@llipe.com/dev-tasks 0.10.0 → 0.11.0

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 (39) hide show
  1. package/.claude/agents/developer.md +11 -0
  2. package/.claude/agents/qa-engineer.md +31 -2
  3. package/.claude/agents/researcher.md +96 -0
  4. package/.claude/commands/planner.md +22 -7
  5. package/.claude/commands/product-engineer.md +37 -10
  6. package/.claude/commands/researcher.md +28 -0
  7. package/.claude/skills/activity-codebase-research/SKILL.md +158 -0
  8. package/.claude/skills/activity-contract-validation/SKILL.md +167 -0
  9. package/.claude/skills/activity-e2e-test-implementation/SKILL.md +156 -0
  10. package/.claude/skills/activity-integration-test-implementation/SKILL.md +156 -0
  11. package/.claude/skills/activity-test-standards/SKILL.md +41 -0
  12. package/.github/agents/developer.agent.md +11 -0
  13. package/.github/agents/planner.agent.md +22 -7
  14. package/.github/agents/product-engineer.agent.md +37 -10
  15. package/.github/agents/qa-engineer.agent.md +30 -3
  16. package/.github/agents/researcher.agent.md +96 -0
  17. package/.github/prompts/researcher.prompt.md +29 -0
  18. package/.github/skills/activity-codebase-research/SKILL.md +158 -0
  19. package/.github/skills/activity-contract-validation/SKILL.md +167 -0
  20. package/.github/skills/activity-e2e-test-implementation/SKILL.md +156 -0
  21. package/.github/skills/activity-integration-test-implementation/SKILL.md +156 -0
  22. package/.github/skills/activity-test-standards/SKILL.md +41 -0
  23. package/.kiro/agents/developer.md +11 -0
  24. package/.kiro/agents/planner.md +22 -7
  25. package/.kiro/agents/product-engineer.md +37 -10
  26. package/.kiro/agents/qa-engineer.md +30 -3
  27. package/.kiro/agents/researcher.md +99 -0
  28. package/.kiro/agents/verifier.md +1 -1
  29. package/.kiro/skills/activity-codebase-research/SKILL.md +158 -0
  30. package/.kiro/skills/activity-contract-validation/SKILL.md +167 -0
  31. package/.kiro/skills/activity-e2e-test-implementation/SKILL.md +156 -0
  32. package/.kiro/skills/activity-integration-test-implementation/SKILL.md +156 -0
  33. package/.kiro/skills/activity-test-standards/SKILL.md +41 -0
  34. package/AGENTS.md +91 -215
  35. package/CHANGELOG.md +33 -0
  36. package/CLAUDE.md +3 -2
  37. package/README.md +1 -0
  38. package/TESTING.md +19 -11
  39. package/package.json +1 -1
package/CHANGELOG.md CHANGED
@@ -5,6 +5,39 @@ All notable changes to this project will be documented in this file.
5
5
  The format is based on [Keep a Changelog](https://keepachangelog.com/),
6
6
  and this project adheres to [Semantic Versioning](https://semver.org/).
7
7
 
8
+ ## [0.11.0] - 2026-08-25
9
+
10
+ ### Added
11
+
12
+ - feat(agent): add researcher agent and activity-codebase-research skill
13
+ - feat(test): add integration, E2E, and contract validation skills (#130)
14
+
15
+ ### Fixed
16
+
17
+ - fix: trim AGENTS.md from 2678 to 1218 words
18
+
19
+ ### Changed
20
+
21
+ - chore: prettier
22
+ - chore: archive workstream
23
+ - Merge pull request #147 from llipe:issue/139-research-agent
24
+ - docs: fix drift found by technical-writer pass
25
+ - Merge pull request #146 from llipe:issue/142-clean-agents-md
26
+ - test(fixtures): update catalog fixture timestamps and generator version
27
+ - Merge pull request #138 from llipe/issue/130-integration-testing-playwright-e2e
28
+ - test: add parity and content tests for issue #130 skills
29
+
30
+ ## [Unreleased]
31
+
32
+ ### Added
33
+
34
+ - feat(agent): add `researcher` agent and `activity-codebase-research` skill (#139)
35
+ - Ten-agent roster (Copilot/Kiro), eight Claude subagents
36
+ - Eight-slice taxonomy, 250-line/30-file budget caps
37
+ - Conditional pre-refine (Issue Mode) and pre-spec (Feature Mode) research step
38
+ - Developer troubleshooting and planner pre-orchestration paths
39
+ - ADR-004: pre-spec codebase research step
40
+
8
41
  ## [0.10.0] - 2026-08-19
9
42
 
