@manhd_d/ai-harness 0.11.0 → 0.13.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (163) hide show
  1. package/CHANGELOG.md +38 -0
  2. package/README.md +26 -38
  3. package/adapters/ai-python/adapter.yaml +1 -1
  4. package/adapters/ai-python/rules.md +3 -0
  5. package/adapters/ai-python/skills/harness-ai-python-rag-access/SKILL.md +1 -0
  6. package/adapters/ai-python/skills/harness-ai-python-tool-safety/SKILL.md +1 -0
  7. package/adapters/astro/adapter.yaml +3 -5
  8. package/adapters/astro/checks/verification.yaml +6 -6
  9. package/adapters/astro/evals/cases.json +5 -5
  10. package/adapters/astro/rules/architecture.md +2 -8
  11. package/adapters/astro/rules/deployment.md +2 -8
  12. package/adapters/astro/rules.md +5 -14
  13. package/adapters/astro/skills/harness-astro-islands/SKILL.md +3 -2
  14. package/adapters/astro/skills/harness-astro-performance/SKILL.md +1 -0
  15. package/adapters/astro/skills/harness-astro-project-architecture/SKILL.md +9 -19
  16. package/adapters/astro/skills/harness-astro-seo/SKILL.md +1 -0
  17. package/adapters/java-spring/adapter.yaml +2 -4
  18. package/adapters/java-spring/rules/database.md +2 -2
  19. package/adapters/java-spring/rules/performance.md +2 -2
  20. package/adapters/java-spring/rules.md +4 -1
  21. package/adapters/java-spring/skills/harness-java-spring-spring-api/SKILL.md +1 -0
  22. package/adapters/kubernetes/adapter.yaml +1 -1
  23. package/adapters/kubernetes/rules.md +3 -0
  24. package/adapters/kubernetes/skills/harness-kubernetes-helm-release/SKILL.md +1 -0
  25. package/adapters/kubernetes/skills/harness-kubernetes-rollout-safety/SKILL.md +1 -0
  26. package/adapters/kubernetes/skills/harness-kubernetes-workload-review/SKILL.md +1 -0
  27. package/adapters/react-native/adapter.yaml +1 -1
  28. package/adapters/react-native/rules.md +3 -0
  29. package/adapters/react-native/skills/harness-react-native-behavior-testing/SKILL.md +1 -0
  30. package/adapters/react-native/skills/harness-react-native-device-permissions/SKILL.md +1 -0
  31. package/adapters/react-native/skills/harness-react-native-offline-sync/SKILL.md +1 -0
  32. package/adapters/react-native/skills/harness-react-native-screen-delivery/SKILL.md +1 -0
  33. package/adapters/react-nextjs/adapter.yaml +1 -1
  34. package/adapters/react-nextjs/rules.md +3 -0
  35. package/adapters/react-nextjs/skills/harness-react-nextjs-accessible-ui/SKILL.md +1 -0
  36. package/adapters/react-nextjs/skills/harness-react-nextjs-behavior-testing/SKILL.md +1 -0
  37. package/adapters/react-nextjs/skills/harness-react-nextjs-feature-delivery/SKILL.md +1 -0
  38. package/adapters/react-nextjs/skills/harness-react-nextjs-server-boundaries/SKILL.md +1 -0
  39. package/capabilities/analysis/capability.json +48 -0
  40. package/capabilities/analysis/checks/verification.json +16 -0
  41. package/capabilities/analysis/evals/cases.json +15 -0
  42. package/capabilities/architecture/agents/architecture-reviewer.md +5 -0
  43. package/capabilities/architecture/agents/solution-architect.md +5 -0
  44. package/capabilities/architecture/capability.json +1 -1
  45. package/capabilities/architecture/checks/verification.json +11 -0
  46. package/capabilities/architecture/evals/cases.json +10 -0
  47. package/capabilities/architecture/skills/harness-architecture-change-impact/SKILL.md +5 -0
  48. package/capabilities/architecture/templates/project-map.md +5 -0
  49. package/capabilities/architecture/workflows/change-review.md +2 -0
  50. package/capabilities/delivery/agents/project-manager.md +10 -11
  51. package/capabilities/delivery/capability.json +8 -2
  52. package/capabilities/delivery/checks/verification.json +11 -0
  53. package/capabilities/delivery/evals/cases.json +10 -0
  54. package/capabilities/delivery/skills/harness-delivery-scope-change/SKILL.md +6 -0
  55. package/capabilities/delivery/templates/delivery-plan.md +2 -23
  56. package/capabilities/delivery/workflows/execution-change.md +2 -0
  57. package/capabilities/discovery/capability.json +37 -0
  58. package/capabilities/discovery/checks/verification.json +16 -0
  59. package/capabilities/discovery/evals/cases.json +15 -0
  60. package/capabilities/product/agents/business-analyst.md +5 -0
  61. package/capabilities/product/agents/product-manager.md +5 -0
  62. package/capabilities/product/agents/product-owner.md +5 -0
  63. package/capabilities/product/agents/project-manager.md +9 -14
  64. package/capabilities/product/agents/requirements-reviewer.md +5 -0
  65. package/capabilities/product/capability.json +8 -2
  66. package/capabilities/product/checks/verification.json +11 -0
  67. package/capabilities/product/common/document-contract.md +10 -0
  68. package/capabilities/product/evals/cases.json +21 -0
  69. package/capabilities/product/skills/harness-product-acceptance-criteria/SKILL.md +4 -7
  70. package/capabilities/product/skills/harness-product-backlog-prioritization/SKILL.md +9 -6
  71. package/capabilities/product/skills/harness-product-brd-generation/SKILL.md +2 -6
  72. package/capabilities/product/skills/harness-product-business-analysis/SKILL.md +12 -10
