Skip to content

chore(workflow): refine agents, skills, commands, and ADR structure for v5#70

Merged
nullhack merged 2 commits intomainfrom
chore/workflow-v5-refinements
Apr 19, 2026
Merged

chore(workflow): refine agents, skills, commands, and ADR structure for v5#70
nullhack merged 2 commits intomainfrom
chore/workflow-v5-refinements

Conversation

@nullhack
Copy link
Copy Markdown
Owner

Summary

  • Consolidate ADR files into a single docs/architecture/adr.md (drop per-decision adr-NNN-<title>.md pattern)
  • Add test-coverage and test-build tasks to pyproject.toml; fix test and test-fast task flags
  • Clarify design priority chain with full complexity ladder in agents, skills, and AGENTS.md

Changes

  • Agents: Remove self-selection language from software-engineer and product-owner; add refactor and design-patterns skills to reviewer
  • feature-selection skill: Add BASELINED guard block (NEVER move to in-progress unless BASELINED)
  • implementation skill: Align test stub format, update ADR path, fix TDD loop tree and handoff commands
  • scope skill: Drop silent pre-mortem requirement from Feature Discovery Session 1
  • AGENTS.md / workflow.md: Sync ADR path, command names (test-build, doc-build), quality gate wording, and code-lines-only clarification for function/class length limits

Testing

  • No runtime code changed — template and workflow documentation only
  • task lint — not applicable (markdown/toml only)
  • task static-check — not applicable

Reviewer Notes

All changes are to workflow documentation, agent instructions, skill files, and pyproject.toml task definitions. No application source code was modified.

…or v5

- Consolidate ADR files into single adr.md (drop adr-NNN-<title>.md pattern)
- Add test-coverage and test-build tasks; fix test-fast/test flags
- Clarify design priority chain with full complexity ladder
- Remove self-selection language from agent instructions
- Add refactor and design-patterns skills to reviewer agent
- Add BASELINED guard to feature-selection skill
- Fix scope skill: drop silent pre-mortem requirement from Session 1
- Align function/class line-count wording to code-lines-only
…ure moves, unified session protocol

- Split docs/discovery.md into three append-only files:
  docs/discovery_journal.md (raw Q&A), docs/discovery.md (synthesis),
  docs/architecture.md (architectural decisions)
- Remove docs/features/discovery.md (superseded)
- Replace Phase 1/Phase 2 model with 2-stage model: Stage 1 Discovery
  (unified iterative sessions) + Stage 2 Specification (stories + criteria)
- PO is sole owner of all .feature file moves; SE and reviewer never move
  or edit .feature files; explicit escalation when no in-progress feature
- Add bug handling protocol: PO adds @bug @id, SE writes both @id test
  and @given Hypothesis property test
- Add real-time split rule: >2 concerns or >8 Examples splits immediately
  within the same session
- Add session status markers to discovery_journal.md: IN-PROGRESS/COMPLETE
- Update all agent files, skills, workflow docs, and research docs to match
@nullhack nullhack merged commit 2b3dca3 into main Apr 19, 2026
8 checks passed
@nullhack nullhack deleted the chore/workflow-v5-refinements branch April 19, 2026 11:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant