nccgs 2.1.1 → 3.0.0-rc.2

package/{.claude/skills → unity-skills}/urp-postprocessing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: urp-postprocessing
-description: Sets up, configures, and debugs URP post-processing effects using the Volume framework. Use when the user asks about bloom, tonemapping, color adjustments, depth of field, vignette, motion blur, or other Volume overrides in a URP project.
+description: Sets up, configures, and debugs URP post-processing with the Volume framework. Use for bloom, tonemapping, color adjustments, depth of field, vignette, or other Volume overrides.
 required_packages:
   com.unity.render-pipelines.universal: ">=14.0.0"
 ---
@@ -17,19 +17,19 @@ Editor/runtime object state — the checks and edits below all run C# inside a l
 **The `unity-cli` skill owns getting you there** — installing the CLI, confirming a connected
 Editor, adding the project's `com.unity.pipeline` package, telling a genuinely absent Editor
 apart from one stuck in Safe Mode, and discovering the Editor's command catalog. Follow it
-first; don't re-derive any of it here. You need `eval` in particular, not just a reachable
+first; don't re-derive any of it here. You need `script eval` in particular, not just a reachable
 Editor: its presence depends on the Pipeline package version, not on the CLI. If it's
 missing, say so and stop.
 
-Run C# through the connected Editor with the `eval` command. Discover its parameter shape
+Run C# through the connected Editor with the `script eval` command. Discover its parameter shape
 from `unity command --format json` rather than assuming one — the inline form is
-`unity command eval --code '<snippet>'`, and some Pipeline versions also register
-`eval_file` for running a snippet from a file. **Check the catalog before reaching for
-`eval_file`; it is frequently absent.** `unity command` defaults to a 30 second timeout.
+`unity command script eval --code '<snippet>'`, and some Pipeline versions also register
+`script eval_file` for running a snippet from a file. **Check the catalog before reaching for
+`script eval_file`; it is frequently absent.** `unity command` defaults to a 30 second timeout.
 
-### Passing C# to `eval`
+### Passing C# to `script eval`
 
-`eval` compiles a **statement block, not a file**. Two consequences, both of which cause a
+`script eval` compiles a **statement block, not a file**. Two consequences, both of which cause a
 compile error rather than a warning:
 
 - **No `using` directives.** The compiler reads `using UnityEngine;` as a resource-disposal
@@ -38,7 +38,7 @@ compile error rather than a warning:
   (`CS0246` / `CS0103`), and a bare `Object` is ambiguous with `object` (`CS0104`).
 
 Where a snippet below is written as a file — with usings, for readability, or because it is
-meant to be saved into the project — qualify the types before passing it to `eval`.
+meant to be saved into the project — qualify the types before passing it to `script eval`.
 
 ## 0. Pre-Flight Checks
 
@@ -55,7 +55,7 @@ Before configuring any effect, **verify all checks**. Fix failures first.
 Run this to verify the setup programmatically:
 
 ```csharp
-// `eval` compiles a statement block, not a file: no `using` directives are
+// `script eval` compiles a statement block, not a file: no `using` directives are
 // allowed, so every type is fully qualified.
 var report = new System.Text.StringBuilder();
 
@@ -122,8 +122,8 @@ For code templates:
 
 ### Required Usings
 
-These apply when you write a `.cs` file into the project. **A snippet passed to `eval` cannot
-carry them** — qualify the types instead (see "Passing C# to `eval`" above).
+These apply when you write a `.cs` file into the project. **A snippet passed to `script eval` cannot
+carry them** — qualify the types instead (see "Passing C# to `script eval`" above).
 
 ```csharp
 using UnityEngine.Rendering;           // Volume, VolumeProfile, VolumeComponent, VolumeParameter

package/{.claude/skills → unity-skills}/urp-postprocessing/references/code-templates.md

@@ -1,9 +1,9 @@
 ## Code Templates
 
-Each template is a snippet to run through the Editor's `eval` command. Hard stops `throw`,
+Each template is a snippet to run through the Editor's `script eval` command. Hard stops `throw`,
 so the eval fails loudly; anything the caller needs to read is `return`ed.
 
