Fix release for 1.1.2: the 14 longest skills keep their later phases
after a compaction, a question nobody answered is never taken as an
answer, settings read the same from a subfolder, the commit check works
for a project in a subfolder of a larger repository, every skill opens
with a title, and the shipped allow rules no longer approve deleting a
branch or writing files without asking. Details in CHANGELOG.md; upgrade
steps in UPGRADING.md (v1.1.2 → v1.1.3).
Refs #83
Refs #133
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0185en4t76fPn7315q4c3nko
Fix release for 1.1.1: the minimal path end to end, engine commands that
run on Godot, Unity and Unreal, hook warnings you can see, and verdicts
that say when they could not check. Details in CHANGELOG.md; upgrade
steps in UPGRADING.md (v1.1.1 → v1.1.2).
Fixes#67Fixes#131
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WuJn2FdynEybfL5KC697nJ
The skill config line is now one plain command, pre-approved in each
skill's own allowed-tools. The 1.1.0 line failed Claude Code's injected-command
permission check as "Contains expansion", so outside auto mode 66 skills
aborted and game-designer / creative-director could not launch.
Fixes#128
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
`project.yaml` at the repo root is now the single source of truth for a
project's configuration, replacing `production/stage.txt`,
`production/review-mode.txt` and `.claude/docs/technical-preferences.md` (all
three still read as a fallback; nothing is force-deleted).
**`modes.rigor` — one question instead of six.** `minimal`, `standard` or
`full` fronts six knobs: `modes.workflow`, `docs.density`, `qa.level`,
`modes.story_granularity`, `modes.review_mode` and `team.size`. It defaults to
`minimal`, which is a change from 1.0's behaviour: the heavier tier was
measured costing several times more to reach working code without producing a
better result, and returning nothing when a fresh developer inherited the
project. Pin `modes.rigor: standard` to keep 1.0's process level.
Also in this release:
- `/settings` to view or change any setting, and `project.local.yaml` for
per-developer preferences that should not be committed.
- `system_overrides` to hold one system to a higher standard than the rest of
the project, and `testing.strict` to set per test type whether missing
evidence blocks a story or warns.
- A story that changes anything the player sees is not closed until the game
has been launched, observed, and a screenshot retained in
`production/qa/evidence/`. A parse check is not a run. This holds at every
rigor level, including `minimal`, where automated tests are waived but the
look is not.
- The code root is engine-specific and enforced as such: Godot `src/`, Unity
`Assets/`, Unreal `Source/<Module>/`. Two of the three will not build a
project laid out any other way.
- Migration tooling for existing projects: `.claude/scripts/migrate-v1-config.sh`
converts a 1.0 layout, non-destructively by default, with a report to review
before `--finalize` deletes anything.
- Ask-before-write holds regardless of personal automation settings.
Upgrading from 1.0 or earlier: see UPGRADING.md. Full list of changes:
CHANGELOG.md.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016xvzG3i7pWQg4LjyDwWMXd
- Add Edit to architecture-decision allowed-tools (retrofit mode and
registry append both call Edit on existing files — was throwing a
permission error on every /architecture-decision retrofit run)
- Add Write to story-done allowed-tools (Phase 7 creates active.md on
first run — was silently failing and losing completion notes)
Fixes#33. Bug found and fix branches prepared by @xiaolai via NLPM audit.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a --review flag to all 13 gate-using skills and a global
production/review-mode.txt config (set during /start). Full runs all
director gates, lean skips per-skill gates but keeps phase gates, solo
skips all directors. Documents modes in director-gates.md, WORKFLOW-GUIDE.md,
and README.md.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Creates .claude/docs/director-gates.md as a central registry of 18 named gate
prompts (CD-*, TD-*, PR-*, LP-*, QL-*, ND-*, AD-*) covering all 7 production
stages. Skills now reference gate IDs instead of embedding inline director prompts,
eliminating drift when prompts need updating.
Updated 15 skills to use gate IDs: brainstorm, map-systems, design-system,
architecture-decision, create-architecture, create-epics, create-stories,
sprint-plan, milestone-review, playtest-report, prototype, story-done,
gate-check, setup-engine, start.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Introduces a full shift-left QA pipeline with Story Type classification
as the backbone of the Definition of Done:
New skills:
- /test-setup: scaffold test framework + CI/CD per engine (Godot/Unity/Unreal)
- /qa-plan: generate sprint test plan classifying stories by type
- /smoke-check: critical path gate (PASS/PASS WITH WARNINGS/FAIL) before QA hand-off
- /team-qa: orchestrate qa-lead + qa-tester through full QA cycle
Story Type classification (Logic/Integration/Visual/Feel/UI/Config/Data):
- Logic and Integration: BLOCKING DoD gate — unit/integration test required
- Visual/Feel and UI: ADVISORY — screenshot + sign-off evidence required
- Config/Data: ADVISORY — smoke check pass sufficient
Updated skills: story-done (test evidence gate), story-readiness (Story Type
check), gate-check (test framework at Technical Setup, test evidence at
Polish/Release), create-epics-stories (Type field + Test Evidence section)
Updated agents: qa-lead (shift-left philosophy + evidence table),
qa-tester (automated test patterns for Godot/Unity/Unreal)
New templates: test-evidence.md (manual sign-off record), test-plan.md
(sprint-oriented QA plan replacing generic feature template)
Updated coding-standards.md: Testing Standards section with DoD table,
test rules, what NOT to automate, and engine-specific CI/CD commands
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