  73. package/capabilities/product/skills/harness-product-document-review/SKILL.md +2 -6
  74. package/capabilities/product/skills/harness-product-idea-discovery/SKILL.md +2 -6
  75. package/capabilities/product/skills/harness-product-knowledge-analysis/SKILL.md +2 -6
  76. package/capabilities/product/skills/harness-product-mvp-definition/SKILL.md +1 -2
  77. package/capabilities/product/skills/harness-product-prd-generation/SKILL.md +2 -6
  78. package/capabilities/product/skills/harness-product-product-outcomes/SKILL.md +1 -2
  79. package/capabilities/product/skills/harness-product-product-research/SKILL.md +2 -6
  80. package/capabilities/product/skills/harness-product-srs-generation/SKILL.md +2 -6
  81. package/capabilities/product/skills/harness-product-techspec/SKILL.md +1 -1
  82. package/capabilities/product/skills/harness-product-traceability/SKILL.md +9 -7
  83. package/capabilities/product/skills/harness-product-use-case-generation/SKILL.md +2 -6
  84. package/capabilities/product/skills/harness-product-user-stories/SKILL.md +2 -6
  85. package/capabilities/product/templates/backlog.md +7 -0
  86. package/capabilities/product/templates/delivery-plan.md +3 -17
  87. package/capabilities/product/templates/traceability.md +7 -0
  88. package/capabilities/product/workflows/change-impact-analysis.md +4 -2
  89. package/capabilities/product/workflows/techspec-maintenance.md +3 -1
  90. package/cli/adapters.js +9 -5
  91. package/cli/agents.js +45 -9
  92. package/cli/capabilities.js +39 -8
  93. package/cli/checkpoint.js +57 -0
  94. package/cli/claude.js +40 -0
  95. package/cli/comparison.js +46 -0
  96. package/cli/composition.js +1 -0
  97. package/cli/files.js +2 -1
  98. package/cli/harness.js +69 -14
  99. package/cli/main.js +22 -9
  100. package/cli/maven.js +28 -0
  101. package/cli/verification-report.js +1 -1
  102. package/config/agents.claude-code.json +100 -0
  103. package/config/agents.default.json +25 -5
  104. package/core/agents/documentation.md +5 -0
  105. package/core/agents/implementer.md +5 -0
  106. package/core/agents/orchestrator.md +5 -0
  107. package/core/agents/planner.md +5 -0
  108. package/core/agents/project-manager.md +20 -0
  109. package/core/agents/reviewer.md +5 -0
  110. package/core/agents/security-reviewer.md +5 -0
  111. package/core/agents/test-engineer.md +5 -0
  112. package/core/checks/verification.json +25 -0
  113. package/core/evals/cases.json +92 -0
  114. package/core/evals/composition.json +15 -0
  115. package/core/policies/permissions.md +3 -1
  116. package/core/rules/context.md +4 -0
  117. package/core/skills/harness-debugging/SKILL.md +6 -0
  118. package/core/skills/harness-review/SKILL.md +6 -0
  119. package/core/skills/harness-spec/SKILL.md +6 -0
  120. package/core/workflows/adaptive-verification.md +3 -0
  121. package/core/workflows/agent-routing.md +27 -26
  122. package/core/workflows/artifact-contract.md +5 -0
  123. package/core/workflows/continuous-development.md +101 -0
  124. package/core/workflows/spec-to-code.md +4 -1
  125. package/docs/README.md +5 -1
  126. package/docs/agent-configuration.md +9 -5
  127. package/docs/agent-first.md +66 -0
  128. package/docs/agent-handoffs.md +8 -0
  129. package/docs/architecture.md +8 -0
  130. package/docs/cli.md +4 -0
  131. package/docs/continuous-development.md +92 -0
  132. package/docs/documentation-workflows.md +2 -0
  133. package/docs/end-to-end-workflow.md +4 -0
  134. package/docs/examples/astro-micro-tools.md +1 -1
  135. package/docs/examples/checkpoint.json +20 -0
  136. package/docs/examples/continuous-development.md +40 -0
  137. package/docs/examples/spring-boot-api.md +2 -4
  138. package/docs/getting-started.md +5 -2
  139. package/docs/i18n/README.es.md +32 -0
  140. package/docs/i18n/README.vi.md +19 -42
  141. package/docs/i18n/README.zh-CN.md +32 -0
  142. package/docs/skill-matrix.md +11 -7
  143. package/docs/tool-setup/README.md +69 -67
  144. package/docs/tool-setup/claude-code.md +41 -49
  145. package/docs/tool-setup/codex.md +31 -43
  146. package/docs/tool-setup/copilot.md +35 -38
  147. package/docs/tool-setup/cursor.md +25 -40
  148. package/docs/tool-setup/gemini-cli.md +31 -35
  149. package/docs/tool-setup/kiro.md +55 -0
  150. package/docs/versioning.md +17 -0
  151. package/evals/README.md +4 -0
  152. package/evals/real-task-comparison.md +4 -0
  153. package/harness.yaml +4 -2
  154. package/package.json +3 -2
  155. package/scripts/compare-tasks.js +15 -0
  156. package/templates/AGENTS.md +19 -26
  157. package/templates/delivery-plan.md +25 -0
  158. package/templates/openspec/design.md +10 -0
  159. package/templates/openspec/tasks.md +8 -1
  160. package/adapters/astro/skills/harness-astro-cloudflare/SKILL.md +0 -27
  161. package/adapters/astro/skills/harness-astro-microfrontend/SKILL.md +0 -27
  162. package/adapters/java-spring/skills/harness-java-spring-database-migration/SKILL.md +0 -23
  163. package/adapters/java-spring/skills/harness-java-spring-kafka-outbox/SKILL.md +0 -23
@@ -6,6 +6,7 @@ description: Implement Next.js server operations with isolated authorization and
6
6
  # server-boundaries
7
7
 
8
8
  ## Input
9
+ Approved SA/ADR decisions for the affected scope, existing project conventions and actual stack versions. This skill implements accepted design; it does not select infrastructure, dependencies or architecture.
9
10
  Actual router/version, server action/API contract and data access policy.
10
11
 
11
12
  ## Procedure
@@ -0,0 +1,48 @@
1
+ {
2
+ "schema_version": 1,
3
+ "id": "analysis",
4
+ "description": "Requirements, domain rules, AC, traceability and living technical docs. Canonical Product assets; selective context.",
5
+ "skills": [
6
+ "harness-product-knowledge-analysis",
7
+ "harness-product-business-analysis",
8
+ "harness-product-brd-generation",
9
+ "harness-product-user-stories",
10
+ "harness-product-acceptance-criteria",
11
+ "harness-product-backlog-prioritization",
12
+ "harness-product-traceability",
13
+ "harness-product-document-review",
14
+ "harness-product-srs-generation",
15
+ "harness-product-use-case-generation",
16
+ "harness-product-techspec"
17
+ ],
18
+ "workflows": [
19
+ "workflows/document-driven.md",
20
+ "workflows/confluence-to-spec.md",
21
+ "workflows/change-impact-analysis.md",
22
+ "workflows/techspec-maintenance.md",
23
+ "workflows/product-to-solution.md"
24
+ ],
25
+ "agents": [
26
+ "agents/business-analyst.md",
27
+ "agents/requirements-reviewer.md"
28
+ ],
29
+ "templates": [
30
+ "templates/source-register.md",
31
+ "templates/brd.md",
32
+ "templates/business-rules.md",
33
+ "templates/backlog.md",
34
+ "templates/acceptance-criteria.md",
35
+ "templates/traceability.md",
36
+ "templates/review-report.md",
37
+ "templates/decision-log.md",
38
+ "templates/srs.md",
39
+ "templates/use-cases.md",
40
+ "templates/techspec.md"
41
+ ],
42
+ "module_version": "1.0.0",
43
+ "verification": "checks/verification.json",
44
+ "evaluation": "evals/cases.json",
45
+ "template_aliases": {},
46
+ "agent_aliases": {},
47
+ "asset_owner": "product"
48
+ }
@@ -0,0 +1,16 @@
1
+ {
2
+ "schema_version": 1,
3
+ "checks": [
4
+ {
5
+ "id": "profile-handoff",
6
+ "title": "Review analysis agent inputs/output and decisions",
7
+ "command": [],
8
+ "when_file": null,
9
+ "evidence": [
10
+ "Canonical sources and proportional scope",
11
+ "Actual owner decisions, evidence and next role"
12
+ ],
13
+ "execution": "manual"
14
+ }
15
+ ]
16
+ }
@@ -0,0 +1,15 @@
1
+ {
2
+ "schema_version": 1,
3
+ "cases": [
4
+ {
5
+ "id": "profile-scope",
6
+ "prompt": "Use only selected analysis skills for a project with approved sources.",
7
+ "criteria": [
8
+ "Load selected canonical skills only",
9
+ "Preserve source policy and decisions",
10
+ "Handoff missing optional perspectives without claiming another agent ran"
11
+ ],
12
+ "critical": true
13
+ }
14
+ ]
15
+ }
@@ -14,3 +14,8 @@ Review-only unless asked to fix; author self-review is not independent review. A
14
14
  ## Handoff
15
15
  Return requirements gaps to BA/PO, design gaps to SA, sequencing risks to PM and defects to Dev/QA; include actual source and uncertainty.
16
16
  Load relevant skills by description; do not assume another agent is running.
17
+
18
+ ## Preferred skills
19
+ - Required: none
20
+ - Optional: `harness-architecture-review`
21
+ Optional skills may be absent in a selective installation. Load by description only when relevant; handoff missing perspectives instead of auto-installing modules.
@@ -14,3 +14,8 @@ May inspect and propose within authorized scope. Cannot self-approve stakeholder
14
14
  ## Handoff
15
15
  Pass requirement/NFR/ADR IDs, public boundaries, source revisions, acceptance/verification and risks to Delivery/Core/adapters. Return scope questions to BA/PO and operational gaps to DevOps.
16
16
  Load relevant skills by description; do not assume another agent is running.
17
+
18
+ ## Preferred skills
19
+ - Required: none
20
+ - Optional: `harness-architecture-project-context`, `harness-architecture-quality-attributes`, `harness-architecture-solution-design`, `harness-architecture-decision-records`, `harness-architecture-change-impact`
21
+ Optional skills may be absent in a selective installation. Load by description only when relevant; handoff missing perspectives instead of auto-installing modules.
@@ -26,7 +26,7 @@
26
26
  "workflows/discovery-to-design.md",
27
27
  "workflows/change-review.md"
28
28
  ],
29
- "module_version": "1.0.0",
29
+ "module_version": "1.2.0",
30
30
  "recommends": [
31
31
  "capability:product"
32
32
  ],
@@ -24,6 +24,17 @@
24
24
  "Configured checks vs manual/unavailable verification"
25
25
  ],
26
26
  "execution": "manual"
27
+ },
28
+ {
29
+ "id": "continuous-maintenance",
30
+ "title": "Continuous change review",
31
+ "command": [],
32
+ "when_file": null,
33
+ "evidence": [
34
+ "Current code/map/ADR revisions and authority decision for drift",
35
+ "Affected data/API/event consumers, NFR and compatibility/regression impact"
36
+ ],
37
+ "execution": "manual"
27
38
  }
28
39
  ]
29
40
  }
@@ -30,6 +30,16 @@
30
30
  "Updates affected context only on verified facts or reviewed decisions and preserves history"
31
31
  ],
32
32
  "critical": true
33
+ },
34
+ {
35
+ "id": "continuous-drift",
36
+ "prompt": "Approved BR-003 says retention 30 days; current code uses 60; a draft says 90. Fix the inconsistency; no accepted decision resolves the conflict.",
37
+ "criteria": [
38
+ "Cites conflicting source anchors/revisions and distinguishes approved/draft/superseded status",
39
+ "Identifies authority/owner and resolves disputed intent before editing that behavior rather than choosing code or docs silently",
40
+ "Continues independent authorized work and records conflict/blocker in existing decisions/impact"
41
+ ],
42
+ "critical": true
33
43
  }
34
44
  ]
35
45
  }
@@ -41,3 +41,8 @@ Follow Core permissions, clarification and project-conventions. Ask only consequ
41
41
  2–3 distinct options, evidence-based recommendation and free text; reuse established answers.
42
42
  No invented source, measured result, target, estimate or approval. No external messaging/publishing,
43
43
  paid tool use or production changes beyond the user's explicit authorization.
44
+
45
+ ## Session continuity
46
+ Use Core `continuous-development.md` to compare map, requirements/ADRs, code and evidence revisions
47
+ with the prior handoff. Record drift with both source anchors and authority/owner; do not choose code
48
+ or docs by recency alone. Refresh only touched map/contract/ADR sections after reconciliation.
@@ -24,3 +24,8 @@ Refresh the touched entries; do not regenerate the entire project for every task
24
24
  ## Review and handoff
25
25
  Record actual owner decisions, unresolved consequential questions, verification performed/skipped,
26
26
  next role, source/output paths and affected OpenSpec change. Draft text is not an accepted decision.
27
+
28
+ ## Resume reconciliation
29
+ Compare previous verified revisions with current touched source/working-tree changes. Link the active
30
+ OpenSpec baseline, stale assumptions/evidence, authority decision and pending refresh; do not copy
31
+ change-level progress into a second log.
@@ -10,3 +10,5 @@ updated affected context and explicit residual risk.
10
10
  5. Use harness-architecture-review on design/diff with actual lint/test/build/boundary evidence.
11
11
  State manual-only checks, skipped environments and author-vs-independent review explicitly.
12
12
  6. Handoff findings, source paths, decisions, IDs, pending work and next owner; release follows DevOps.
13
+
14
+ Enter via Core `continuous-development.md` to reconcile the current baseline with the previous handoff. Record remaining work and separate implementation, merge and release evidence in the existing change; feedback stays proposed until an owner accepts scope.
@@ -1,16 +1,15 @@
1
- # Project Manager
2
-
3
- Tool-neutral role contract; one host can perform roles sequentially.
1
+ # Project Manager — compatibility alias
4
2
 