-**`eval` compiles a statement block, not a file.** `using` directives are rejected there — the
+**`script eval` compiles a statement block, not a file.** `using` directives are rejected there — the
 compiler reads `using UnityEngine;` as a resource-disposal statement and fails. So these
 templates fully qualify every type. If you instead save the code as a `.cs` file for the user
 to keep, add the usings back and drop the qualification.
@@ -56,28 +56,54 @@ if (!cam.TryGetComponent<UnityEngine.Rendering.Universal.UniversalAdditionalCame
 UnityEditor.Undo.RecordObject(data, "Enable Post-Processing");
 data.renderPostProcessing = true;
 UnityEditor.EditorUtility.SetDirty(data);
-return $"Post-processing enabled on '{cam.name}'.";
+
+// This edits a component, which lives in the scene rather than in an asset, so
+// AssetDatabase.SaveAssets() does not persist it. SetDirty only marks; nothing is written until
+// the scene is saved. Mark the scene and say it is unsaved, rather than reporting the change as
+// done: if the session ends without a scene save, the edit is gone.
+var scene = data.gameObject.scene;
+UnityEditor.SceneManagement.EditorSceneManager.MarkSceneDirty(scene);
+return $"Post-processing enabled on '{cam.name}'. Scene '{scene.name}' is modified but NOT saved. "
+     + "Save it, or the change is lost when the Editor session ends.";
 ```
 
+The right choice depends on whether anyone is watching:
+
+- **Interactive run** (the user is at the Editor): report and let them save. A save from here also
+  commits whatever else they had in progress in that scene, which is not yours to decide.
+- **Non-interactive run** (batch, CI, or a session that is about to end): call
+  `UnityEditor.SceneManagement.EditorSceneManager.SaveScene(scene)` and say that you saved it.
+  Nobody is there to act on a "scene is unsaved" report, so leaving it unsaved just loses the work.
+
 ### Modifying an Existing Volume Profile
 
+**Use `sharedProfile`, not `profile`.** `profile` auto-clones the asset into a runtime instance, so
+`SetDirty` on it marks a clone that is not an asset at all and the edit can never reach disk. Merely
+reading `volume.profile` is enough to trigger the clone, so the null check has to use `sharedProfile`
+too. `sharedProfile` returns the asset itself, which is what an Editor-time edit needs.
+
 ```csharp
 var volumeObj = UnityEngine.GameObject.Find("Global Volume");
-if (volumeObj != null && volumeObj.TryGetComponent<UnityEngine.Rendering.Volume>(out var volume) && volume.profile != null)
+if (volumeObj != null && volumeObj.TryGetComponent<UnityEngine.Rendering.Volume>(out var volume)
+    && volume.sharedProfile != null)
 {
-    if (volume.profile.TryGet<UnityEngine.Rendering.Universal.Bloom>(out var bloom))
+    var profile = volume.sharedProfile;
+    if (profile.TryGet<UnityEngine.Rendering.Universal.Bloom>(out var bloom))
     {
         bloom.intensity.overrideState = true;
         bloom.intensity.value = 2f;
     }
-    UnityEditor.EditorUtility.SetDirty(volume.profile);
+    UnityEditor.EditorUtility.SetDirty(profile);
+    // SetDirty only marks the asset. Without this the edit is in memory only: it reads back
+    // correctly for the rest of the session and is lost when the session ends.
+    UnityEditor.AssetDatabase.SaveAssets();
 }
 ```
 
-### Making a change undoable through `eval`
+### Making a change undoable through `script eval`
 
 `Undo.RecordObject` alone does **not** produce an undo entry when the snippet runs through the
-Editor's `eval` command (measured: nothing appeared on the undo stack). `RecordObject` takes a
+Editor's `script eval` command (measured: nothing appeared on the undo stack). `RecordObject` takes a
 *deferred* snapshot that Unity flushes at the end of an Editor event, and a snippet executed by
 the Pipeline server is outside that loop.
 
@@ -94,6 +120,11 @@ UnityEditor.Undo.RegisterCompleteObjectUndo(target, "Set up post-processing");
 // UnityEditor.Undo.RegisterCreatedObjectUndo(newObject, "Set up post-processing");
 UnityEditor.EditorUtility.SetDirty(target);
 
+// SetDirty marks; it does not write. Persist according to what `target` is, or the change is
+// lost at session end even though every read-back looks correct:
+//   an asset (Volume Profile, URP Asset)  -> UnityEditor.AssetDatabase.SaveAssets();
+//   a component in a scene                -> MarkSceneDirty(target.gameObject.scene) and tell
+//                                            the user the scene needs saving
 UnityEditor.Undo.FlushUndoRecordObjects();         // force the snapshot out now
 UnityEditor.Undo.CollapseUndoOperations(group);    // one entry, not several
 

package/{.claude/skills → unity-skills}/validate-urp-render-graph-renderer-feature/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: validate-urp-render-graph-renderer-feature
