@jstn-sdk/rcs 0.1.0 → 0.1.1

package/docs/reference/roblox-workspace-standard.md

@@ -0,0 +1,83 @@
+# Roblox Workspace Standard
+
+Status: canonical Roblox Studio workspace layer for active repository development.
+
+## Purpose
+
+This repo is no longer just a CLI/runtime layer. It now defines a baseline Roblox Studio
+workspace standard so creator work can live in source-controlled Luau artifacts instead of
+only in prompts, docs, and playground notes.
+
+Optional live Studio truth can be layered on top through:
+- [`docs/reference/robloxstudio-mcp-compatibility.md`](./robloxstudio-mcp-compatibility.md)
+
+## Canonical Workspace Files
+
+- `default.project.json` — Rojo source-of-truth mapping into Roblox Studio services
+- `wally.toml` — Roblox package manifest
+- `aftman.toml` — pinned local toolchain for Rojo, Wally, StyLua, Selene, and Lune
+- `stylua.toml` — Luau formatter rules
+- `selene.toml` — Luau lint rules
+
+## Canonical Source Tree
+
+Active Roblox source now lives under:
+
+- `src/roblox/ReplicatedFirst/`
+- `src/roblox/ReplicatedStorage/`
+- `src/roblox/ServerScriptService/`
+- `src/roblox/ServerStorage/`
+- `src/roblox/StarterGui/`
+- `src/roblox/StarterPlayer/`
+- `src/roblox/TestService/`
+- `src/roblox/Workspace/`
+
+## GUI Stack Decision
+
+Greenfield default for this repo is:
+- strict Luau
+- `ScreenGui` / `Frame` / `TextLabel` / `TextButton` / `UIListLayout` style Studio primitives
+- shared design-token modules under `ReplicatedStorage`
+- client controllers under `StarterPlayerScripts` or `StarterGui`
+
+Do not assume Roact, ReactLua, or Fusion as the default stack unless repo evidence explicitly
+introduces one. RCS should prefer a plain Studio-native baseline first.
+
+## Plugin Source Standard
+
+Studio plugin source should live under:
+- `src/studio-plugin/`
+
+Expected module slices:
+- `PluginMain.luau`
+- `Toolbar.luau`
+- `Widget.luau`
+- `Commands.luau`
+- `State.luau`
+
+This is the canonical source layout for plugin work, even if plugin packaging/build flow
+evolves later.
+
+## Test Standard
+
+Roblox workspace verification should include:
+- `--!strict` Luau modules by default
+- `TestService` specs for critical shared/runtime contracts
+- lint/format toolchain via Selene + StyLua
+- optional future package/framework adoption only when repo evidence justifies it
+- optional live Studio MCP inspection/write lane only when the creator explicitly enables the upstream plugin/server standard
+
+## Asset and GUI Artifact Standard
+
+Shared creator-facing asset contracts should live under:
+- `ReplicatedStorage/Assets/`
+- `ReplicatedStorage/Gui/`
+
+Use manifest modules for:
+- icons
+- sounds
+- image ids
+- design tokens
+- widget/layout constants
+
+Do not scatter raw asset ids or visual constants across unrelated scripts.

