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
* Fix architecture-decision skill: duplicate ## 0. heading + broken step numbering
Resolves#44. Renumbers the duplicate '## 0. Load Engine Context' to '## 1.',
shifts all subsequent H2 headings (1→2, 2→3, 3→4, 4→5), renames '## 7. Closing
Next Steps' to '## 6.', and updates all inline cross-references (sub-step labels
4.5/4.6/4.7 → 5.5/5.6/5.7, section refs '### 2a' → '### 3a', 'Step 3' → 'Step 4').
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Fix three stale Step 0 cross-references missed in #45
Lines 51, 61, and 69 still pointed to "Step 0" after Load Engine Context
was renumbered to ## 1. in the previous fix — updated all three to Step 1.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace head with tail so the quick summary surfaces the last 20 lines
of active.md — where all skills append their session extracts — rather
than the first 20 lines which grow stale as the file accumulates history.
Fixes#39
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* Fix: document that rg --type gdscript is invalid, use --glob *.gd instead
Closes#37. ripgrep has no gdscript type — *.gd files are registered under
the gap type (GAP programming language). Using --type gdscript produces a
hard error, silently preventing any search from executing.
Added explicit warnings in two places:
- .claude/agents/godot-gdscript-specialist.md: new Tooling section with
the correct Grep tool param (glob: "*.gd") and shell equivalent
- docs/engine-reference/godot/current-best-practices.md: new Tooling
section agents read at version-check time
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Fix: propagate rg --glob *.gd tooling warning to all Godot agents
Closes the coverage gap identified in PR #42 review — the ripgrep
gdscript-type warning was only in godot-gdscript-specialist. Added
the same CRITICAL tooling section to godot-specialist,
godot-gdextension-specialist, godot-shader-specialist, and
godot-csharp-specialist so no Godot agent can silently misfire a search.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
- 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>
Both SubagentStart/SubagentStop hooks were extracting `.agent_name` from the
hook payload, but Claude Code emits the agent name in `agent_type`. This caused
every audit log entry to fall through to the "unknown" fallback, making the
entire agent audit trail useless.
Fix: swap `.agent_name` -> `.agent_type` in both the jq path and the grep/sed
fallback for systems without jq. Log output format is unchanged so existing
audit logs remain valid.
Bug reported and fix authored by @bobloy in issue #20:
https://github.com/Donchitos/Claude-Code-Game-Studios/issues/20
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>
- Remove invalid `agent: Explore` frontmatter from read-only skills (asset-audit, design-review, project-stage-detect, reverse-document)
- Fix design-system and map-systems to create session-state/active.md if it does not exist before updating
- Fix gate-check to remove reference to non-existent bmad-bmm-check skill
- Expand /start recommended paths into phased roadmap (Concept → Architecture → Production)
- Restructure /sprint-plan into numbered phases with clearer next-steps section
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- New agent: godot-csharp-specialist covering partial class requirement,
[Export]/[Signal] attributes, SignalName emit pattern, ToSignal async,
Godot.Collections vs .NET collections, [GlobalClass] resources, .csproj config,
and C#-specific anti-patterns
- /setup-engine now asks GDScript vs C# vs Both before showing the Technology
Stack when Godot is chosen; choice determines CLAUDE.md template, naming
conventions, and specialist routing
- Refactored Godot-specific variants (3 CLAUDE.md templates, naming conventions,
3 routing tables) into Appendix A at the bottom of the skill — main flow stays
clean for Unity/Unreal users
- argument-hint updated to include engine-only invocation mode
- Section 5 collaborative step and Section 12 summary output updated for language
awareness
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Wire Notification event in settings.json to new notify.sh hook
- notify.sh: Windows toast notifications via PowerShell balloon tip
- docs/CLAUDE.md: authoring standards for ADRs, TR registry, control manifest, engine reference
- design/CLAUDE.md: GDD directory guidance placeholder
- src/: scaffold with .gitkeep and CLAUDE.md authoring guide
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- NEW /create-epics (agent: technical-director): architect-level epic scoping,
one epic per architectural module. Does not create stories.
- NEW /create-stories (agent: lead-programmer): decomposes a single epic into
story files with embedded TR-IDs, ADR guidance, and test evidence paths.
