@jstn-sdk/rcs 0.1.0 → 0.1.6

package/docs/STATE_MODEL.md

@@ -11,7 +11,7 @@ Public creator workflow language should lead with:
 - `$crew`
 - `$autoforge`
 
-The mode identifiers described below (`deep-interview`, `ralplan`, `ralph`, `team`, `autopilot`, and related runtime names) are lower-level runtime identifiers retained for execution, compatibility, and diagnostics.
+The mode identifiers described below (`deep-interview`, `blueprint`, `forge`, `team`, `autopilot`, and related runtime names) are lower-level runtime identifiers retained for execution and diagnostics.
 
 ## Goals
 
@@ -31,8 +31,8 @@ Authoritative workflow state lives in per-mode files under `.rcs/state/`:
 
 Examples:
 
-- `.rcs/state/ralplan-state.json`
-- `.rcs/state/sessions/<session_id>/ralph-state.json`
+- `.rcs/state/blueprint-state.json`
+- `.rcs/state/sessions/<session_id>/forge-state.json`
 - `.rcs/state/team-state.json`
 
 These files determine whether a workflow mode is active, completed, cancelled, or failed. Those mode phases are not always identical to the user-facing terminal lifecycle vocabulary; see the explicit terminal lifecycle section below for that compatibility boundary.
@@ -144,7 +144,7 @@ The requested mode is added without completing the source mode.
 
 Examples:
 
-- `team + ralph`
+- `team + forge`
 - `ultrawork + <any tracked mode>`
 
 ### C. Allow with source auto-complete
@@ -153,11 +153,11 @@ The source mode is terminalized and the destination becomes active.
 
 Current allowlisted forward handoffs between lower-level runtime identifiers:
 
-- `deep-interview -> ralplan`
-- `ralplan -> team`
-- `ralplan -> ralph`
-- `ralplan -> autopilot`
-- `autopilot -> ralplan` when Autopilot's code-review phase is not clean
+- `deep-interview -> blueprint`
+- `blueprint -> team`
+- `blueprint -> forge`
+- `blueprint -> autopilot`
+- `autopilot -> blueprint` when Autopilot's code-review phase is not clean
 
 ### D. Deny
 
@@ -167,16 +167,16 @@ The requested transition is not allowed and no state is changed.
 
 | From | To | Result |
 |---|---|---|
-| `deep-interview` | `ralplan` | auto-complete `deep-interview`, start `ralplan` |
-| `ralplan` | `team` | auto-complete `ralplan`, start `team` |
-| `ralplan` | `ralph` | auto-complete `ralplan`, start `ralph` |
-| `ralplan` | `autopilot` | auto-complete `ralplan`, start `autopilot` |
-| `autopilot` | `ralplan` | auto-complete `autopilot`, start `ralplan` for review-driven loopback |
-| `team` | `ralph` | allowed overlap |
-| `ralph` | `team` | allowed overlap |
+| `deep-interview` | `blueprint` | auto-complete `deep-interview`, start `blueprint` |
+| `blueprint` | `team` | auto-complete `blueprint`, start `team` |
+| `blueprint` | `forge` | auto-complete `blueprint`, start `forge` |
+| `blueprint` | `autopilot` | auto-complete `blueprint`, start `autopilot` |
+| `autopilot` | `blueprint` | auto-complete `autopilot`, start `blueprint` for review-driven loopback |
+| `team` | `forge` | allowed overlap |
+| `forge` | `team` | allowed overlap |
 | `<any tracked mode>` | `ultrawork` | allowed overlap |
 | `ultrawork` | `<any tracked mode>` | allowed overlap |
-| execution-like mode | planning-like mode | denied rollback auto-complete, except the explicit `autopilot -> ralplan` review loopback |
+| execution-like mode | planning-like mode | denied rollback auto-complete, except the explicit `autopilot -> blueprint` review loopback |
 | anything else non-allowlisted | new conflicting mode | denied |
 
 ## Planning-like vs execution-like
@@ -184,13 +184,13 @@ The requested transition is not allowed and no state is changed.
 ### Planning-like runtime identifiers
 
 - `deep-interview`
-- `ralplan`
+- `blueprint`
 - `autoresearch`
 
 ### Execution-like runtime identifiers
 
 - `team`
-- `ralph`
+- `forge`
 - `autopilot`
 - `ultrawork`
 - `ultraqa`
@@ -206,14 +206,14 @@ A single prompt can explicitly invoke multiple contiguous lower-level runtime `$
 Example:
 
 ```text
-$ralplan $team $ralph ship this fix
+$blueprint $team $forge ship this fix
 ```
 
 Expected result:
 
-1. `ralplan` is recognized as the planning source
+1. `blueprint` is recognized as the planning source
 2. simultaneous execution follow-ups are deferred instead of auto-starting
-3. final active skill remains `ralplan`
+3. final active skill remains `blueprint`
 4. deferred execution skills are surfaced in native-hook output for traceability
 5. native hook output should describe all explicit skills, not only the primary one
 