10
43
  ### Added
package/CLAUDE.md CHANGED
@@ -55,13 +55,14 @@ This toolkit is exposed as **commands** (entry points you invoke with `/`), **su
55
55
  | `/technical-writer` | Sync `/docs` with the codebase. |
56
56
  | `/housekeeping` | Fix lint/type/test-wiring issues. |
57
57
  | `/qa-engineer` | Establish `/TESTING.md`, author missing Layer 1-2 tests, and report `coverage_gate` plus risk-ranked gaps. |
58
+ | `/researcher` | Bounded codebase investigation producing a structured research artifact at `/workstream/research-*.md`. |
58
59
  | `/ux-engineer` | PRD/SPEC → React mockups + refinement handoff. |
59
60
  | `/verifier-design` | Generate a compliance test plan + traceability matrix from a spec/story (Design Mode). |
60
61
  | `/verifier-audit` | Grey-box fidelity audit of delivered work against requirements and PRD/spec intent (Audit Mode). |
61
62
 
62
63
  ### Subagents (`.claude/agents/`)
63
64
 
64
- `developer`, `github-ops`, `technical-writer`, `housekeeping`, `ux-engineer`, `verifier`, `qa-engineer` — isolated, scoped-tool workers. Claude delegates to these automatically when a task matches their description, and the orchestrator commands (`/planner`, `/product-engineer`) drive them via the Task tool.
65
+ `developer`, `github-ops`, `technical-writer`, `housekeeping`, `ux-engineer`, `verifier`, `qa-engineer`, `researcher` — isolated, scoped-tool workers. Claude delegates to these automatically when a task matches their description, and the orchestrator commands (`/planner`, `/product-engineer`) drive them via the Task tool.
65
66
 
66
67
  ### Orchestration model (important)
67
68
 
@@ -72,7 +73,7 @@ Claude Code subagents **cannot spawn other subagents** — the hierarchy is flat
72
73
 
73
74
  ### Skills (`.claude/skills/`)
74
75
 
75
- Activity skills: `activity-init`, `activity-refine`, `activity-generate-spec`, `activity-generate-stories`, `activity-publish-github`, `activity-e2e-test-design`, `activity-contract-test-design`, `activity-edge-case-refinement`, `activity-random-test-tactics`, `activity-test-standards`, `activity-test-implementation`, `activity-coverage-gap-analysis`, `activity-drift-reconciliation` (routes `verifier` drift findings into task-list/checklist expansion, new issues, or human-confirmed PRD/spec changelog updates — used by `product-engineer`). Process skills: `plan`, `implement` (the single source of truth for task-list execution rules, including the mandatory `verifier` audit gate). Operational: `git-ops`, `webapp-mockup`, `memo-cli-usage`.
76
+ Activity skills: `activity-init`, `activity-refine`, `activity-codebase-research`, `activity-generate-spec`, `activity-generate-stories`, `activity-publish-github`, `activity-e2e-test-design`, `activity-e2e-test-implementation`, `activity-contract-test-design`, `activity-contract-validation`, `activity-edge-case-refinement`, `activity-random-test-tactics`, `activity-test-standards`, `activity-test-implementation`, `activity-integration-test-implementation`, `activity-coverage-gap-analysis`, `activity-drift-reconciliation` (routes `verifier` drift findings into task-list/checklist expansion, new issues, or human-confirmed PRD/spec changelog updates — used by `product-engineer`). Process skills: `plan`, `implement` (the single source of truth for task-list execution rules, including the mandatory `verifier` audit gate). Operational: `git-ops`, `ux-scaffold`, `ux-theme-gen`, `memo-cli-usage`.
76
77
 
77
78
  `plan` and `implement` are scoped instructions on Copilot (`applyTo`) and scoped steering on Kiro (`fileMatchPattern`); as Claude skills they load on demand instead of consuming context on every matching turn.
78
79
 
package/README.md CHANGED
@@ -257,6 +257,7 @@ Multi-story orchestration with checkpoint/resume:
257
257
  | `github-ops` | GitHub consistency — issues, PRs, branches, labels |
258
258
  | `verifier` | Compliance test-plan design and fidelity auditing |
259
259
  | `qa-engineer` | Testing standard, missing test harnesses, coverage and gap reporting |
260
+ | `researcher` | Bounded codebase investigation producing structured research artifacts |
260
261
 