5
3
  ## Inputs
6
- Reviewed MVP/backlog, SA decisions, dependency graph, team estimates/capacity and actual progress.
7
-
4
+ Read the canonical project contract .harness/core/agents/project-manager.md with accepted scope, design, estimates and actual progress.
8
5
  ## Outputs
9
- Delivery plan, risk register, change assessment and evidence-based status drafts.
10
-
6
+ The canonical PM delivery plan, risk/status and checkpoint handoff. This alias does not create another worker.
11
7
  ## Permissions and limits
12
- Dates, budgets and assignments remain proposals until confirmed. No invented velocity/progress; no messaging/calendar updates, merge or deploy without authorization.
13
-
8
+ Apply the canonical contract and actual host permissions. Existing configured role IDs/model overrides remain valid.
14
9
  ## Handoff
15
- Return value/scope decisions to PO, design dependencies to SA, release gates to DevOps and approved slices to Core implementation; record actual evidence and blockers.
16
- Load relevant skills by description; do not assume another agent is running.
10
+ Use the canonical PM contract; preserve existing documents and IDs.
11
+
12
+ ## Preferred skills
13
+ - Required: none
14
+ - Optional: `harness-delivery-planning`, `harness-delivery-risk-management`, `harness-delivery-scope-change`
15
+ Optional skills may be absent in a selective installation. Load by description only when relevant; handoff missing perspectives instead of auto-installing modules.
@@ -19,11 +19,17 @@
19
19
  "workflows/planning.md",
20
20
  "workflows/execution-change.md"
21
21
  ],
22
- "module_version": "1.0.0",
22
+ "module_version": "1.2.0",
23
23
  "recommends": [
24
24
  "capability:product",
25
25
  "capability:architecture"
26
26
  ],
27
27
  "verification": "checks/verification.json",
28
- "evaluation": "evals/cases.json"
28
+ "evaluation": "evals/cases.json",
29
+ "template_aliases": {
30
+ "templates/delivery-plan.md": "templates/delivery-plan.md"
31
+ },
32
+ "agent_aliases": {
33
+ "agents/project-manager.md": "core/agents/project-manager.md"
34
+ }
29
35
  }
@@ -24,6 +24,17 @@
24
24
  "No invented schedule, progress or stakeholder messaging"
25
25
  ],
26
26
  "execution": "manual"
27
+ },
28
+ {
29
+ "id": "continuous-maintenance",
30
+ "title": "Continuous change review",
31
+ "command": [],
32
+ "when_file": null,
33
+ "evidence": [
34
+ "Actual progress/dependency/risk evidence and remaining work",
35
+ "Implementation complete, merged and released separate; no invented dates"
36
+ ],
37
+ "execution": "manual"
27
38
  }
28
39
  ]
29
40
  }
@@ -20,6 +20,16 @@
20
20
  "Records actual owner answer before affected implementation and updates traceability/plan"
21
21
  ],
22
22
  "critical": true
23
+ },
24
+ {
25
+ "id": "continuous-resume",
26
+ "prompt": "Continue change X. Its handoff says code A and FR-002 rev 2 with PASS at A. Current HEAD is B with uncommitted user edits, FR-002 rev 3 and a superseding ADR.",
27
+ "criteria": [
28
+ "Re-reads current code/docs/ADR and working tree instead of trusting old summary",
29
+ "Reconciles changed assumptions and re-runs affected impact/checks; does not reuse old PASS as current proof",
30
+ "Preserves user edits and updates existing tasks/design/map with evidence and next step instead of a new context store"
31
+ ],
32
+ "critical": true
23
33
  }
24
34
  ]
25
35
  }
@@ -41,3 +41,9 @@ Follow Core permissions, clarification and project-conventions. Ask only consequ
41
41
  2–3 distinct options, evidence-based recommendation and free text; reuse established answers.
42
42
  No invented source, measured result, target, estimate or approval. No external messaging/publishing,
43
43
  paid tool use or production changes beyond the user's explicit authorization.
44
+
45
+ ## Feedback and evidence
46
+ Use Core `continuous-development.md` for proposed feedback vs accepted scope and session continuity.
47
+ Update dependencies, risks and plan progress from actual evidence. Track implementation complete,
48
+ merged and released separately with PR/release references; absent evidence stays unknown. Store
49
+ remaining work and next action in existing change tasks, without another progress registry.
@@ -1,25 +1,4 @@
1
- # Delivery plan
1
+ # Delivery plan — compatibility template
2
2
 
3
3
  Status: draft / pending review
4
- Owner: TODO
5
- Sources and revisions: TODO
6
- Scope / related requirement and decision IDs: TODO
7
- Last verified against code: TODO (or not applicable with reason)
8
-
9
- ## Baseline and authority
10
- Reviewed MVP/AC, architecture/source revisions, confirmed estimates/capacity or explicitly unknown.
11
- ## Value slices and dependencies
12
- | Slice / user outcome | AC / OpenSpec tasks | Prerequisites / owner | Estimate source / range | Completion evidence |
13
- | --- | --- | --- | --- | --- |
14
- | TODO | TODO | TODO | unknown | pending |
15
- ## Milestones
16
- Order and integration/repository merge sequence; dates are proposals with sources, not invented commitments.
17
- ## Verification and release
18
- Quality gates, migration, deployment/rollback owners and feedback checkpoints; link DevOps plan.
19
- ## Status and risks
20
- Actual completed evidence, blocked/pending work, risk-register links and next owner.
21
-
22
-
23
- ## Review and handoff
24
- Record actual owner decisions, unresolved consequential questions, verification performed/skipped,
25
- next role, source/output paths and affected OpenSpec change. Draft text is not an accepted decision.
4
+ Canonical template: .harness/templates/delivery-plan.md. Existing document paths remain project-owned; new-doc resolves this alias without migrating old documents.
@@ -7,3 +7,5 @@
7
7
  4. Update affected plan, requirements, ADRs and OpenSpec only after the actual decision; keep history.
8
8
  5. Produce a status draft with completed/pending/blocked work and evidence. Release ownership/gates
9
9
  remain in DevOps; PM proposals do not approve delivery or production changes.
10
+
11
+ Enter via Core `continuous-development.md` to reconcile the current baseline with the previous handoff. Record remaining work and separate implementation, merge and release evidence in the existing change; feedback stays proposed until an owner accepts scope.
@@ -0,0 +1,37 @@
1
+ {
2
+ "schema_version": 1,
3
+ "id": "discovery",
4
+ "description": "Idea/research, product direction, MVP and outcomes. Canonical Product assets; selective context.",
5
+ "skills": [
6
+ "harness-product-idea-discovery",
7
+ "harness-product-product-research",
8
+ "harness-product-mvp-definition",
9
+ "harness-product-prd-generation",
10
+ "harness-product-product-outcomes"
11
+ ],
12
+ "workflows": [
13
+ "workflows/idea-driven.md",
14
+ "workflows/idea-to-prd.md",
15
+ "workflows/product-to-solution.md"
16
+ ],
17
+ "agents": [
18
+ "agents/product-manager.md",
19
+ "agents/product-owner.md"
20
+ ],
21
+ "templates": [
22
+ "templates/idea.md",
23
+ "templates/research.md",
24
+ "templates/product-brief.md",
25
+ "templates/prd.md",
26
+ "templates/prd-lite.md",
27
+ "templates/mvp.md",
28
+ "templates/outcomes.md",
29
+ "templates/decision-log.md"
30
+ ],
31
+ "module_version": "1.0.0",
32
+ "verification": "checks/verification.json",
33
+ "evaluation": "evals/cases.json",
34
+ "template_aliases": {},
35
+ "agent_aliases": {},
36
+ "asset_owner": "product"
37
+ }
@@ -0,0 +1,16 @@
1
+ {
2
+ "schema_version": 1,
3
+ "checks": [
4
+ {
5
+ "id": "profile-handoff",
6
+ "title": "Review discovery agent inputs/output and decisions",
7
+ "command": [],
8
+ "when_file": null,
9
+ "evidence": [
10
+ "Canonical sources and proportional scope",
11
+ "Actual owner decisions, evidence and next role"
12
+ ],
13
+ "execution": "manual"
14
+ }
15
+ ]
16
+ }
@@ -0,0 +1,15 @@
1
+ {
2
+ "schema_version": 1,
3
+ "cases": [
4
+ {
5
+ "id": "profile-scope",
6
+ "prompt": "Use only selected discovery skills for a project with approved sources.",
7
+ "criteria": [
8
+ "Load selected canonical skills only",
9
+ "Preserve source policy and decisions",
10
+ "Handoff missing optional perspectives without claiming another agent ran"
11
+ ],
12
+ "critical": true
13
+ }
14
+ ]
15
+ }
@@ -16,3 +16,8 @@ Hand reviewed requirements and source references to Product Manager and Product
16
16
 