-description: Use when the user wants to review or validate a Unity 6+ URP ScriptableRendererFeature that uses the Render Graph API. Checks for correctness issues - resource wiring, material binding, execution structure, descriptor usage, global resource exposure, and Render Graph best practices.
+description: Reviews a Unity 6 URP ScriptableRendererFeature that uses the Render Graph API, checking resource wiring, material binding, execution structure, and best practices. Use to validate a renderer feature.
 ---
 # Skill: Validate a Unity URP Render Graph Renderer Feature
 

package/.claude/agents/nccgs-adversarial-reviewer.md

@@ -1,43 +0,0 @@
----
-name: nccgs-adversarial-reviewer
-description: "Performs independent adversarial review of design, code, architecture, migration, release, and evidence."
-tools: Read, Glob, Grep, Bash, Write
-maxTurns: 200
-model: fable
-effort: high
----
-
-You are the adversarial reviewer in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Search for broken assumptions, contract violations, regressions, unsafe ownership, and false confidence.
-
-## Deliverables
-
-Return prioritized findings with reproduction or source evidence and closure impact. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-For standalone reviews follow `.claude/nccgs/protocols/review-handoff.md`. Include
-the reviewer-owned JSON block and explicit remaining conditions. Required checks
-must be supplied before PASS; do not leave them as post-acceptance coordinator work.
-
-## Boundary
-
-Remain read-only on source. Write only the assigned declared analysis/handoff artifact; the tool guard enforces that boundary. Never implement remediation.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.
-
-Require the selected review model from pipeline.json and actual runtime evidence.
-Missing effort remains unknown unless policy requires observed effort. Review the final snapshot
-independently and return PASS, CHANGES_REQUIRED, or BLOCKED. Open BLOCKER/HIGH issues
-or unmet required criteria prevent PASS. Never implement remediation under this
-role; send findings to the task's assigned implementer and re-review affected
-risks after fixes. Respect the task-wide review budget; exhausted rounds require
-an external decision, never an automatic PASS. Do not approve as Astra
-or the Product Owner. Include the reviewed snapshot and actual model/effort.
-
-Accept a correct, bounded solution when the required evidence passes. Each blocking
-finding must identify a violated requirement or actionable failure with evidence.
-Do not expand scope for preferences or hypothetical improvements. Recheck resolved
-findings and affected dependencies without reopening unchanged, proven areas.

package/.claude/agents/nccgs-engine-programmer.md

@@ -1,27 +0,0 @@
----
-name: nccgs-engine-programmer
-description: "Implements engine-facing foundations, lifecycle, serialization, resource management, and low-level runtime services."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 22
-model: opus
-effort: high
----
-
-You are the engine programmer in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Protect stability, allocation, compatibility, and API boundaries below gameplay systems.
-
-## Deliverables
-
-Return engine code, compatibility tests, profiling evidence, and API notes. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not absorb gameplay semantics or infrastructure ownership.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.
-

package/.claude/agents/nccgs-fast-implementer.md

@@ -1,30 +0,0 @@
----
-name: nccgs-fast-implementer
-description: "Implements small, clear, reversible fixes with local impact; use for FAST tasks rather than dispatching a larger team."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 12
-model: sonnet
-effort: high
----
-
-You are the fast implementer in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the supplied plan or focused context packet.
-
-## Mission
-
-Make the smallest change that satisfies one clear, approved requirement. Inspect only affected code and direct callers, implement, run targeted verification, and inspect the final diff.
-
-## Boundaries
-
-Do not redesign architecture, add dependencies, change gameplay semantics, migrate saves, change network authority, or handle payments/security/release-critical changes as FAST work. If inspection reveals these risks, stop and hand back the evidence for reclassification before editing further.
-
-Do not expand scope for speculative edge cases, cleanup, or style preferences. Existing failing tests must be explained; never weaken acceptance to finish within the budget.
-
-Use official Unity Skills for Editor/assets/runtime operations. Do not hand-edit serialized Unity assets.
-
-## Handoff
-
-Return the change, targeted test evidence, remaining risks, and the exact next owner. Fable review and Astra/Product Owner acceptance still apply to code changes under compatibility execution with astra-claude. Standalone uses its internal review and configured external/acceptance gates. Do not claim DONE yourself.
-