@@ -222,7 +222,7 @@ Public creator-facing UX should still prefer the canonical creator workflow fami
 Recommended message shape:
 
 - detected keywords summary
-- deferred-skill summary, e.g. `planning preserved over simultaneous execution follow-up; deferred skills: team, ralph`
+- deferred-skill summary, e.g. `planning preserved over simultaneous execution follow-up; deferred skills: team, forge`
 - final active skill / initialized state summary
 - team runtime hint only when `team` is actually among the final active skills
 
@@ -243,7 +243,7 @@ These rules should remain true unless intentionally changed:
 
 - rollback to planning never auto-completes
 - non-allowlisted transitions remain blocked
-- `ultrawork` overlap-any must not weaken `ralplan-first` gating
+- `ultrawork` overlap-any must not weaken `blueprint-first` gating
 - native-hook output is a presentation layer over shared transition results, not a separate decision engine
 - compatibility sync must not resurrect completed source modes
 

package/docs/agents.html

@@ -22,17 +22,17 @@
       <h1>Agent Catalog</h1>
       <p class="muted">Specialist agent reference for advanced use inside the canonical creator workflow.</p>
       <p>Start with <code>$brief</code>, then <code>$blueprint</code>, then execute with <code>$forge</code>, <code>$crew</code>, or <code>$autoforge</code>. Use the catalog below when you already know you need a specialist lane.</p>
-      <p class="muted">Lower-level engine-facing surfaces such as <code>$deep-interview</code>, <code>$ralplan</code>, <code>$ralph</code>, <code>$team</code>, and <code>$autopilot</code> remain available as compatibility/runtime layers rather than the primary onboarding path.</p>
+      <p class="muted">Lower-level engine-facing surfaces such as <code>$deep-interview</code>, <code>$blueprint</code>, <code>$team</code>, and <code>$autopilot</code> remain available as runtime layers rather than the primary onboarding path.</p>
 
       <h2>Build & Analysis</h2>
       <table>
         <thead><tr><th>Agent</th><th>Model</th><th>Description</th><th>Example</th></tr></thead>
         <tbody>
-          <tr><td>explore</td><td>low</td><td>Codebase discovery and symbol mapping.</td><td><code>explore "map auth flow"</code></td></tr>
+          <tr><td>explore</td><td>low</td><td>Codebase discovery and symbol mapping.</td><td><code>explore "map remote validation flow"</code></td></tr>
           <tr><td>analyst</td><td>high</td><td>Clarifies requirements and acceptance criteria.</td><td><code>analyst "define scope"</code></td></tr>
-          <tr><td>planner</td><td>high</td><td>Builds execution plans and sequencing.</td><td><code>planner "plan migration"</code></td></tr>
-          <tr><td>architect</td><td>high</td><td>System boundaries and architecture design.</td><td><code>architect "review service boundaries"</code></td></tr>
-          <tr><td>debugger</td><td>medium</td><td>Root-cause and regression diagnosis.</td><td><code>debugger "investigate flaky test"</code></td></tr>
+          <tr><td>planner</td><td>high</td><td>Builds execution plans and sequencing.</td><td><code>planner "plan profile migration safety checks"</code></td></tr>
+          <tr><td>architect</td><td>high</td><td>System boundaries and architecture design.</td><td><code>architect "review server-authority boundaries"</code></td></tr>
+          <tr><td>debugger</td><td>medium</td><td>Root-cause and regression diagnosis.</td><td><code>debugger "investigate flaky remote contract test"</code></td></tr>
           <tr><td>executor</td><td>medium</td><td>Implementation and refactoring work.</td><td><code>executor "add validation"</code></td></tr>
           <tr><td>verifier</td><td>medium</td><td>Evidence-backed completion checks.</td><td><code>verifier "verify release readiness"</code></td></tr>
         </tbody>
@@ -42,11 +42,7 @@
       <table>