package/docs/reference/robloxstudio-mcp-compatibility.md

@@ -0,0 +1,117 @@
+# robloxstudio-mcp Compatibility
+
+Status: optional live Roblox Studio connection standard for RCS.
+
+## Purpose
+
+RCS already provides:
+- creator workflow guidance
+- local CLI/runtime orchestration
+- first-party MCP servers for state, memory, code-intel, trace, and wiki
+
+What it does **not** provide by itself is a live bridge into an open Roblox Studio session for
+real-time structure inspection, script reads, script writes, object creation, or screenshot capture.
+
+For that lane, RCS adopts compatibility with the upstream standard:
+- upstream repo: `https://github.com/boshyxd/robloxstudio-mcp`
+- packages:
+  - `robloxstudio-mcp`
+  - `robloxstudio-mcp-inspector`
+
+## When To Use It
+
+Use `robloxstudio-mcp` when you need:
+- live Roblox Studio hierarchy reads
+- script edits against an open Studio session
+- object/property inspection without exporting the place manually
+- faster feedback for plugin/widget/UI iteration
+- real-time environment truth instead of filesystem-only inference
+
+Use `robloxstudio-mcp-inspector` when you want:
+- read-only safety
+- live inspection without write access
+- lower-risk debugging or repo/studio comparison work
+
+## Why It Fits RCS
+
+RCS is the workflow/runtime layer.
+`robloxstudio-mcp` is the live Studio transport layer.
+
+They solve different problems and compose cleanly:
+- RCS keeps the creator workflow strict and Roblox-native
+- `robloxstudio-mcp` gives a live Studio connection when the creator wants real-time truth
+
+## Recommended Standard
+
+1. Install the upstream Studio plugin from the upstream release flow.
+2. Enable **Allow HTTP Requests** in Roblox Studio.
+3. Connect Codex with one of the standard commands:
+
+### Full live Studio write lane
+
+```bash
+codex mcp add robloxstudio -- npx -y robloxstudio-mcp@latest
+```
+
+### Read-only live Studio inspection lane
+
+```bash
+codex mcp add robloxstudio-inspector -- npx -y robloxstudio-mcp-inspector@latest
+```
+
+### Windows fallback
+
+If `npx` transport is unreliable on Windows shells, use:
+
+```json
+{
+  "mcpServers": {
+    "robloxstudio": {
+      "command": "cmd",
+      "args": ["/c", "npx", "-y", "robloxstudio-mcp@latest"]
+    },
+    "robloxstudio-inspector": {
+      "command": "cmd",
+      "args": ["/c", "npx", "-y", "robloxstudio-mcp-inspector@latest"]
+    }
+  }
+}
+```
+
+## RCS Policy
+
+RCS does **not** auto-install or silently auto-enable this third-party MCP server in setup.
+
+Reasons:
+- it depends on a separate Studio plugin
+- it needs HTTP enabled in Studio
+- it expands the live write surface into an open Studio session
+- creators should opt into that trust boundary deliberately
+
+RCS therefore treats this as an **optional standard compatibility lane**, not a forced default.
+
+## How To Use It Inside RCS
+
+When connected, prefer the live Studio MCP lane for:
+- confirming current Explorer hierarchy
+- reading actual live script contents from Studio
+- checking whether a remote, widget, or GUI object already exists
+- validating live plugin/widget state
+
+Prefer the repo filesystem/Rojo/workspace lane for:
+- source-of-truth Luau modules under version control
+- PR review and deterministic diffs
+- toolchain formatting/lint rules
+- workspace structure and plugin source standards
+
+Best practice:
+- use the live Studio lane to inspect truth in the open session
+- use the repo workspace lane to keep source-controlled artifacts canonical
+
+## Templates
+
+RCS ships ready examples:
+- `templates/roblox/robloxstudio-mcp.codex.json`
