apiVersion: devrunbook.io/v1alpha1
kind: Playbook
metadata:
  id: testing.unit-test-foundation
  slug: unit-test-foundation
  version: 1.0.0
  title: Establish Unit Test Foundation
  summary: Introduce a maintainable unit-test baseline around core domain behavior without over-mocking implementation details.
  category: testing
  tags:
  - testing
  - unit-tests
  - foundation
  lifecycle: reviewed
  riskTier: moderate
  authors:
  - name: DevRunbook Core Team
  license: MIT
package:
  files:
  - path: prompt.md
    role: template
    digest: true
    exportByDefault: false
  - path: README.md
    role: documentation
    digest: true
    exportByDefault: false
  - path: CHANGELOG.md
    role: changelog
    digest: true
    exportByDefault: false
  - path: examples/minimal.yaml
    role: example
    digest: true
    exportByDefault: false
  - path: evaluations/static-structure.yaml
    role: evaluation
    digest: true
    exportByDefault: false
spec:
  type: run-pack
  intent:
    problem: Development work around establish unit test foundation is often underspecified, inconsistently executed or reported
      without enough evidence.
    outcome: Introduce a maintainable unit-test baseline around core domain behavior without over-mocking implementation details.
    whenToUse:
    - Use this playbook when the repository needs a bounded establish unit test foundation task with explicit evidence and
      completion criteria.
    - Use it when Codex should follow a repeatable workflow rather than improvise from a one-line request.
    whenNotToUse:
    - Do not use it when the desired outcome or authority boundaries are still materially undecided.
    - Do not use it to access unavailable production credentials, bypass safeguards or claim validation that cannot be performed.
  modes:
  - guided
  - execute
  - recovery
  defaultMode: execute
  autonomy:
    min: implement
    max: repair
    default: verify
  inputs:
  - key: criticalModules
    label: Critical modules
    description: List the modules or behavior that need the first unit-test coverage.
    type: string-list
    required: true
    sensitive: false
    includeInOutput: true
  - key: testFrameworkPreference
    label: Test framework preference
    description: State an existing or preferred test framework, or leave blank to follow repository conventions.
    type: string
    required: false
    sensitive: false
    includeInOutput: true
    default: ''
  compatibility:
    repositoryRequired: true
    languages: []
    frameworks: []
    packageManagers: []
    databases: []
    deploymentTypes: []
    requiredProfileCapabilities: []
    incompatibleConditions: []
  guardrails:
  - id: guardrail-1
    severity: blocking
    text: Follow existing architecture and avoid introducing a competing test framework without justification.
  - id: guardrail-2
    severity: blocking
    text: Do not test private implementation details when observable behavior provides a stable contract.
  - id: guardrail-3
    severity: blocking
    text: Do not add broad mocks that make tests pass while bypassing meaningful behavior.
  workflow:
  - id: inventory-testability
    title: Inventory testability
    instruction: Inspect current test tooling, module boundaries, side effects and critical untested behavior.
    required: true
  - id: select-framework
    title: Select framework
    instruction: Use the existing framework or justify the smallest compatible addition.
    required: true
  - id: configure
    title: Configure foundation
    instruction: Add deterministic configuration, scripts, fixtures and test environment isolation.
    required: true
  - id: add-critical-tests
    title: Add critical tests
    instruction: Cover the selected modules with behavior-focused tests and representative edge cases.
    required: true
  - id: improve-boundaries
    title: Improve test seams
    instruction: Make minimal architecture changes only where necessary to isolate external effects.
    required: true
  - id: document
    title: Document usage
    instruction: Document commands, conventions and how to add new tests.
    required: true
  - id: verify
    title: Verify suite
    instruction: Run tests repeatedly plus relevant lint, typecheck and build checks.
    required: true
  validation:
    commandRoles:
    - lint
    - typecheck
    - unit-test
    - build
    checks:
    - id: check-1
      type: assertion
      description: The test command is reproducible from a fresh checkout.
      blocking: true
      evidence: Referenced files, command results or explicit review notes.
    - id: check-2
      type: assertion
      description: Critical selected modules have meaningful behavior coverage and stable fixtures.
      blocking: true
      evidence: Referenced files, command results or explicit review notes.
    - id: command-lint
      type: command
      description: Run the resolved lint command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
    - id: command-typecheck
      type: command
      description: Run the resolved typecheck command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
    - id: command-unit-test
      type: command
      description: Run the resolved unit-test command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
    - id: command-build
      type: command
      description: Run the resolved build command when the repository profile provides it and record the result.
      blocking: true
      evidence: Resolved command, exit status and concise result summary.
  completion:
    criteria:
    - Critical behavior has deterministic tests.
    - Test command is documented and integrated into validation.
    - Validation evidence and unresolved limitations are reported honestly.
  failurePolicy:
    onValidationFailure: Investigate failures caused by the current work, repair them when they remain within scope, rerun
      affected validation and report any genuine blocker without claiming success.
    onAmbiguity: Use repository evidence and existing conventions for minor reversible choices. Preserve current behavior
      and stop before any material irreversible decision that the specification does not resolve.
    onMissingContext: Inspect the repository for missing non-sensitive context. Never invent commands, credentials, production
      behavior or validation results; report what remains unavailable.
    onOutOfScopeCause: Explain the evidenced out-of-scope cause, avoid unrelated changes and provide the smallest safe follow-up
      recommendation.
    onExternalDependencyUnavailable: Use an approved local substitute or fixture only when it preserves the behavior under
      test. Otherwise record the blocked validation and do not claim the external path succeeded.
    onUnableToReproduce: Record attempted reproduction, environment and observed evidence. Do not apply speculative production
      changes; provide the narrowest next diagnostic action.
  reporting:
    sections:
    - id: outcome
      title: Outcome
      required: true
      description: State the delivered result or audit conclusion without overstating evidence.
    - id: evidence
      title: Evidence and scope
      required: true
      description: List inspected or changed areas and the evidence supporting the result.
    - id: validation
      title: Validation
      required: true
      description: Report commands, manual checks and their actual outcomes.
    - id: risks
      title: Risks and limitations
      required: true
      description: State residual risk, inaccessible evidence and untested conditions.
    - id: follow-up
      title: Recommended follow-up
      required: true
      description: List the smallest useful next actions or state None.
  template:
    main: prompt.md
    partials: []
  exports:
    prompt: true
    markdown: true
    runPack: true
    agentsSuggestion: false
quality:
  reviewStatus: editorial-reviewed
  testedStacks: []
  knownLimitations:
  - Repository-specific effectiveness depends on the accuracy of the selected profile and the evidence available to Codex.
  evaluationCaseIds:
  - unit-test-foundation.static-structure