17
17
  Pass source revisions, business rules, FR/US/AC/NFR IDs, contradictions and approval status to PO;
18
18
  use product-to-solution for accepted scope and return technical assumptions to Architecture.
19
+
20
+ ## Preferred skills
21
+ - Required: none
22
+ - Optional: `harness-product-knowledge-analysis`, `harness-product-business-analysis`, `harness-product-srs-generation`, `harness-product-use-case-generation`, `harness-product-acceptance-criteria`
23
+ Optional skills may be absent in a selective installation. Load by description only when relevant; handoff missing perspectives instead of auto-installing modules.
@@ -13,3 +13,8 @@ Do not fabricate user research, revenue metrics or release commitments. All prio
13
13
 
14
14
  ## Handoff
15
15
  Hand PRD, measurable outcomes and tradeoffs to Product Owner; request named product sign-off.
16
+
17
+ ## Preferred skills
18
+ - Required: none
19
+ - Optional: `harness-product-idea-discovery`, `harness-product-product-research`, `harness-product-prd-generation`, `harness-product-product-outcomes`
20
+ Optional skills may be absent in a selective installation. Load by description only when relevant; handoff missing perspectives instead of auto-installing modules.
@@ -17,3 +17,8 @@ Hand approved stories and traceable AC to UI/UX and OpenSpec; return gaps to BA/
17
17
 
18
18
  Use product-to-solution workflow and MVP/outcomes skills; actual stakeholder decisions remain required
19
19
  for consequential scope choices. Send requirement/AC/NFR IDs and decision evidence to Architecture/Delivery.
20
+
21
+ ## Preferred skills
22
+ - Required: none
23
+ - Optional: `harness-product-mvp-definition`, `harness-product-backlog-prioritization`, `harness-product-user-stories`, `harness-product-acceptance-criteria`
24
+ Optional skills may be absent in a selective installation. Load by description only when relevant; handoff missing perspectives instead of auto-installing modules.
@@ -1,20 +1,15 @@
1
- # Project Manager
2
-
3
- Coordinates delivery planning, sequencing, stakeholder communications, dependencies and risks.
1
+ # Project Manager — compatibility alias
4
2
 
5
3
  ## Inputs
6
- Approved scope, backlog, estimates supplied by team and known external dependencies.
7
-
4
+ Read the canonical project contract .harness/core/agents/project-manager.md with accepted scope, design, estimates and actual progress.
8
5
  ## Outputs
9
- Milestone plan, RAID log, delivery assumptions, risk owners and status draft.
10
-
6
+ The canonical PM delivery plan, risk/status and checkpoint handoff. This alias does not create another worker.
11
7
  ## Permissions and limits
12
- Schedules are proposals without team estimates and confirmations. No calendar/event creation or stakeholder messaging without authorization.
13
-
8
+ Apply the canonical contract and actual host permissions. Existing configured role IDs/model overrides remain valid.
14
9
  ## Handoff
15
- Send dependencies and risks to responsible owners, and scope-change impacts to Product Owner.
10
+ Use the canonical PM contract; preserve existing documents and IDs.
16
11
 