261
262
  ---
262
263
 
package/TESTING.md CHANGED
@@ -25,15 +25,18 @@ established" rather than as permission.
25
25
 
26
26
  The layer taxonomy below is fixed. What belongs in each layer is project-specific.
27
27
 
28
- | Layer | Name | Scope | Status |
29
- | ----- | ------------------------- | ------------------------------------------------------------------------- | ----------------- |
30
- | 1 | Deterministic foundations | Unit tests, schema validation. No I/O, no network, no real database. | <!-- unfilled --> |
31
- | 2 | Constrained model/tool | Backend component tests, mocked APIs, fixtures and gold datasets. | <!-- unfilled --> |
32
- | 3 | Product evaluation | Semantic, tone, groundedness, hallucination evals. Only for LLM features. | <!-- unfilled --> |
33
- | 4 | Human evaluation | Review gates, safeguards, risk alerts. | <!-- unfilled --> |
34
-
35
- Integration and end-to-end layers are declared per project in the table below
36
- when they exist.
28
+ | Layer | Name | Scope | Status |
29
+ | -------- | ------------------------- | ------------------------------------------------------------------------------------- | ----------------- |
30
+ | 1 | Deterministic foundations | Unit tests, schema validation. No I/O, no network, no real database. | <!-- unfilled --> |
31
+ | 2 | Constrained model/tool | Backend component tests, mocked APIs, fixtures and gold datasets. | <!-- unfilled --> |
32
+ | 2.5 | Integration | Real database, real migrations, RLS policies, schema contracts. No mocked data layer. | <!-- unfilled --> |
33
+ | E2E | End-to-end | Playwright CLI — committed browser automation, full-stack, scenario-driven. | <!-- unfilled --> |
34
+ | Contract | Contract validation | API spec drift, breaking-change detection, consumer impact. `dt verify` family. | <!-- unfilled --> |
35
+ | 3 | Product evaluation | Semantic, tone, groundedness, hallucination evals. Only for LLM features. | <!-- unfilled --> |
36
+ | 4 | Human evaluation | Review gates, safeguards, risk alerts. | <!-- unfilled --> |
37
+
38
+ Integration, end-to-end, and contract validation layers are declared per project
39
+ in the table below when they exist.
37
40
 
38
41
  ### Layer boundaries
39
42
 
@@ -42,8 +45,12 @@ enforceable rather than aspirational.
42
45
 
43
46
  - **Layer 1 must not:** <!-- unfilled -->
44
47
  - **Layer 2 must not:** <!-- unfilled -->
48
+ - **Layer 2.5 must not:** mock the data layer. If the database is mocked, the test belongs at Layer 2. If the test hits a live external service over the network, it may belong at E2E or remote integration.
49
+ - **E2E must not:** assert on internal state or implementation details. Assertions are on observable user-facing behavior only.
50
+ - **Contract validation must not:** test internal business logic. It checks the boundary/interface only.
45
51
  - **Escalation rule** — when a Layer 1 test needs a real dependency, it moves up
46
52
  a layer rather than growing a test double that reimplements the dependency.
53
+ When a Layer 2 test needs a real database, it moves to Layer 2.5.
47
54
 
48
55
  ## Packages
49
56
 
@@ -86,8 +93,9 @@ Canonical script names for JS/TS packages. Prefer `pnpm`.
86
93
  | `typecheck` | Type analysis | yes |
87
94
  | `test` | Aggregate — MUST reach every test package | yes |
88
95
  | `test:unit` | Layer 1 | yes |
89
- | `test:integration` | Integration layer | when present |
90
- | `test:e2e` | End-to-end layer | when present |
96
+ | `test:integration` | Layer 2.5 — real database integration | when present |
97
+ | `test:e2e` | E2E layer — Playwright browser automation | when present |
98
+ | `test:contract` | Contract validation — `dt verify` family | when present |
91
99
  | `test:coverage` | Coverage measurement | when tooling exists |
92
100
  | `audit` | Dependency vulnerability scan | yes |
93
101
  | `validate` | Aggregate quality gate | yes |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@llipe.com/dev-tasks",
3
- "version": "0.10.0",
3
+ "version": "0.11.0",
4
4
  "description": "Multi-repo context tooling for dev-tasks",
5
5
  "type": "module",
6
6
  "imports": {