+- `templates/roblox/robloxstudio-mcp.windows.json`
+
+Use them as starting points, not as proof that the live plugin is already installed.

package/docs/reference/semantic-design-system.md

@@ -0,0 +1,110 @@
+# Semantic Design System
+
+Status: canonical structure contract for prompts, skills, missions, and guidance.
+
+## Purpose
+
+This file defines the semantic system that active repo surfaces must follow so the project reads
+as one coherent Roblox-native product rather than a collection of unrelated role/workflow texts.
+
+The semantic system has three pillars:
+- canonical vocabulary
+- surface taxonomy
+- per-surface schema requirements
+
+Canonical vocabulary is defined in:
+- [`docs/reference/canonical-vocabulary.md`](./canonical-vocabulary.md)
+
+## Surface Taxonomy
+
+| Surface | Purpose | Required posture |
+|---|---|---|
+| prompts | internal specialist execution surfaces | narrow, grounded, non-product-primary |
+| skills | canonical or operator workflows | explicit workflow boundaries |
+| missions | semantic creator design/evaluation contracts | Roblox-first problem framing |
+| AGENTS/runtime guidance | orchestration brain | canonical routing + vocabulary enforcement |
+
+## Metadata Contract
+
+Active prompts, skills, missions, and sandboxes must expose machine-readable frontmatter with:
+- `surface-class`
+- `domain`
+- `audience`
+- `artifact-type`
+
+Allowed values:
+- `surface-class`: `canonical`, `operator`, `internal`, `historical`
+- `domain`: `roblox-studio`, `creator-runtime`, `archive`
+- `audience`: `creator`, `operator`, `internal`, `archive`
+- `artifact-type`: `prompt`, `skill`, `mission`, `sandbox`
+
+## Prompt Contract
+
+Prompts must:
+- use the canonical vocabulary by default
+- stay role-scoped, not product-onboarding scoped
+- prefer Roblox/creator examples when examples are needed
+- avoid teaching removed compatibility roles as the normal mental model
+- be classified as `internal` prompt surfaces unless they are intentionally archived
+
+## Skill Contract
+
+Skills must be classified as one of:
+- canonical
+- operator
+- internal
+- historical
+
+Canonical skills must:
+- be Roblox Studio / creator native in name, examples, and remit
+- point to real creator outcomes
+- avoid generic web-enterprise framing by default
+
+## Mission Contract
+
+Every mission bundle should communicate the same semantic shape.
+
+### `mission.md` required sections
+
+1. Title
+2. Creator Outcome
+3. Player Outcome
+4. Deliverable
+5. Roblox Touchpoints
+6. Required Services
+7. Acceptance Signals
+8. Server-Authority Risks
+9. Anti-Patterns
+10. Forbidden Language
+11. Reference Layers
+12. Validation
+
+### `sandbox.md` required sections
+
+1. evaluation command
+2. scope statement
+3. tightly scoped lab/playground path
+4. out-of-scope statement
+5. required services
+6. acceptance signals
+7. anti-patterns
+8. forbidden language
+9. reference layers
+10. vocabulary guardrail
+
+## Archive Rule
+
+Historical surfaces may describe deleted/generic role labels, but:
+- they should be clearly archival
+- they should not be used as active onboarding
+- they should not be required by active runtime/catalog behavior
+
+## Enforcement
+
+The repo should keep lightweight tests that verify:
+- canonical vocabulary doc exists
+- AGENTS/skills reference the canonical vocabulary
+- active prompts/skills/missions expose valid taxonomy metadata
+- mission files follow the semantic mission schema
+- generated surface-map output stays synced to taxonomy metadata
+- active public/generated surfaces do not re-expose removed compatibility labels

package/docs/reference/surface-map.md

@@ -0,0 +1,131 @@
+# Surface Map
+
+Status: generated map of active taxonomy-classified prompt, skill, and mission surfaces.
+
+Sources:
+- [`docs/reference/canonical-vocabulary.md`](./canonical-vocabulary.md)
+- [`docs/reference/semantic-design-system.md`](./semantic-design-system.md)
+
+## Counts
+
+- canonical: 30
+- operator: 31
+- internal: 24
+- historical: 3
+- total tracked surfaces: 88
+
+## Canonical Surfaces
+
+| Path | Type | Domain | Audience | Surface |
+| --- | --- | --- | --- | --- |
+| `missions/cross-server-party-flow/mission.md` | `mission` | `roblox-studio` | `creator` | Cross-Server Party Flow |
+| `missions/cross-server-party-flow/sandbox.md` | `sandbox` | `roblox-studio` | `creator` | cross-server-party-flow sandbox |
+| `missions/gui-onboarding-clarity/mission.md` | `mission` | `roblox-studio` | `creator` | GUI Onboarding Clarity |
+| `missions/gui-onboarding-clarity/sandbox.md` | `sandbox` | `roblox-studio` | `creator` | gui-onboarding-clarity sandbox |
+| `missions/liveops-reward-loop-balance/mission.md` | `mission` | `roblox-studio` | `creator` | Live-Ops Reward Loop Balance |
+| `missions/liveops-reward-loop-balance/sandbox.md` | `sandbox` | `roblox-studio` | `creator` | liveops-reward-loop-balance sandbox |
+| `missions/profile-datastore-recovery/mission.md` | `mission` | `roblox-studio` | `creator` | Profile DataStore Recovery |
+| `missions/profile-datastore-recovery/sandbox.md` | `sandbox` | `roblox-studio` | `creator` | profile-datastore-recovery sandbox |
+| `missions/remote-contract-hardening/mission.md` | `mission` | `roblox-studio` | `creator` | Remote Contract Hardening |
+| `missions/remote-contract-hardening/sandbox.md` | `sandbox` | `roblox-studio` | `creator` | remote-contract-hardening sandbox |
+| `skills/autoforge/SKILL.md` | `skill` | `roblox-studio` | `creator` | autoforge |
+| `skills/blueprint-loop/SKILL.md` | `skill` | `roblox-studio` | `creator` | blueprint-loop |
+| `skills/blueprint-psych/SKILL.md` | `skill` | `roblox-studio` | `creator` | blueprint-psych |
+| `skills/blueprint-retention/SKILL.md` | `skill` | `roblox-studio` | `creator` | blueprint-retention |
+| `skills/blueprint-social/SKILL.md` | `skill` | `roblox-studio` | `creator` | blueprint-social |
+| `skills/blueprint/SKILL.md` | `skill` | `roblox-studio` | `creator` | blueprint |
+| `skills/brief-audience/SKILL.md` | `skill` | `roblox-studio` | `creator` | brief-audience |
+| `skills/brief-motivation/SKILL.md` | `skill` | `roblox-studio` | `creator` | brief-motivation |
+| `skills/brief/SKILL.md` | `skill` | `roblox-studio` | `creator` | brief |
+| `skills/crew/SKILL.md` | `skill` | `roblox-studio` | `creator` | crew |
+| `skills/forge-community/SKILL.md` | `skill` | `roblox-studio` | `creator` | forge-community |
+| `skills/forge-daily-loop/SKILL.md` | `skill` | `roblox-studio` | `creator` | forge-daily-loop |
+| `skills/forge-event-loop/SKILL.md` | `skill` | `roblox-studio` | `creator` | forge-event-loop |
+| `skills/forge-fomo/SKILL.md` | `skill` | `roblox-studio` | `creator` | forge-fomo |
+| `skills/forge-mastery/SKILL.md` | `skill` | `roblox-studio` | `creator` | forge-mastery |
+| `skills/forge-progression/SKILL.md` | `skill` | `roblox-studio` | `creator` | forge-progression |
+| `skills/forge-reward-loop/SKILL.md` | `skill` | `roblox-studio` | `creator` | forge-reward-loop |
+| `skills/forge-status/SKILL.md` | `skill` | `roblox-studio` | `creator` | forge-status |
+| `skills/forge/SKILL.md` | `skill` | `roblox-studio` | `creator` | forge |
+| `skills/visual-forge/SKILL.md` | `skill` | `roblox-studio` | `creator` | visual-forge |
+
+## Operator Surfaces
+
+| Path | Type | Domain | Audience | Surface |
+| --- | --- | --- | --- | --- |
+| `skills/ai-slop-cleaner/SKILL.md` | `skill` | `creator-runtime` | `operator` | ai-slop-cleaner |
+| `skills/analyze/SKILL.md` | `skill` | `creator-runtime` | `operator` | analyze |
+| `skills/ask-claude/SKILL.md` | `skill` | `creator-runtime` | `operator` | ask-claude |
+| `skills/ask-gemini/SKILL.md` | `skill` | `creator-runtime` | `operator` | ask-gemini |
+| `skills/autopilot/SKILL.md` | `skill` | `creator-runtime` | `operator` | autopilot |
+| `skills/autoresearch/SKILL.md` | `skill` | `creator-runtime` | `operator` | autoresearch |
+| `skills/build-fix/SKILL.md` | `skill` | `creator-runtime` | `operator` | build-fix |
+| `skills/cancel/SKILL.md` | `skill` | `creator-runtime` | `operator` | cancel |
+| `skills/code-review/SKILL.md` | `skill` | `creator-runtime` | `operator` | code-review |
+| `skills/configure-notifications/SKILL.md` | `skill` | `creator-runtime` | `operator` | configure-notifications |
+| `skills/deep-interview/SKILL.md` | `skill` | `creator-runtime` | `operator` | deep-interview |
+| `skills/deepsearch/SKILL.md` | `skill` | `creator-runtime` | `operator` | deepsearch |
+| `skills/doctor/SKILL.md` | `skill` | `creator-runtime` | `operator` | doctor |
+| `skills/ecomode/SKILL.md` | `skill` | `creator-runtime` | `operator` | ecomode |
+| `skills/git-master/SKILL.md` | `skill` | `creator-runtime` | `operator` | git-master |
+| `skills/help/SKILL.md` | `skill` | `creator-runtime` | `operator` | help |
+| `skills/hud/SKILL.md` | `skill` | `creator-runtime` | `operator` | hud |
+| `skills/note/SKILL.md` | `skill` | `creator-runtime` | `operator` | note |
+| `skills/pipeline/SKILL.md` | `skill` | `creator-runtime` | `operator` | pipeline |
+| `skills/plan/SKILL.md` | `skill` | `creator-runtime` | `operator` | plan |
+| `skills/rcs-setup/SKILL.md` | `skill` | `creator-runtime` | `operator` | rcs-setup |
+| `skills/review/SKILL.md` | `skill` | `creator-runtime` | `operator` | review |
+| `skills/security-review/SKILL.md` | `skill` | `creator-runtime` | `operator` | security-review |
+| `skills/skill/SKILL.md` | `skill` | `creator-runtime` | `operator` | skill |
+| `skills/tdd/SKILL.md` | `skill` | `creator-runtime` | `operator` | tdd |
+| `skills/team/SKILL.md` | `skill` | `creator-runtime` | `operator` | team |
+| `skills/trace/SKILL.md` | `skill` | `creator-runtime` | `operator` | trace |
+| `skills/ultraqa/SKILL.md` | `skill` | `creator-runtime` | `operator` | ultraqa |
+| `skills/ultrawork/SKILL.md` | `skill` | `creator-runtime` | `operator` | ultrawork |
+| `skills/visual-verdict/SKILL.md` | `skill` | `creator-runtime` | `operator` | visual-verdict |
+| `skills/wiki/SKILL.md` | `skill` | `creator-runtime` | `operator` | wiki |
+
+## Internal Surfaces
+
+| Path | Type | Domain | Audience | Surface |
+| --- | --- | --- | --- | --- |
+| `prompts/analyst.md` | `prompt` | `creator-runtime` | `internal` | analyst |
+| `prompts/architect.md` | `prompt` | `creator-runtime` | `internal` | architect |
+| `prompts/build-fixer.md` | `prompt` | `creator-runtime` | `internal` | build-fixer |
+| `prompts/code-reviewer.md` | `prompt` | `creator-runtime` | `internal` | code-reviewer |
+| `prompts/code-simplifier.md` | `prompt` | `creator-runtime` | `internal` | code-simplifier |
+| `prompts/critic.md` | `prompt` | `creator-runtime` | `internal` | critic |
+| `prompts/debugger.md` | `prompt` | `creator-runtime` | `internal` | debugger |
+| `prompts/dependency-expert.md` | `prompt` | `creator-runtime` | `internal` | dependency-expert |
+| `prompts/designer.md` | `prompt` | `creator-runtime` | `internal` | designer |
+| `prompts/executor.md` | `prompt` | `creator-runtime` | `internal` | executor |
+| `prompts/explore-harness.md` | `prompt` | `creator-runtime` | `internal` | explore-harness |
+| `prompts/explore.md` | `prompt` | `creator-runtime` | `internal` | explore |
+| `prompts/git-master.md` | `prompt` | `creator-runtime` | `internal` | git-master |
+| `prompts/planner.md` | `prompt` | `creator-runtime` | `internal` | planner |
+| `prompts/researcher.md` | `prompt` | `creator-runtime` | `internal` | researcher |
+| `prompts/security-reviewer.md` | `prompt` | `creator-runtime` | `internal` | Security Review Report (Roblox) |
+| `prompts/sisyphus-lite.md` | `prompt` | `creator-runtime` | `internal` | sisyphus-lite |
+| `prompts/team-executor.md` | `prompt` | `creator-runtime` | `internal` | team-executor |
+| `prompts/team-orchestrator.md` | `prompt` | `creator-runtime` | `internal` | team-orchestrator |
+| `prompts/test-engineer.md` | `prompt` | `creator-runtime` | `internal` | test-engineer |
+| `prompts/verifier.md` | `prompt` | `creator-runtime` | `internal` | verifier |
+| `prompts/vision.md` | `prompt` | `creator-runtime` | `internal` | vision |
+| `prompts/writer.md` | `prompt` | `creator-runtime` | `internal` | writer |
+| `skills/worker/SKILL.md` | `skill` | `creator-runtime` | `internal` | worker |
+
+## Historical Surfaces
+
+| Path | Type | Domain | Audience | Surface |
+| --- | --- | --- | --- | --- |
+| `skills/forge-init/SKILL.md` | `skill` | `archive` | `archive` | forge-init |
+| `skills/swarm/SKILL.md` | `skill` | `archive` | `archive` | swarm |
+| `skills/web-clone/SKILL.md` | `skill` | `archive` | `archive` | web-clone |
+
+## Additional Repo Lanes
+
+- `AGENTS.md` and `templates/AGENTS.md` remain the orchestration brain and guidance authority.
+- `docs/archive/` is the historical lane; archive content may describe removed surfaces but must not act as active onboarding.
+- `src/catalog/manifest.json`, `templates/catalog-manifest.json`, and `src/catalog/generated/public-catalog.json` are the catalog source/generated contract lane.
+- `dist/` is generated runtime output and should reflect the taxonomy, not redefine it.
+

package/docs/reference/team-allocation-rebalance-policy.md

@@ -47,7 +47,7 @@ To keep the upgrade incremental and reversible, separate **signal collection** f
 
 ## Repo-aware DAG handoff seam
 
-The repo-aware RALPLAN -> Team handoff should enter before `startTeam()` and before worker inbox generation. Keep the decomposition gate as a bounded preflight module that returns normalized startup tasks, an effective worker count, and an inspectable metadata/report payload. Runtime dispatch should remain unchanged: workers still receive tasks through inboxes and must claim through the existing lifecycle APIs.
+The repo-aware BLUEPRINT -> Team handoff should enter before `startTeam()` and before worker inbox generation. Keep the decomposition gate as a bounded preflight module that returns normalized startup tasks, an effective worker count, and an inspectable metadata/report payload. Runtime dispatch should remain unchanged: workers still receive tasks through inboxes and must claim through the existing lifecycle APIs.
 
 Preflight allocation may use DAG `filePaths`, `domains`, `lane`, and symbolic dependency metadata to improve owner assignment, but only concrete runtime task IDs should reach `blocked_by` / `depends_on`. Rich metadata belongs in a decomposition report or manifest policy block unless the Team task schema intentionally supports it.
 

package/docs/release-notes-v0.1.0.md

@@ -4,7 +4,7 @@
 
 ## Summary
 
-`v0.1.0` is the first strict RCS-owned ship candidate after the fork-to-RCS transition. This release consolidates the retained pre-v0.1.0 release-note train into one canonical archival note and defines the current shipped product surface as **Roblox Creator Skills for Codex**.
+`v0.1.0` is the first strict RCS-owned ship candidate after the package and product transition into Roblox Creator Skills. This release consolidates the retained pre-v0.1.0 release-note train into one canonical archival note and defines the current shipped product surface as **Roblox Creator Skills for Codex**.
 
 ## Canonical product surface
 

package/docs/release-notes-v0.1.1.md

@@ -0,0 +1,49 @@
+# Roblox Creator Skills v0.1.1
+
+## Summary
+
+`v0.1.1` is the first hardening release after the initial `0.1.0` ship line. It turns the repo into a more coherent Roblox Studio product/workspace by tightening public identity, enforcing a semantic system, adding a real workspace standard, and documenting optional live Studio MCP compatibility.
+
+## Canonical product surface
+
+- Package: `@jstn-sdk/rcs`
+- Owner: `JustineDevs`
+- Repository: `https://github.com/JustineDevs/roblox-ai-os`
+- Product: `Roblox Creator Skills`
+- Short identity: `RCS`
+
+## What changed
+
+- Public surface hardening:
+  - Roblox-native prompts, skills, missions, docs, README, and generated catalog
+  - cleanup of older compatibility wording on active surfaces
+- Semantic enforcement:
+  - canonical vocabulary
+  - semantic design system
+  - machine-readable surface taxonomy
+  - generated surface map
+  - contract tests for semantic/workflow drift
+- Roblox workspace standard:
+  - `default.project.json`
+  - `wally.toml`
+  - `aftman.toml`
+  - `stylua.toml`
+  - `selene.toml`
+  - canonical Luau source tree
+  - canonical Studio plugin source layout
+- Optional live Studio connection:
+  - documented `robloxstudio-mcp` compatibility lane
+  - shipped Codex MCP template configs
+- CI and release proof:
+  - final CI proof artifact
+  - stronger release/workflow verification contracts
+
+## Verification
+
+- `npm run build`
+- targeted semantic/taxonomy/workspace/compatibility verification suites
+- top-level release proof rerun with post-checks
+
+## Notes
+
+This release keeps `robloxstudio-mcp` as an explicit optional compatibility layer rather than silently enabling a third-party live Studio write transport during default RCS setup. That separation is intentional.

package/docs/reports/open-prs-dev-readiness-2026-04-09.md

@@ -8,7 +8,7 @@ Current `dev` head reviewed: `8656d21149a0772369f697df002f7bf85002db8d`.
 
 Push run `24141814673` on `dev` finished red because long jobs were cancelled, not because the fast validation jobs failed.
 
-- Passed on `dev`: Rust Format, Rust Clippy, Lint, Typecheck (Node 20/22), Test (Node 22 / smoke), Coverage Report (Rust), Coverage Gate (Team Critical), Ralph Persistence Gate.
+- Passed on `dev`: Rust Format, Rust Clippy, Lint, Typecheck (Node 20/22), Test (Node 22 / smoke), Coverage Report (Rust), Coverage Gate (Team Critical), Forge Persistence Gate.
 - Cancelled on `dev`: `Test (Node 20 / full)`, `Coverage Report (TypeScript Full)`.
 - Failed gate: `CI Status`.
 - Workflow reason: `.github/workflows/ci.yml:260-289` requires every `needs.*.result` to equal `success`; cancelled/skipped results force the gate red.
@@ -19,7 +19,7 @@ Push run `24141814673` on `dev` finished red because long jobs were cancelled, n
 | --- | --- | --- | --- | --- |
 | #1403 | Shared-session shutdown hardening + regression coverage | Fast checks mostly green, but both Typecheck jobs failed in run `24173665271`; full Node 20 suite still running | **Hard blocker:** `npm run check:no-unused` fails locally on PR head `e802eff1` with `src/team/runtime.ts(20,3): error TS6133: 'isNativeWindows' is declared but its value is never read.` | **Do not merge yet.** Fix unused import, rerun PR CI, then reassess. |
 | #1402 | tmux HUD self-healing / prompt-submit reconcile | Lint, typecheck, smoke, rust coverage, team coverage gate passed; full Node 20 and TS full coverage still pending | Pending long jobs; touches `src/cli`, `src/hud`, and native-hook operational events, so I would not merge before `dev` CI is green | **Good candidate once long jobs finish green and `dev` is green.** Recommended ahead of docs-only work. |
-| #1400 | Unknown `$token` duplicate continuation + stale Ralph state fix | Lint, typecheck, smoke, rust coverage, team coverage gate passed; full Node 20 and TS full coverage still pending | Pending long jobs; overlaps `src/scripts/codex-native-hook.ts` and its tests with #1380 | **Merge after #1380 is in `dev`, then rebase/retest.** Otherwise likely conflict/re-review churn. |
+| #1400 | Unknown `$token` duplicate continuation + stale Forge state fix | Lint, typecheck, smoke, rust coverage, team coverage gate passed; full Node 20 and TS full coverage still pending | Pending long jobs; overlaps `src/scripts/codex-native-hook.ts` and its tests with #1380 | **Merge after #1380 is in `dev`, then rebase/retest.** Otherwise likely conflict/re-review churn. |
 | #1382 | Stale team worktree cleanup at startup | PR is open, but its head commit `e5f9ffe7...` is already an ancestor of current `dev` head | No merge work left; CI Status failure is stale noise from cancelled long jobs on an already-landed change | **Close as stale/already merged.** No merge needed. |
 | #1380 | Stale deep-interview stop-hook gating fix | Fast checks passed; CI Status failed only because long jobs were cancelled in old run `24142611197` | Long jobs were cancelled; overlaps same native-hook files as #1400 | **Best first merge among the hook fixes once `dev` CI is green.** Land before #1400. |
 | #1357 | AGENTS/template token reduction | Fast checks passed; CI Status failed only because long jobs were cancelled in old run `24145469951` | Long jobs cancelled; PR body/checklist says only two files changed, but diff also changes `CLAUDE.md` | **Hold for manual review after runtime fixes.** Lower urgency than #1380/#1400/#1402. |

package/docs/shared/agent-tiers.md

@@ -17,11 +17,11 @@ Use role to choose responsibility, tier to choose depth, and posture to choose o
 - `LOW`:
   Fast lookups and narrow checks.
   Use for simple exploration, style checks, and lightweight doc edits.
-  Typical roles: `explore`, `style-reviewer`, `writer`.
+  Typical roles: `explore`, `writer`.
 
 - `STANDARD`:
   Default tier for implementation, debugging, and normal verification.
-  Typical roles: `executor`, `debugger`, `test-engineer`, `quality-reviewer`.
+  Typical roles: `executor`, `debugger`, `test-engineer`, `code-reviewer`.
 
 - `THOROUGH`:
   Use for architectural, security-sensitive, or high-impact multi-file work.
@@ -36,7 +36,7 @@ Use role to choose responsibility, tier to choose depth, and posture to choose o
    - security/auth/trust-boundary changes
    - architectural decisions with system-wide impact
    - large refactors across many files
-4. For Ralph completion checks, use at least `STANDARD` architect verification.
+4. For Forge completion checks, use at least `STANDARD` architect verification.
 