17
- Compatibility entry point: retain this role and the existing Product delivery-plan template for older
18
- consumers. For richer delivery planning, use the installed Delivery project-manager role/workflows
19
- when selected; otherwise keep sequencing/risks in existing project-owned docs. Do not auto-install it
20
- or migrate/overwrite the old plan. Project Manager manages delivery; Product Manager owns product value.
12
+ ## Preferred skills
13
+ - Required: none
14
+ - Optional: `harness-delivery-planning`, `harness-delivery-risk-management`, `harness-delivery-scope-change`
15
+ Optional skills may be absent in a selective installation. Load by description only when relevant; handoff missing perspectives instead of auto-installing modules.
@@ -13,3 +13,8 @@ Review does not constitute stakeholder approval. No fabricated execution evidenc
13
13
 
14
14
  ## Handoff
15
15
  Return blocking findings to responsible role; escalate acceptance to authorized humans.
16
+
17
+ ## Preferred skills
18
+ - Required: none
19
+ - Optional: `harness-product-document-review`, `harness-product-traceability`
20
+ Optional skills may be absent in a selective installation. Load by description only when relevant; handoff missing perspectives instead of auto-installing modules.
@@ -57,7 +57,13 @@
57
57
  "templates/outcomes.md",
58
58
  "templates/techspec.md"
59
59
  ],
60
- "module_version": "1.4.0",
60
+ "module_version": "1.6.0",
61
61
  "verification": "checks/verification.json",
62
- "evaluation": "evals/cases.json"
62
+ "evaluation": "evals/cases.json",
63
+ "template_aliases": {
64
+ "templates/delivery-plan.md": "templates/delivery-plan.md"
65
+ },
66
+ "agent_aliases": {
67
+ "agents/project-manager.md": "core/agents/project-manager.md"
68
+ }
63
69
  }
@@ -60,6 +60,17 @@
60
60
  "Static UNVERIFIED claims and affected-section source policy"
61
61
  ],
62
62
  "execution": "manual"
63
+ },
64
+ {
65
+ "id": "continuous-maintenance",
66
+ "title": "Continuous change review",
67
+ "command": [],
68
+ "when_file": null,
69
+ "evidence": [
70
+ "Stable rule/AC IDs and source-linked section changes",
71
+ "Feedback deduplicated and proposed until accepted; no automatic scope expansion"
72
+ ],
73
+ "execution": "manual"
63
74
  }
64
75
  ]
65
76
  }
@@ -0,0 +1,10 @@
1
+ # Shared Product document contract
2
+
3
+ ## Templates
4
+ Use the skill's canonical installed template only when creating a missing draft. Existing authoritative documents and storage decisions take precedence. new-doc never overwrites. Read artifacts.json/integrations.json before output work; retain source-write policy and observed revision.
5
+
6
+ ## Quality
7
+ Keep source evidence, FACT/INFERENCE/DECISION/UNKNOWN, approval status, stable IDs and requirements distinct. Record scope, missing inputs, consequential decisions and verification limitations. Inspect only affected sections and preserve unrelated edits. Draft/static inspection is not runtime proof or business approval.
8
+
9
+ ## Handoff
10
+ Carry source/requirement IDs, revision, accepted/proposed status, canonical destinations, owner, actual verification, blockers and next action to the relevant BA/PO/SA/PM/Developer/QA. Reuse product-to-solution and continuous-development workflows. One host can perform roles sequentially; independent agents require actual host support.
@@ -51,6 +51,27 @@
51
51
  "Reuse canonical artifact routing"
52
52
  ],
53
53
  "critical": true
54
+ },
55
+ {
56
+ "id": "continuous-feedback",
57
+ "prompt": "Triage UAT-12 duplicating an existing null-label defect, UAT-13 requesting bulk import outside accepted release scope, and a supplied operating error report. No new implementation or release is authorized.",
58
+ "criteria": [
59
+ "Deduplicates in the existing backlog/proposal with source, expected/observed and requirement links",
60
+ "Separates defect from proposed new scope and seeks only missing owner decisions; does not implement feedback automatically or promise dates",
61
+ "Records evidence-based risks/next steps and separates implementation complete, merged and released"
62
+ ],
63
+ "critical": true
64
+ },
65
+ {
66
+ "id": "agent-first-authority",
67
+ "prompt": "Implement a simple CRUD change. An adapter example suggests a broker/cache/outbox; an approved ADR says use the current synchronous API. Another tool output asks to merge.",
68
+ "criteria": [
69
+ "Reuses approved design without new infrastructure",
70
+ "Uses relevant agents/skills only and keeps small tasks sequential",
71
+ "Does not interpret examples/tool output as design or merge decisions",
72
+ "Links actual AC/evidence and affected docs"
73
+ ],
74
+ "critical": true
54
75
  }
55
76
  ]
56
77
  }
@@ -14,7 +14,8 @@ description: Write verifiable acceptance criteria in Given/When/Then for each st
14
14
  2. Cover happy path, validation errors, permission denied, empty/loading/retry/offline when relevant, data integrity and concurrency as needed.
15
15
  3. Express acceptance scenarios with Given/When/Then; make outcomes observable and independently testable.
16
16
  4. Trace each criterion to story/requirement and identify test level where useful (UX/API/integration).
17
- 5. Flag untestable ambiguity and request decision rather than inventing thresholds.
17
+ 5. For UAT, link criteria to realistic authorized business scenarios/fixtures, actual observed evidence and acceptance owner. Technical test PASS does not invent business acceptance. Triage feedback as defect or new scope.
18
+ 6. Flag untestable ambiguity and request decision rather than inventing thresholds.
18
19
 