- NEW /dev-story: the missing implementation skill — reads a story, loads full
context (TR registry, ADR, control manifest, engine prefs), routes to the
correct programmer agent via Task, and drives implementation to completion
including writing the test.
- DEPRECATED /create-epics-stories: added redirect notice; original content
preserved for reference.
- Updated /gate-check: Pre-Prod→Production artifact check and follow-up actions
now reference the two new skills.
- Updated workflow-catalog.yaml: replaced create-epics-stories step with two
separate steps; implement step now references /dev-story with command field.
Story loop is now explicit:
/story-readiness → /dev-story → /code-review → /story-done
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>
Closes the gap where /design-system, story lifecycle, gate-check transitions,
UX pipeline, and brownfield adoption had no worked examples. Adds visual ASCII
flow diagrams for the full 7-phase pipeline and 4 detailed skill chains.
New files:
- docs/examples/session-design-system-skill.md
- docs/examples/session-story-lifecycle.md
- docs/examples/session-gate-check-phase-transition.md
- docs/examples/session-ux-pipeline.md
- docs/examples/session-adopt-brownfield.md
- docs/examples/skill-flow-diagrams.md
Updated:
- docs/examples/README.md — reorganized with Core Workflow / Foundational sections
- .claude/docs/quick-start.md — synced
- docs/WORKFLOW-GUIDE.md — synced
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Add UPGRADING.md migration guide and link from README
Covers v0.1→v0.2 upgrade with three strategies (git merge, cherry-pick,
manual copy), file safety categories, and post-upgrade verification steps.
Structured to support future version sections.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Rename /design-systems to /map-systems + /design-system and fix all references
Split the monolithic /design-systems skill into two focused skills:
- /map-systems: systems decomposition and index creation
- /design-system: guided section-by-section GDD authoring
Updated all cross-references across 14 files: README, UPGRADING,
WORKFLOW-GUIDE, quick-start, skills-reference, game-concept template,
systems-index template, brainstorm, design-review, gate-check,
project-stage-detect, setup-engine, and start skills. Fixed skill
counts from 36 to 37 everywhere. Added /map-systems and /design-system
to quick-start Paths A and B workflows.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Fix cross-reference gaps, broken hooks, and stale workflow chains
- Fix log-agent.sh parsing agent_type instead of agent_name (always logged "unknown")
- Fix GDD status lifecycle: design-system now writes Approved/Designed/In Review
- Clean up settings.local.json vestigial Bash grants from development
- Delete orphaned docs marked for removal in UPGRADING.md
- Add /design-system to next-steps in /start, /brainstorm, /setup-engine
- Fix WORKFLOW-GUIDE: add /map-systems + /design-system to Appendix C Workflow 1
- Fix invalid /map-systems map argument in WORKFLOW-GUIDE Step 2.1
- Update map-systems frontmatter to document [system-name] argument
- Update commit hook to validate all 8 required GDD sections (was 5)
- Update README template count 28 → 29, add 5 missing templates to quick-start
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add custom status line with 7-stage production pipeline
Introduces a status line showing context %, model name, and production
stage at a glance. Aligns gate-check and project-stage-detect to a
unified 7-stage model (Concept → Systems Design → Technical Setup →
Pre-Production → Production → Polish → Release). Stage is determined
by explicit override (production/stage.txt) or auto-detected from
project artifacts. Epic/Feature/Task breadcrumb appears conditionally
in Production+ stages via a structured STATUS block in active.md.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add v0.2→v0.3 upgrade guide and PR validation test suite
- UPGRADING.md: add v0.2.0→v0.3.0 section documenting breaking rename
of /design-systems→/map-systems, new /design-system skill, statusline.sh,
gate-check stage advancement, and safe-to-overwrite file list
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
New users no longer get pushed toward /setup-engine before they even
have a game idea. The /start skill asks where they are (no idea, vague
idea, clear concept, existing work) and routes to the right workflow.
The detect-gaps hook now detects fresh projects and suggests /start.
All docs updated: README, quick-start, workflow guide, skills/hooks
references, CLAUDE.md (skill count 34→35).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