         <thead><tr><th>Agent</th><th>Model</th><th>Description</th><th>Example</th></tr></thead>
         <tbody>
-          <tr><td>style-reviewer</td><td>low</td><td>Formatting and naming conventions.</td><td><code>style-reviewer "check style"</code></td></tr>
-          <tr><td>quality-reviewer</td><td>medium</td><td>Logic and maintainability defects.</td><td><code>quality-reviewer "review PR"</code></td></tr>
-          <tr><td>api-reviewer</td><td>medium</td><td>API contracts and compatibility.</td><td><code>api-reviewer "audit API changes"</code></td></tr>
           <tr><td>security-reviewer</td><td>medium</td><td>Security boundaries and vulnerabilities.</td><td><code>security-reviewer "security audit"</code></td></tr>
-          <tr><td>performance-reviewer</td><td>medium</td><td>Performance and complexity bottlenecks.</td><td><code>performance-reviewer "profile hotspots"</code></td></tr>
           <tr><td>code-reviewer</td><td>high</td><td>Comprehensive multi-axis code review.</td><td><code>code-reviewer "comprehensive review"</code></td></tr>
         </tbody>
       </table>
@@ -57,11 +53,9 @@
         <tbody>
           <tr><td>dependency-expert</td><td>medium</td><td>External SDK/API/package evaluation.</td><td><code>dependency-expert "compare SDK options"</code></td></tr>
           <tr><td>test-engineer</td><td>medium</td><td>Test strategy and coverage improvements.</td><td><code>test-engineer "write test plan"</code></td></tr>
-          <tr><td>quality-strategist</td><td>medium</td><td>Release quality and risk strategy.</td><td><code>quality-strategist "assess release risk"</code></td></tr>
           <tr><td>build-fixer</td><td>medium</td><td>Build/toolchain/type issue resolution.</td><td><code>build-fixer "fix CI failures"</code></td></tr>
           <tr><td>designer</td><td>medium</td><td>UI/UX architecture and interaction design.</td><td><code>designer "improve onboarding UX"</code></td></tr>
           <tr><td>writer</td><td>low</td><td>Documentation and user guidance.</td><td><code>writer "draft migration guide"</code></td></tr>
-          <tr><td>qa-tester</td><td>medium</td><td>Interactive runtime QA validation.</td><td><code>qa-tester "run manual QA pass"</code></td></tr>
           <tr><td>git-master</td><td>medium</td><td>Commit strategy and history hygiene.</td><td><code>git-master "prepare clean commit plan"</code></td></tr>
           <tr><td>code-simplifier (internal)</td><td>high</td><td>Post-stop code simplification and cleanup automation.</td><td><code>code-simplifier "simplify touched files"</code></td></tr>
           <tr><td>researcher</td><td>medium</td><td>Reference and external documentation research.</td><td><code>researcher "collect official API docs"</code></td></tr>
@@ -72,10 +66,8 @@
       <table>
         <thead><tr><th>Agent</th><th>Model</th><th>Description</th><th>Example</th></tr></thead>
         <tbody>
-          <tr><td>product-manager</td><td>medium</td><td>Problem framing and PRD definition.</td><td><code>product-manager "define user outcomes"</code></td></tr>
-          <tr><td>ux-researcher</td><td>medium</td><td>Usability and accessibility audits.</td><td><code>ux-researcher "run heuristic audit"</code></td></tr>
-          <tr><td>information-architect</td><td>medium</td><td>Navigation, taxonomy, and structure.</td><td><code>information-architect "improve docs IA"</code></td></tr>
-          <tr><td>product-analyst</td><td>medium</td><td>Metrics, funnels, and experiments.</td><td><code>product-analyst "analyze onboarding funnel"</code></td></tr>
+          <tr><td>analyst</td><td>high</td><td>Problem framing, requirements clarity, and acceptance criteria.</td><td><code>analyst "define creator outcomes"</code></td></tr>
+          <tr><td>designer</td><td>medium</td><td>Creator UX, interface direction, and usability shaping.</td><td><code>designer "improve onboarding flow"</code></td></tr>
         </tbody>
       </table>
 
@@ -90,7 +82,7 @@
     </main>
 
     <footer>
-      <div class="container"><span class="muted">Installable agents follow the catalog manifest (active/internal roles only); merged roles stay documented for migration context.</span></div>
+      <div class="container"><span class="muted">Installable agents follow the catalog manifest. Public docs list only the canonical active/internal roles, not merged compatibility labels.</span></div>
     </footer>
   </body>
 </html>

package/docs/archive/README.md

@@ -0,0 +1,15 @@
+# Archive Docs
+
+This directory holds historical or migration-only collateral that is **not** part of the active
+RCS product surface.
+
+Archive docs may include:
+- migration changelogs
+- old release-body collateral
+- transitional QA snapshots
+- historical restructuring notes
+
+Rules:
+- do not use archive docs as active onboarding or canonical runtime guidance
+- if a file in `docs/archive/` is still needed by active runtime/code/tests, it should move back out
+- active source-of-truth docs stay under the main `docs/`, `docs/reference/`, `docs/contracts/`, and `docs/qa/` surfaces

package/docs/{prompt-migration-changelog.md → archive/prompt-migration-changelog.md}

@@ -25,7 +25,6 @@
 | Prompt File | Added | Removed | Structural Highlights | Behavior Delta |
 |---|---:|---:|---|---|
 | `prompts/analyst.md` | 102 | 105 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/api-reviewer.md` | 90 | 93 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/architect.md` | 102 | 104 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/build-fixer.md` | 81 | 84 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/code-reviewer.md` | 98 | 100 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
@@ -37,20 +36,11 @@
 | `prompts/executor.md` | 92 | 94 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/explore.md` | 104 | 107 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/git-master.md` | 84 | 87 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/information-architect.md` | 28 | 29 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/performance-reviewer.md` | 86 | 89 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/planner.md` | 108 | 111 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/product-analyst.md` | 28 | 29 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/product-manager.md` | 33 | 34 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/qa-tester.md` | 90 | 93 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/quality-reviewer.md` | 98 | 100 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/quality-strategist.md` | 33 | 34 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/researcher.md` | 88 | 91 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/scientist.md` | 84 | 87 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/security-reviewer.md` | 119 | 121 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/style-reviewer.md` | 79 | 82 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/test-engineer.md` | 96 | 98 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
-| `prompts/ux-researcher.md` | 28 | 29 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/verifier.md` | 87 | 90 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/vision.md` | 67 | 70 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
 | `prompts/writer.md` | 78 | 81 | XML-like wrapper blocks converted to Markdown section hierarchy; output/checklist sections normalized. | No intentional functional delta in migration commit. |
@@ -125,7 +115,6 @@ Skill docs are operational runbooks. The migration focused on:
 | `skills/configure-notifications/SKILL.md` | 0 | 0 | Canonical notification setup skill replacing standalone configure-* variants. | Catalog/install surface now converges on one entry point. |
 | `skills/doctor/SKILL.md` | 47 | 45 | Codex path/terminology normalization; examples updated to Codex-first conventions. | No direct runtime behavior change; instruction correctness improved. |
 | `skills/ecomode/SKILL.md` | 1 | 1 | Codex path/terminology normalization; examples updated to Codex-first conventions. | No direct runtime behavior change; instruction correctness improved. |
-| `skills/frontend-ui-ux/SKILL.md` | 2 | 2 | Codex path/terminology normalization; examples updated to Codex-first conventions. | No direct runtime behavior change; instruction correctness improved. |
 | `skills/help/SKILL.md` | 1 | 1 | Codex path/terminology normalization; examples updated to Codex-first conventions. | No direct runtime behavior change; instruction correctness improved. |
 | `skills/learner/SKILL.md` | 5 | 5 | Codex path/terminology normalization; examples updated to Codex-first conventions. | No direct runtime behavior change; instruction correctness improved. |
 | `skills/rcs-setup/SKILL.md` | 144 | 156 | Codex path/terminology normalization; examples updated to Codex-first conventions. | No direct runtime behavior change; instruction correctness improved. |

package/docs/{release-body-0.9.0.md → archive/release-body-0.9.0.md}

@@ -1,7 +1,7 @@
-# roblox-ai-os-creator-skills v0.9.0
+# RCS v0.9.0
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/Yeachan-Heo/roblox-ai-os-creator-skills/v0.9.0/docs/shared/rcs-character-spark-initiative.jpg" alt="RCS character sparked for the Spark Initiative" width="720">
+  <img src="./shared/rcs-character-spark-initiative.jpg" alt="RCS character sparked for the Spark Initiative" width="720">
 </p>
 
 `0.9.0` is the Spark Initiative release: RCS now has a stronger native fast path for repository discovery, shell-native inspection, and cross-platform native distribution.
@@ -49,7 +49,7 @@ rcs sparkshell --tmux-pane %12 --tail-lines 400
 
 ## Important Spark Initiative notes
 
-- Users can install RCS normally with `npm install -g roblox-ai-os-creator-skills`.
+- Users can install RCS normally with `npm install -g @jstn-sdk/rcs`.
 - The npm tarball intentionally excludes staged cross-platform native binaries.
 - Tagged releases publish verified native archives for `rcs-explore-harness` and `rcs-sparkshell`.
 - Packaged installs hydrate the matching native binary through `native-release-manifest.json`.
@@ -81,24 +81,6 @@ Validated locally on `dev` before tagging:
 - `node bin/rcs.js setup --dry-run`
 - `npm pack --dry-run`
 
-## Notable PRs
-
-- [#782](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/782) — explore routes qualifying read-only shell tasks via sparkshell
-- [#784](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/784) — cross-platform native publishing and release-pipeline follow-through
-- [#785](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/785) — team runtime lifecycle and cleanup hardening
-- [#786](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/786) — nested help routing cleanup
-- [#787](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/787) — centralized RCS default model resolution
-- [#788](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/788) — HUD branch/config loading hardening
-- [#789](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/789) — distribute generated aspect tasks across workers
-- [#793](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/793) — Windows Codex command shim probing fix
-- [#794](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/794) — merge `experimental/dev` into `dev`
-- [#805](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/805) — keep workers running after mailbox replies
-
-## Related issues
-
-- [#781](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/781) — sparkshell summary reasoning hardening
-- [#744](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/issues/744) — lifecycle profile persistence
-- [#745](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/issues/745) — cleanup policy hardening
-- [#746](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/issues/746) — governance split follow-through
-- [#741](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/issues/741) — linked Ralph/team runtime follow-up
-- [#732](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/issues/732) — related team lifecycle follow-up
+## Historical note
+
+This archived release note is retained for product history, but current first-party release ownership lives on the current RCS repository and package coordinates.