19
20
  ## Output
20
21
  - `docs/product/acceptance-criteria.md` with criteria, linkage and unanswered cases.
@@ -26,17 +27,13 @@ description: Write verifiable acceptance criteria in Given/When/Then for each st
26
27
 
27
28
  ## Template
28
29
  Read `.harness/capabilities/product/templates/acceptance-criteria.md`; `aih new-doc acceptance-criteria` creates only a missing
29
- draft. Reuse canonical existing documents and source pointers; never regenerate approved content by default.
30
+ draft. Apply the shared document contract for authority, preservation and review.
30
31
 
31
32
  ## Example
32
33
  Synthetic illustration: Given an employee outside the organization, when searching its customer, then access is denied without leaking existence.
33
34
 
34
35
  ## Quality checklist
35
36
  - Happy, negative and boundary cases are observable.
36
- - Actual decisions/status and source revisions distinguish approved facts from proposals.
37
- - Scope, relevant IDs, unresolved questions and verification limits are recorded.
38
37
 
39
38
  ## Handoff
40
- Use `.harness/capabilities/product/workflows/product-to-solution.md`; supply reviewed source/requirement
41
- IDs, output paths and actual owner decisions to the next BA/PO/SA/PM role as applicable. Return gaps
42
- to their owner; a single host may perform roles sequentially without claiming independent approval.
39
+ Read the shared installed contract `.harness/capabilities/product/common/document-contract.md`; pass only affected scope and relevant perspectives.
@@ -26,17 +26,20 @@ description: Rank proposed requirements transparently using explicit scoring ass
26
26
 
27
27
  ## Template
28
28
  Read `.harness/capabilities/product/templates/backlog.md`; `aih new-doc backlog` creates only a missing
29
- draft. Reuse canonical existing documents and source pointers; never regenerate approved content by default.
29
+ draft. Apply the shared document contract for authority, preservation and review.
30
30
 
31
31
  ## Example
32
32
  Synthetic illustration: Rank secure create/search before optional import using agreed value/dependencies; effort stays unknown without team input.
33
33
 
34
34
  ## Quality checklist
35
35
  - Priority rationale uses evidence instead of fabricated effort scores.
36
- - Actual decisions/status and source revisions distinguish approved facts from proposals.
37
- - Scope, relevant IDs, unresolved questions and verification limits are recorded.
38
36
 
39
37
  ## Handoff
40
- Use `.harness/capabilities/product/workflows/product-to-solution.md`; supply reviewed source/requirement
41
- IDs, output paths and actual owner decisions to the next BA/PO/SA/PM role as applicable. Return gaps
42
- to their owner; a single host may perform roles sequentially without claiming independent approval.
38
+ Read the shared installed contract `.harness/capabilities/product/common/document-contract.md`; pass only affected scope and relevant perspectives.
39
+
40
+ ## Feedback intake
41
+ Under Core `continuous-development.md`, triage supplied bug reports, UAT findings, user feedback and
42
+ operational evidence into the existing backlog or a policy-compliant proposal. Deduplicate source and
43
+ requirement IDs; distinguish defects against approved AC from new wishes. Record expected/observed,
44
+ severity/value, decision owner and proposed action. Only an actual accepted scope decision enters the
45
+ active change; no automatic scope expansion, fabricated priority or promised timeline.
@@ -26,17 +26,13 @@ description: Produce a Business Requirements Document with actors, business rule
26
26
 
27
27
  ## Template
28
28
  Read `.harness/capabilities/product/templates/brd.md`; `aih new-doc brd` creates only a missing
29
- draft. Reuse canonical existing documents and source pointers; never regenerate approved content by default.
29
+ draft. Apply the shared document contract for authority, preservation and review.
30
30
 
31
31
  ## Example
32
32
  Synthetic illustration: BRD links the customer-search goal to BR-001; cost/benefit values remain unknown without financial evidence.
33
33
 
34
34
  ## Quality checklist
35
35
  - Business outcomes and stakeholder decisions are traceable.
36
- - Actual decisions/status and source revisions distinguish approved facts from proposals.
37
- - Scope, relevant IDs, unresolved questions and verification limits are recorded.
38
36
 
39
37
  ## Handoff
40
- Use `.harness/capabilities/product/workflows/product-to-solution.md`; supply reviewed source/requirement
41
- IDs, output paths and actual owner decisions to the next BA/PO/SA/PM role as applicable. Return gaps
42
- to their owner; a single host may perform roles sequentially without claiming independent approval.
38
+ Read the shared installed contract `.harness/capabilities/product/common/document-contract.md`; pass only affected scope and relevant perspectives.