ready for Agent issues end-to-end by composing take-next-issue, execute-ready-issue, PR merge, workspace/thread rollover, and the next issue handoff. Use when the user wants autonomous backlog draining, issue-by-issue execution, Conductor workspace-per-issue execution, or a goal that keeps working until no eligible ready-for-agent issues remain.

Set up a repository's baseline unit and integration test suite, including package scripts, minimal passing example tests, and an isolated database strategy when the app uses a database. Use once per repo or when test tooling is missing or broken. Do not use for implementing feature coverage inside normal issues.

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

Open or update a pull request for the current branch and generate a review briefing with context, implementation decisions, verification, risks, and human QA walkthrough. Use after an issue has been implemented and required checks have passed. Do not use to implement feature code.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Explore the codebase to map conventions, reusable utilities, analogous features, and data flows relevant to a planned change. Returns raw findings (file paths, patterns, code snippets), does NOT produce a plan. Used by /flagrare:atdd-plan as its codebase understanding step.

Use when proposing, writing, or reviewing automated tests, defines what a good test is: behavior over implementation details, and the Testing Trophy with a hard floor on end-to-end coverage for user-facing features. Generalized to any language and any layer (frontend, backend, CLI, library), not just JS/React. REQUIRED BACKGROUND for skills that plan or review tests, atdd-plan, implementation-review, tdd-writer, wrap-up. Use when the user asks whether tests are good, what to test, why a test is brittle, or whether e2e is needed.

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.