package/docs/{release-body-0.9.1.md → archive/release-body-0.9.1.md}

@@ -1,7 +1,7 @@
-# roblox-ai-os-creator-skills v0.9.1
+# RCS v0.9.1
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/Yeachan-Heo/roblox-ai-os-creator-skills/v0.9.1/docs/shared/rcs-character-spark-initiative.jpg" alt="RCS character sparked for the Spark Initiative" width="720">
+  <img src="./shared/rcs-character-spark-initiative.jpg" alt="RCS character sparked for the Spark Initiative" width="720">
 </p>
 
 `0.9.1` is a targeted Spark Initiative hotfix release.
@@ -9,7 +9,7 @@
 ## Why this release exists
 
 - `v0.9.0` remains historically red.
-- The required packed-install smoke hydration fix landed later on `dev` in PR [#806](https://github.com/Yeachan-Heo/roblox-ai-os-creator-skills/pull/806).
+- The required packed-install smoke hydration fix landed in the post-0.9.0 line and is reflected here as the superseding hotfix cut.
 - `v0.9.1` is the clean superseding release cut from `main` with that fix applied.
 
 ## Included fix

package/docs/codex-native-hooks.md

@@ -30,15 +30,15 @@ RCS only owns the wrapper entries that invoke `dist/scripts/codex-native-hook.js
 | --- | --- | --- | --- | --- |
 | `session-start` | `SessionStart` | `session-start` | native | Native adapter refreshes leader session bookkeeping, preserves the canonical leader scope when a native subagent `SessionStart` is detected from rollout `session_meta`, restores startup developer context, and ensures `.rcs/` is gitignored at the repo root |
 | wiki startup context | `SessionStart` | `session-start` | native | Wiki session-start context can append a compact `.rcs/wiki/` summary when wiki pages exist; startup writes stay config-gated |
-| `keyword-detector` | `UserPromptSubmit` | `keyword-detector` | native | Persists skill activation state and can add prompt-side developer context; `$ralph` prompt routing seeds workflow state only and does not launch `rcs ralph --prd ...` |
+| `keyword-detector` | `UserPromptSubmit` | `keyword-detector` | native | Persists skill activation state and can add prompt-side developer context; `$forge` prompt routing seeds workflow state only and does not launch `rcs forge --prd ...` |
 | `pre-tool-use` | `PreToolUse` (`Bash`) | `pre-tool-use` | native-partial | Current native scope is Bash-only; built-in native behavior cautions on `rm -rf dist`, blocks inspectable inline `git commit` commands until Lore-format structure + the required `Co-authored-by: RCS <rcs@roblox-ai-os.dev>` trailer are present, and emits non-blocking document-refresh warnings for mapped staged commit changes that lack rule-scoped docs/spec refresh evidence |
 | `post-tool-use` | `PostToolUse` (`Bash`) | `post-tool-use` | native-partial | Current native scope is Bash-only; built-in native behavior covers command-not-found / permission-denied / missing-path guidance only from stderr or non-zero Bash results, ignores failure-looking strings from successful source/log reads, and keeps MCP transport-death guidance scoped to MCP-like tool calls; document-refresh commit warnings use PreToolUse advisory output, with PostToolUse reserved as a future fallback if Codex advisory semantics change |
-| Ralph/persistence stop handling | `Stop` | `stop` | native-partial | Native adapter uses the documented native Stop continuation contract (`decision: "block"` + `reason`) for active Ralph runs, emits a single JSON object on Stop stdout even for no-op Stop decisions, and emits deterministic JSON continuation output if Stop dispatch fails before normal handling |
+| Forge/persistence stop handling | `Stop` | `stop` | native-partial | Native adapter uses the documented native Stop continuation contract (`decision: "block"` + `reason`) for active Forge runs, emits a single JSON object on Stop stdout even for no-op Stop decisions, and emits deterministic JSON continuation output if Stop dispatch fails before normal handling |
 | Autopilot continuation | `Stop` | `stop` | native-partial | Native adapter continues non-terminal autopilot sessions from active session/root mode state |
 | Ultrawork continuation | `Stop` | `stop` | native-partial | Native adapter continues non-terminal ultrawork sessions from active session/root mode state |
 | UltraQA continuation | `Stop` | `stop` | native-partial | Native adapter continues non-terminal ultraqa sessions from active session/root mode state |
 | Team-phase continuation | `Stop` | `stop` | native-partial | Native adapter treats per-team `phase.json` as canonical when deciding whether a current-session team run is still non-terminal and can re-block on later fresh Stop replies while keeping leader guidance explicit about rewriting system-generated worker auto-checkpoint commits into Lore-format final history |
-| `ralplan` skill-state continuation | `Stop` | `stop` | native-partial | Native adapter can block on active `skill-active-state.json` for `ralplan`, unless active subagents are already the real in-flight owners |
+| `blueprint` skill-state continuation | `Stop` | `stop` | native-partial | Native adapter can block on active `skill-active-state.json` for `blueprint`, unless active subagents are already the real in-flight owners |
 | `deep-interview` skill-state continuation | `Stop` | `stop` | native-partial | Native adapter can block on active `skill-active-state.json` for `deep-interview`, unless active subagents are already the real in-flight owners |
 | auto-nudge continuation | `Stop` | `stop` | native-partial | Native adapter continues turns that end in a permission/stall prompt, can re-fire for later fresh replies, and suppresses auto-nudge while interview / deep-interview state is active; explicit terminal lifecycle metadata should be authoritative when present, legacy `blocked_on_user` remains a suppress-continuation compatibility signal, and `cancelled` stays internal legacy-only for user-facing lifecycle summaries |
 | `ask-user-question` | none | runtime-only | runtime-fallback | No distinct Codex native hook today |
@@ -125,7 +125,7 @@ Stop/continuation readers must interpret approved combined workflow state from
 the shared active-set contract rather than from a single legacy `skill` owner.
 For the first-pass multi-state rollout, the approved overlaps are:
 
-- `team + ralph`
+- `team + forge`
 - `team + ultrawork`
 
 Unsupported overlaps should preserve the current state unchanged and direct the

package/docs/contracts/forge-cancel-contract.md

@@ -0,0 +1,20 @@
+# Forge Cancellation Contract
+
+This contract defines required post-conditions for cancelling Forge.
+
+## Required post-conditions
+
+After cancelling Forge, implementations MUST ensure:
+
+1. Targeted Forge state is terminal and non-active:
+   - `active=false`
+   - `current_phase='cancelled'`
+   - `completed_at` is set
+2. If Forge is linked to Ultrawork or Ecomode in the same scope, that linked mode MUST also be terminal/non-active.
+3. Cancellation MUST NOT mutate unrelated sessions.
+
+## Alignment points
+
+- `src/cli/index.ts`
+- `src/modes/base.ts`
+- `skills/cancel/SKILL.md`

package/docs/contracts/forge-state-contract.md

@@ -0,0 +1,52 @@
+# Forge State Contract
+
+## Canonical Forge state schema
+
+Forge runtime state is stored at:
+- `.rcs/state/forge-state.json`
+- `.rcs/state/sessions/<session_id>/forge-state.json`
+
+Required active fields:
+- `active: boolean`
+- `iteration: number`
+- `max_iterations: number`
+- `current_phase: string`
+- `started_at: ISO8601 string`
+
+Optional terminal and audit fields:
+- `completed_at`
+- `error`
+- `owner_rcs_session_id`
+- `owner_codex_session_id`
+- `owner_codex_thread_id`
+- `tmux_pane_id`
+- `tmux_pane_set_at`
+- `stop_reason`
+
+## Canonical phase vocabulary
+
+`current_phase` must be one of:
+- `starting`
+- `executing`
+- `verifying`
+- `fixing`
+- `blocked_on_user`
+- `complete`
+- `failed`
+- `cancelled`
+
+Unknown phase values must be rejected.
+
+## Scope rules
+
+1. Session-scoped state is authoritative when a session id exists.
+2. Root scope is compatibility fallback only.
+3. Writes target one authoritative scope only.
+4. Cross-session migration must preserve single-owner semantics and must not overwrite an already-authoritative current session file.
+
+## Canonical PRD and progress
+
+- Canonical PRD: `.rcs/plans/prd-{slug}.md`
+- Startup validation compatibility source: `.rcs/prd.json`
+- Canonical progress ledger: `.rcs/state/{scope}/forge-progress.json`
+- Legacy compatibility reader: prior pre-Forge progress ledgers are imported forward when encountered.

package/docs/contracts/multi-state-transition-contract.md

@@ -20,7 +20,7 @@ are live.
 Allowed active-set shapes in this rollout are intentionally narrow:
 
 - standalone single-workflow state for tracked workflows
-- `team + ralph`
+- `team + forge`
 - `team + ultrawork`
 
 The resulting active set is peer state. Neither member is semantically primary
@@ -70,12 +70,12 @@ Example operator guidance shape:
 CLI parity surface:
 
 - `rcs state clear --input '{"mode":"team"}' --json`
-- `rcs state clear --input '{"mode":"ralph","all_sessions":true}' --json`
+- `rcs state clear --input '{"mode":"forge","all_sessions":true}' --json`
 
 MCP parity surface:
 
 - `rcs_state.state_clear({ mode: "team" })`
-- `rcs_state.state_clear({ mode: "ralph", all_sessions: true })`
+- `rcs_state.state_clear({ mode: "forge", all_sessions: true })`
 
 ## Brownfield consumer expectations
 
@@ -107,9 +107,9 @@ must not accidentally delete the entire combined state.
 Implementation should be considered complete only when tests prove:
 
 1. canonical active state can hold a multi-entry active set
-2. `team + ralph` is allowed in both activation orders
+2. `team + forge` is allowed in both activation orders
 3. `team + ultrawork` is allowed in both activation orders
 4. unsupported overlaps deny without mutation
 5. denial messages mention both `rcs state` and `rcs_state.*`
 6. HUD / overlay / stop-hook consumers honor the combined set consistently
-7. `autopilot` and `autoresearch` still reject unsupported overlap attempts; `autopilot -> ralplan` is the only review-driven planning loopback exception
+7. `autopilot` and `autoresearch` still reject unsupported overlap attempts; `autopilot -> blueprint` is the only review-driven planning loopback exception

package/docs/contracts/multi-state-transition-review.md

@@ -34,7 +34,7 @@ Observed strengths:
   skill-active state and are structurally closer to a peer-state model than a
   strict single-owner model.
 - `src/modes/base.ts` already preserves key standalone restrictions:
-  `autopilot` and `autoresearch` remain exclusive; `ralph` and `ultrawork`
+  `autopilot` and `autoresearch` remain exclusive; `forge` and `ultrawork`
   remain mutually exclusive with each other.
 