 ## Posture Guidance
 

package/docs/skills.html

@@ -63,17 +63,16 @@
         <li>Map each driver through mechanic patterns, UI feedback, economy impact, retention impact, monetization fit, risk notes, and Roblox-fit notes.</li>
       </ul>
 
-      <h2>Compatibility Runtime Layers</h2>
-      <p class="muted">These are advanced lower-level execution layers. They remain available for compatibility, diagnostics, and operator control, but they are not the primary creator workflow.</p>
+      <h2>Advanced Execution Surfaces</h2>
+      <p class="muted">These are advanced operator surfaces. They are useful for diagnostics, parallel coordination, or focused verification, but they are not the primary creator workflow.</p>
       <ul>
-        <li><code>$team</code> - lower-level coordinated team runtime retained for compatibility and operational control.</li>
-        <li><code>$ralph</code> - lower-level persistence loop retained for compatibility and runtime control.</li>
-        <li><code>$autopilot</code> - lower-level autonomous execution runtime retained for compatibility.</li>
-        <li><code>$ultrawork</code> - lower-level max-parallel execution mode retained for compatibility.</li>
+        <li><code>$team</code> - coordinated parallel execution when a creator plan needs durable staffing.</li>
+        <li><code>$forge</code> - persistent implementation and verification loop.</li>
+        <li><code>$autopilot</code> - autonomous execution runtime for advanced operator use.</li>
+        <li><code>$ultrawork</code> - max-parallel execution mode.</li>
         <li><code>$visual-verdict</code> - structured visual QA loop for screenshot/reference matching</li>
         <li><code>$ecomode</code> - token-efficient model routing</li>
         <li><code>$ultraqa</code> - test/verify/fix loop</li>
-        <li><code>$swarm</code> - team compatibility facade</li>
       </ul>
 
       <h2>Planning & Clarification</h2>
@@ -81,7 +80,7 @@
         <li><code>$brief</code> - canonical briefing surface</li>
         <li><code>$blueprint</code> - canonical planning surface</li>
         <li><code>$plan</code> - supporting strategic planning when you are not using the canonical creator path</li>
-        <li><code>$deep-interview</code> and <code>$ralplan</code> remain available as compatibility/internal planning layers.</li>
+        <li><code>$deep-interview</code> - ambiguity-gated requirements clarification before implementation.</li>
       </ul>
 
       <h2>Agent Shortcuts</h2>
@@ -92,8 +91,8 @@
         <li><code>$build-fix</code></li>
         <li><code>$code-review</code></li>
         <li><code>$security-review</code></li>
-        <li><code>$visual-ralph</code> (advanced compatibility visual runtime)</li>
-        <li><code>$frontend-ui-ux</code></li>
+        <li><code>$visual-forge</code> (advanced visual-delivery runtime)</li>
+        <li><code>$visual-forge</code></li>
         <li><code>$git-master</code></li>
         <li><code>$review</code></li>
       </ul>
@@ -103,8 +102,7 @@
         <li><code>$cancel</code>, <code>$doctor</code>, <code>$help</code>, <code>$note</code>, <code>$trace</code></li>
         <li><code>$skill</code></li>
         <li><code>$hud</code>, <code>$rcs-setup</code>, <code>$configure-notifications</code></li>
-        <li><code>$ralph-init</code> (legacy compatibility helper)</li>
-        <li><code>$worker</code> (internal) - team worker protocol / lifecycle</li>
+        <li><code>$forge-init</code> (legacy helper)</li>
       </ul>
 
       <h2>Usage Examples</h2>

package/docs/troubleshooting.md

@@ -16,7 +16,7 @@ rcs exec --skip-git-repo-check -C . "Reply with exactly RCS-EXEC-OK"
 Treat the boundary this way:
 
 - Codex plugin install/discovery may cache `roblox-ai-os-creator-skills` under `${CODEX_HOME:-~/.codex}/plugins/cache/$MARKETPLACE_NAME/roblox-ai-os-creator-skills/$VERSION/` (with `local` possible as a version identifier for local installs). That confirms a marketplace/plugin artifact; the packaged plugin includes plugin-scoped companion metadata for MCP servers and apps, while native/runtime hooks remain setup-owned, so it is still not the full RCS runtime setup.
-- Plugin install/discovery is not a replacement for `npm install -g roblox-ai-os-creator-skills` plus `rcs setup`; legacy setup mode installs native agents and prompts, while plugin setup mode relies on plugin discovery for bundled skills and archives/removes legacy RCS-managed prompts/native-agent TOMLs so stale role files cannot shadow plugin behavior.
+- Plugin install/discovery is not a replacement for `npm install -g @jstn-sdk/rcs` plus `rcs setup`; legacy setup mode installs native agents and prompts, while plugin setup mode relies on plugin discovery for bundled skills and archives/removes legacy RCS-managed prompts/native-agent TOMLs so stale role files cannot shadow plugin behavior.
 - `rcs doctor` green: install and local runtime wiring look sane.
 - `codex login status` green: the active Codex profile can see login state.
 - `rcs exec ...` returns `RCS-EXEC-OK`: real execution, auth, provider routing, and current working-directory assumptions are working together.