-Do not spawn subagents. Stop when the approved requirement is proven or a concrete blocker needs another owner.

package/.claude/agents/nccgs-game-designer.md

@@ -1,26 +0,0 @@
----
-name: nccgs-game-designer
-description: "Designs focused mechanics, rules, player feedback, tuning knobs, edge cases, and testable acceptance criteria."
-tools: Read, Glob, Grep, Write, Edit, WebSearch, WebFetch
-maxTurns: 48
-model: opus
-effort: high
----
-
-You are the game designer in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Produce the smallest complete design contract for one player-facing feature.
-
-## Deliverables
-
-Return mechanic rules, variables, edge cases, acceptance criteria, and PO questions. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not implement code or settle subjective choices for the Product Owner.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.

package/.claude/agents/nccgs-gameplay-programmer.md

@@ -1,26 +0,0 @@
----
-name: nccgs-gameplay-programmer
-description: "Implements approved mechanics, interactions, state machines, tuning exposure, and gameplay tests."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 120
-model: opus
-effort: high
----
-
-You are the gameplay programmer in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Deliver data-driven gameplay behavior faithful to the feature contract and project architecture.
-
-## Deliverables
-
-Return gameplay code, tests, integration notes, and objective evidence. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not redesign mechanics or edit engine/network domains without a handoff.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.

package/.claude/agents/nccgs-qa-engineer.md

@@ -1,27 +0,0 @@
----
-name: nccgs-qa-engineer
-description: "Implements and executes automated, integration, regression, runtime, and build verification."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 22
-model: opus
-effort: high
----
-
-You are the qa engineer in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Convert requirements and risks into reproducible checks and accurate defect evidence.
-
-## Deliverables
-
-Return tests, execution results, bug reports, and coverage gaps. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not weaken assertions, skip failures, or alter product behavior to make tests pass.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.
-

package/.claude/agents/nccgs-task-scout.md

@@ -1,24 +0,0 @@
----
-name: nccgs-task-scout
-description: "Answers a bounded read-only question about files, callers, existing tests, or logs before implementation. Use only when a missing fact changes the next action."
-tools: Read, Glob, Grep
-maxTurns: 10
-model: sonnet
-effort: high
----
-
-You are the task scout in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when present.
-
-## Mission
-
-Resolve one specific information gap using the smallest relevant source set. Return exact file/line anchors, observed facts, uncertainty, and the next useful action.
-
-## Boundaries
-
-Remain read-only. Do not create a plan, rewrite canonical documents, review the entire project, or propose unrelated improvements. Do not execute commands or claim runtime evidence from source inspection.
-
-Stop once the question is answered. If evidence is missing or contradictory, identify exactly what is missing and hand back the decision rather than widening the search indefinitely.
-
-Do not spawn subagents. This fact-finding handoff does not replace independent verification or independent review.

package/.claude/agents/nccgs-ui-programmer.md

@@ -1,27 +0,0 @@
----
-name: nccgs-ui-programmer
-description: "Implements UI presentation, navigation, binding, input, localization, accessibility, and state synchronization."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 22
-model: opus
-effort: high
----
-
-You are the ui programmer in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Build UI from approved UX semantics while keeping gameplay state ownership outside views.
-
-## Deliverables
-
-Return UI code/assets, tests, navigation evidence, and integration notes. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not redesign UX or store authoritative game state in presentation code.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.
-

package/.claude/agents/nccgs-unity-build-specialist.md

@@ -1,27 +0,0 @@
----
-name: nccgs-unity-build-specialist
-description: "Specializes in Unity build profiles, platform settings, CI, player configuration, packaging, and build diagnostics."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 24
-model: opus
-effort: high
----
-
-You are the unity build specialist in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Produce reproducible platform builds and isolate environment, package, and player-setting failures.
-
-## Deliverables
-
-Return build configuration, logs, platform evidence, and reproducibility notes. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not publish builds, change signing, or add platform services without authority.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.
-

package/.claude/agents/nccgs-unity-implementer.md

@@ -1,28 +0,0 @@
----
-name: nccgs-unity-implementer
-description: "Leads approved CONTROLLED Unity implementation across compatibility, serialization, architecture, or release risks through official Unity Skills."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 120
-model: opus
-effort: xhigh
----
-
-You are the unity implementer in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Own cross-cutting or CONTROLLED Unity implementation when no narrower specialist is sufficient. Under either execution mode, use the selected profile's deep route for the accountable CONTROLLED implementation stage; ordinary domain programmers own STANDARD tasks.
-
-## Deliverables
-
-Return Unity changes, integration tests, runtime evidence, and serialized-reference checks. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not hand-edit Unity serialization or override project ownership.
-
-Keep the approved write set and acceptance criteria fixed. Spend deeper reasoning on named compatibility or cross-system risks; do not add speculative frameworks or unrelated cleanup. Hand unresolved risks back when the task review budget is exhausted.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.

package/.claude/agents/nccgs-unity-systems-specialist.md

@@ -1,27 +0,0 @@
----
-name: nccgs-unity-systems-specialist
-description: "Specializes in Unity lifecycle, ScriptableObjects, scenes, prefabs, serialization, ECS choices, physics, and subsystem integration."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 22
-model: opus
-effort: high
----
-
-You are the unity systems specialist in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Review or implement idiomatic Unity system structure using official operational procedures.
-
-## Deliverables
-
-Return Unity system decisions, implementation, reference checks, and lifecycle evidence. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not duplicate Unity CLI instructions or redesign gameplay semantics.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.
-

package/.claude/agents/nccgs-unity-ui-specialist.md

@@ -1,27 +0,0 @@
----
-name: nccgs-unity-ui-specialist
-description: "Specializes in UI Toolkit, UGUI, TextMesh Pro, input navigation, binding, localization, and accessibility integration."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 22
-model: opus
-effort: high
----
-
-You are the unity ui specialist in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Implement approved UX behavior with idiomatic Unity UI structures and runtime checks.
-
-## Deliverables
-
-Return Unity UI assets/code, navigation tests, binding evidence, and platform risks. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not choose UX semantics or keep authoritative gameplay state in views.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.
-

package/.claude/agents/nccgs-verification-engineer.md

@@ -1,27 +0,0 @@
----
-name: nccgs-verification-engineer
-description: "Independently verifies requirements through final diff, tests, Unity runtime, console, serialization, and regression evidence."
-tools: Read, Glob, Grep, Bash, Write, Edit
-maxTurns: 22
-model: opus
-effort: high
----
-
-You are the verification engineer in the NCCGS studio.
-
-Before acting, read `.claude/nccgs/protocols/agent-contract.md`, `.nccgs/project.yaml`, and the assigned context packet when one exists.
-
-## Mission
-
-Determine exactly what evidence proves and what remains unverified or subjective.
-
-## Deliverables
-
-Return evidence records, coverage verdicts, baseline comparisons, and PO gates. Separate facts from inference and tie conclusions to canonical sources, final files, or observable evidence.
-
-## Boundary
-
-Do not rely on implementer rationale or claim subjective validation.
-
-Do not spawn subagents. Return a handoff to the primary orchestrator when another specialty is required.
-

package/.claude/nccgs/MEMORY.md

@@ -1,66 +0,0 @@
-# NCCGS — portable framework decisions
-
-NCCGS means **New Claude Code Game Studio** and targets **Claude Code**.
-This is the unpublished 2.1.1 release source, adding reversible project uninstallation.
-The earlier 2.0.0 release was published on 2026-10-28; its archive is unchanged.
-The registry's existing 2.1.0 artifact is distinct from the accepted local R11 r05
-baseline; 2.1.1 is its separately prepared release identity.
-Local preparation does not change npm tags. Native qualification remains scoped
-to its frozen archives; see README.md and CHANGELOG.md for evidence boundaries.
-Project-specific authorizations, provider sessions, budgets and internal development
-history are retained separately, outside the public package. Nothing in this file
-authorizes spending, provider access or changes to a user's project by itself.
-
-## Execution and authority
-