 Primary gaps relative to the PRD/test-spec:
@@ -112,9 +112,9 @@ This freezes the rollout expectations for:
 - regression expectations
 
 Also clarified two adjacent operator-facing docs so the approved overlap is not
-misread as the old linked `team ralph` lifecycle:
+misread as the removed linked team-follow-up lifecycle:
 
-- `docs/contracts/ralph-state-contract.md`
+- `docs/contracts/forge-state-contract.md`
 - `docs/codex-native-hooks.md`
 
 Added concrete recovery examples to the compatibility contract so denial

package/docs/contracts/repo-aware-team-dag-decomposition.md

@@ -93,6 +93,6 @@ This makes ownership constraints visible where workers actually operate instead
 
 - Do not put a large opaque DAG heuristic block directly into `src/cli/team.ts`; keep a small preflight module seam.
 - Do not widen `TeamTask` with rich metadata unless state readers, API interop, and monitor snapshots are updated together.
-- Do not treat RALPLAN-suggested worker counts as CLI-explicit overrides.
+- Do not treat BLUEPRINT-suggested worker counts as CLI-explicit overrides.
 - Do not bypass claim-safety by directly writing in-progress/completed task state during preflight.
 - Do not launch workers before symbolic dependencies are remapped to concrete Team task IDs.

package/docs/contracts/rust-runtime-thin-adapter-contract.md

@@ -28,7 +28,7 @@ Rust-authored compatibility views.
 |---|---|---|
 | `rcs team status` | `.rcs/state/team/<team>/config.json`, `manifest.v2.json`, `tasks/*.json`, `approvals/*.json`, `workers/*` | Manifest-backed team config is authoritative when both config and manifest exist. |
 | `rcs doctor --team` | `.rcs/state/team/<team>/config.json`, `manifest.v2.json`, `workers/*/status.json`, `workers/*/heartbeat.json`, `.rcs/state/hud-state.json` | Manifest-backed tmux/session identity is authoritative when both config and manifest exist. |
-| HUD readers | `.rcs/state/session.json`, `.rcs/state/sessions/<session>/team-state.json`, `.rcs/state/team-state.json`, `.rcs/state/ralph-state.json` | Session-scoped files are authoritative when a session is active; root files are compatibility fallback only. |
+| HUD readers | `.rcs/state/session.json`, `.rcs/state/sessions/<session>/team-state.json`, `.rcs/state/team-state.json`, `.rcs/state/forge-state.json` | Session-scoped files are authoritative when a session is active; root files are compatibility fallback only. |
 
 ## Rust-authored runtime files
 

package/docs/contracts/team-startup-dispatch-latency.md

@@ -7,7 +7,7 @@ Review lane: worker-3
 ## Scope
 
 This note documents the review contract for the team startup assignment-delay
-fix described by `.rcs/plans/ralplan-team-worker-assignment-delay-20260430T110158Z.md`.
+fix described by `.rcs/plans/blueprint-team-worker-assignment-delay-20260430T110158Z.md`.
 It focuses on the startup window after tmux worker panes are created and before
 workers receive their first inbox trigger.
 

package/docs/getting-started.html

@@ -27,12 +27,18 @@
         <li>Node.js 20+ and npm.</li>
         <li>OpenAI Codex CLI installed and authenticated.</li>
         <li>Git (recommended) for project workflows.</li>
+        <li>Optional for live Studio truth: the upstream <code>robloxstudio-mcp</code> Studio plugin and MCP server standard.</li>
       </ul>
 
       <h2>Installation</h2>
       <pre><code>npm install -g @openai/codex @jstn-sdk/rcs
 rcs doctor</code></pre>
       <p>When <code>@jstn-sdk/rcs</code> actually bumps to a newer version, the global npm install prints an explicit reminder instead of launching <code>rcs setup</code> automatically. When you're ready, rerun <code>rcs setup</code> manually or use <code>rcs update</code> to check npm and then run the same setup refresh path. Fresh RCS-managed <code>gpt-5.5</code> configs now recommend <code>model_context_window = 250000</code> and <code>model_auto_compact_token_limit = 200000</code> only when those keys are missing.</p>
+      <p>Explicit latest-version triggers also exist:</p>
+      <pre><code>npm install -g @jstn-sdk/rcs@latest
+rcs update
+rcs latest
+rcs @latest</code></pre>
       <p><code>rcs doctor</code> verifies the install shape. Before treating the runtime as ready, also prove that the active Codex profile can perform a real request:</p>
       <pre><code>codex login status
 rcs exec --skip-git-repo-check -C . &quot;Reply with exactly RCS-EXEC-OK&quot;</code></pre>
@@ -56,7 +62,11 @@ rcs                    # standard launch</code></pre>
       <h2>Creator Workflow First</h2>
       <p>The canonical public path is:</p>
       <pre><code>$brief -> $blueprint -> $forge / $crew -> $autoforge</code></pre>
-      <p>Older engine-facing surfaces such as <code>$deep-interview</code>, <code>$ralplan</code>, <code>$ralph</code>, <code>$team</code>, and <code>$autopilot</code> remain available as lower-level compatibility/runtime layers, but they are not the primary onboarding path.</p>
+      <p>The creator-first path stays <code>$brief -> $blueprint -> $forge / $crew -> $autoforge</code>. Supporting execution surfaces still exist for operational control, but onboarding should stay creator-first and Roblox-first.</p>
+
+      <h2>Optional Live Studio Connection</h2>
+      <p>If you want real-time Roblox Studio inspection or script/object changes against an open Studio session, use the upstream <code>robloxstudio-mcp</code> compatibility lane instead of treating RCS itself as the live Studio transport.</p>
+      <p>See <a href="./reference/robloxstudio-mcp-compatibility.md">robloxstudio-mcp Compatibility</a> for the standard Codex commands, read-only inspector mode, and Windows fallback config.</p>
 
       <h2>Prompt Instruction Source</h2>
       <p>RCS layers project instructions by default (extends Codex behavior, does not replace/bypass Codex core system policies):</p>

package/docs/guidance-schema.md

@@ -28,6 +28,8 @@ This standard is additive and migration-safe: it does not change task-state APIs
    - Evidence required before completion claims.
 6. **Recovery & Lifecycle**
    - Cancel/cleanup/resume behavior and state transitions.
+7. **Semantic Vocabulary**
+   - Active surfaces should default to the canonical Roblox-native vocabulary from `docs/reference/canonical-vocabulary.md`.
 
 ### Optional sections
 
@@ -54,7 +56,7 @@ This standard is additive and migration-safe: it does not change task-state APIs
 | Surface | Role & Intent | Operating Principles | Execution Protocol | Constraints & Safety | Verification & Completion | Recovery & Lifecycle |
 |---|---|---|---|---|---|---|
 | `AGENTS.md` (workspace root, optional tracked copy) | Title + opening intro | `<operating_principles>` | mode selection + delegation/model-routing/skills/team sections + leader/worker split | compact hook-backed keyword/cancellation/state contract + stop/escalate rules | `<verification>` + continuation checklist + concise output contract | cancel + recovery/state guidance + runtime/team markers |
-| `templates/AGENTS.md` | Title + opening intro | `<operating_principles>` | same canonical orchestration sections as the tracked root copy when one exists | same safety constraints | same verification section | runtime/team overlays added later via markers |
+| `templates/AGENTS.md` | Title + opening intro | `<operating_principles>` | same canonical workflow sections as the tracked root copy when one exists | same safety constraints | same verification section | runtime/team overlays added later via markers |
 | `prompts/*.md` canonical role prompt surfaces | role-local identity + remit | role-local operating posture | task execution steps for that specialist | role boundaries / tool rules / handoff limits (report upward, do not recursively orchestrate) | evidence required before role-local completion claims | scenario handling + final checklist |
 | Runtime AGENTS overlay block | session context identity | compaction protocol directives | checkpoint flow | overlay marker boundaries and size/lock gates | checkpoint evidence before compaction | runtime apply/strip lifecycle |
 | Team worker overlay block | worker identity + team scope | worker protocol intent | ACK → read task → claim → execute → complete → idle | file ownership + blocked-state rules | write task result + status updates | mailbox polling + shutdown handling |
@@ -64,6 +66,7 @@ This standard is additive and migration-safe: it does not change task-state APIs
 
 - Prefer additive wording updates over structural removals during rollout.
 - Preserve all marker-bounded overlay text contracts while aligning language to this schema.
-- Role prompts should recommend handoffs upward to the orchestrator instead of spawning or requesting other agents directly.
-- Root orchestration surfaces should choose one mode clearly (`$deep-interview`, `$ralplan`, `$team`, or solo execute) before mixing lanes.
+- Role prompts should recommend handoffs upward to the active workflow owner instead of spawning or requesting other agents directly.
+- Root workflow surfaces should choose one mode clearly (`$deep-interview`, `$blueprint`, `$team`, or solo execute) before mixing lanes.
 - When guidance conflicts are found, fix wording while preserving existing behavioral semantics unless explicitly versioned.
+- Treat `docs/reference/canonical-vocabulary.md` and `docs/reference/semantic-design-system.md` as the semantic source of truth for active prompts, skills, missions, and orchestration surfaces.