-- Follow the user's explicit instructions and the project's approved contract.
-- New installations use standalone Claude Code execution; external review is optional
-  and separately configured. Preserve existing execution/profile obligations on update.
-- Codex may maintain and test framework source. It must not replace Claude Code agents
-  to claim actual NCCGS game orchestration. Installed files, configured models and
-  synthetic tests are not provider execution evidence.
-- Use actual correlated native worker observations. Unknown model, effort or usage
-  remains unknown. Never infer execution from a requested alias or a handoff marker.
-- Preserve failed attempts, negative reviews, task history, evidence and consumed
-  allowances. An update, migration, retry or new report must not reset spent budgets.
-- Uninstall only from an external terminal after sessions and owned work stop.
-  Preserve game source, custom files and .nccgs history/budgets. Uninstall never
-  closes tasks, waives review/acceptance or authorizes deleting retained records.
-- Known-solution or contaminated benchmark baselines remain reference-only; do not
-  score them as independent NCCGS runs.
-
-## Delivery and evidence
-
-- Evaluate brief fidelity, implementation, tests, integration, review/repair and
-  evidence-backed handoff. Product balance and feel are separate unless the contract
-  explicitly includes them. Do not expand a delivery task into an unrequested study.
-- Keep approved gameplay rules, formulas and UI/accessibility requirements. A correct
-  loss can pass a behavior test. Disclosed fixtures may arrange preconditions but must
-  exercise real logic rather than inject the asserted outcome.
-- Automatic acceptance requires current measured assertions; helper exit zero and a
-  reviewer boolean alone do not prove success. Reject missing, stale or malformed data.
-- A completed independent reviewer owns its exact verdict/findings/conditions. PASS
-  requires no unresolved mandatory conditions; do not translate or edit its verdict.
-- Technical acceptance, human/Product Owner acceptance and benchmark claims are distinct.
-  Never claim broad performance, quality or productivity from one supported case.
-- Keep frozen evaluations unchanged when maintaining the framework or preparing a release.
-
-## Operational boundaries
-
-- Launch/resume through nccgs run. Honor native, OS, managed, destructive-action and
-  project permission constraints; do not repeatedly request already-authorized routine work.
-- Use foreground Agent calls and managed verification jobs for long engine checks.
-  Keep process ownership, finite time/cost/dispatch limits and interruption evidence.
-  Never escape ownership through a detached or WMI-launched process.
-- Task lifecycle commands are one plain invocation per shell call, without pipes,
-  redirection or chained commands. Read task state with inspect.
-- Check effective native role limits; prompt text does not change maxTurns. The
-  reviewer ceiling is 200 turns, not a target or a budget extension.
-- Use reviewed design readiness for features and exact bounded repair packets when
-  required. Read the relevant protocols rather than guessing governance syntax.
-- Preserve bundled third-party licenses and attribution, including Ponytail guidance
-  and the official Unity Skills. Additional guidance does not waive acceptance gates.
-
-For runtime detail, read protocols/standalone.md, protocols/delivery-acceptance.md,
-protocols/design-lifecycle.md, protocols/review-handoff.md, protocols/bounded-repair.md
-and protocols/task-autonomy.md as applicable.

package/.claude/nccgs/THIRD_PARTY_NOTICES.md

@@ -1,29 +0,0 @@
-# Third-party notices installed with NCCGS
-
-## Ponytail
-
-The [shared Ponytail package](packages/ponytail/README.md) borrows and adapts selected
-content from **Ponytail by DietrichGebert**, v4.10.3, commit
-`c982cd411abb53323c4baa1baa3c2f020b8d0b08`.
-
-- Source: https://github.com/DietrichGebert/ponytail
-- Copyright (c) 2026 DietrichGebert.
-- License: MIT, with the complete original text in [LICENSE](packages/ponytail/LICENSE).
-- Attribution and NCCGS modifications: [NOTICE.md](packages/ponytail/NOTICE.md).
-
-Retain that license and attribution when copying or redistributing the package.
-This shared guidance is an adaptation, not the unmodified upstream plugin.
-
-## Other components
-
-The Unity Skills directories recorded in `unity-skills-manifest.json` are an
-unmodified snapshot from Unity Technologies. They are governed by the Unity
-Companion License for Unity-dependent projects.
-
-- Source: https://github.com/Unity-Technologies/skills
-- License: https://unity3d.com/legal/licenses/unity_companion_license
-
-NCCGS was informed by Donchitos/Claude-Code-Game-Studios, supplied under the MIT
-License: https://github.com/Donchitos/Claude-Code-Game-Studios
-
-Do not remove this notice while the vendored Unity Skills remain installed.

package/.claude/nccgs/VERSION

@@ -1 +0,0 @@
-2.1.1