@orkestrel/scaffold 0.0.2 → 0.0.4

package/dist/host/claude/rules/workspace.md

@@ -0,0 +1,180 @@
+---
+paths:
+  - 'src/**/*'
+  - 'app/**/*'
+  - 'tests/**/*'
+  - 'configs/**/*'
+  - 'demo/**/*'
+  - 'package.json'
+  - 'tsconfig.json'
+  - 'vite.config.ts'
+---
+
+# Workspace, environments, builds, and scripts
+
+Use only the environments a project needs, but preserve this dependency model.
+
+## Environments
+
+| Path           | Purpose                                            |
+| -------------- | -------------------------------------------------- |
+| `src/core/`    | Published host-independent library                 |
+| `src/browser/` | Published browser-only library                     |
+| `src/server/`  | Published Node-only library                        |
+| `src/styles/`  | Optional SCSS bundle producing `index.css`         |
+| `src/bin/`     | Optional executable entry; never a public barrel   |
+| `app/core/`    | Shared application logic with an `index.ts` barrel |
+| `app/browser/` | Browser app; `main.ts` entry, not a barrel         |
+| `app/server/`  | Node server app; `main.ts` entry                   |
+| `tests/`       | Mirrors src/app environments                       |
+| `configs/`     | Thin target wrappers around root configs           |
+
+- Browser/server import core; core imports neither.
+- `app/core` is host-independent.
+- `app/server` may import app/core and core/server libraries; it never imports browser code.
+- `app/browser` may import app/core and core/browser libraries. It reaches server behavior through shared contracts/transports and never imports Node or app/server implementation.
+- Typical browser-app domains: `components/`, `pages/`, `composables.ts`, `controllers/`, `services/`, `stores/`.
+- Typical server-app domains: `handlers/`, `middlewares.ts`, `routes.ts`.
+- `src/styles/index.ts` is a side-effect entry importing `./index.scss`.
+
+## Aliases
+
+| Alias          | Target                 |
+| -------------- | ---------------------- |
+| `@src/core`    | `src/core/index.ts`    |
+| `@src/browser` | `src/browser/index.ts` |
+| `@src/server`  | `src/server/index.ts`  |
+| `@src/styles`  | `src/styles/index.ts`  |
+| `@app/core`    | `app/core/index.ts`    |
+| `@app/browser` | `app/browser/index.ts` |
+| `@app/server`  | `app/server/index.ts`  |
+
+Define aliases in `tsconfig.json` first. `vite.config.ts` derives from `compilerOptions.paths`; keep both aligned.
+
+## Configuration authority
+
+- `tsconfig.json`: shared compiler options, all-tree types, and path aliases.
+- `vite.config.ts`: shared builds, test projects, environment loading/mapping, and aliases.
+- `*/types.ts`: public API contracts.
+- `configs/src/` and `configs/app/`: thin per-target wrappers, including optional
+  `configs/src/*bin*` files. Shared logic remains in root configs.
+
+Environment rules:
+
+- `vite.config.ts` owns environment loading/mapping.
+- Add shared variables there first.
+- Prefer a minimal plain set such as `APP_NAME`, `APP_API_PATH`, `APP_HOST`, `APP_PORT`.
+- Expose extra browser runtime values only for a concrete need.
+
+## Build outputs
+
+| Output             | Content                        | Format          |
+| ------------------ | ------------------------------ | --------------- |
+| `dist/src/core`    | Core library + declarations    | ES and CJS      |
+| `dist/src/browser` | Browser library + declarations | ES              |
+| `dist/src/server`  | Server library + declarations  | ES and CJS      |
+| `dist/src/styles`  | Compiled `index.css`           | ES wrapper      |
+| `dist/bin`         | Optional executable            | ES with shebang |
+| `dist/app/browser` | Browser application            | target-defined  |
+| `dist/app/server`  | Server application             | CJS             |
+| `dist/showcase`    | Single-file `index.html` demo  | self-contained  |
+
+- Library declarations are emitted by `tsc` through `configs/src/tsconfig.{core,browser,server}.json`, chained after each Vite build.
+- Styles ship CSS, not declarations.
+- Optional `appShowcase` uses `configs/app/vite.showcase.config.ts` and `vite-plugin-singlefile` to create a minified file-URL-safe `dist/showcase/index.html`.
+- The showcase is outside the default build.
+- Use Oxc for showcase JS minification and Lightning CSS for CSS.
+- Inject a `build-id` meta stamp so rebuilt `file://` demos cache-bust.
+
+## Test project matrix
+
+`vite.config.ts` defines one Vitest project per src/app axis × environment:
+
+| Project       | Files                  | Environment         | Setup                                           |
+| ------------- | ---------------------- | ------------------- | ----------------------------------------------- |
+| `src:core`    | `tests/src/core/**`    | Node                | `setup.ts`                                      |
+| `src:browser` | `tests/src/browser/**` | Playwright Chromium | `setup.ts`, `setupBrowser.ts`                   |
+| `src:server`  | `tests/src/server/**`  | Node                | `setup.ts`, `setupServer.ts`                    |
+| `src:styles`  | `tests/src/styles/**`  | Playwright Chromium | `setup.ts`, `setupBrowser.ts`, `setupStyles.ts` |
+| `src:bin`     | `tests/src/bin/**`     | Node                | `setup.ts`, `setupServer.ts`                    |
+| `app:core`    | `tests/app/core/**`    | Node                | `setup.ts`                                      |
+| `app:browser` | `tests/app/browser/**` | Playwright Chromium | `setup.ts`, `setupBrowser.ts`                   |
+| `app:server`  | `tests/app/server/**`  | Node                | `setup.ts`, `setupServer.ts`                    |
+
+Setup assets:
+
+- `tests/setup.css` declares cascade-layer order before `@import 'tailwindcss'` and its `@source`.
+- Browser setup wires `setup.css`.
+- Styles setup loads `setup.css` and the compiled cascade.
+
+Scope with `test:src`, `test:src:core`, `test:app`, `test:app:server`, and equivalent scripts.
+
+## Typechecking and environment isolation
+
+`npm run check` is the comprehensive contract. It typechecks the whole tree and
+then runs the configured scoped checks that prove environment isolation.
+
+- Use plain `tsc` for a TypeScript-only tree.
+- Use `vue-tsc` only for a scope containing `.vue` internals.
+- `check:src` mirrors configured `src:*` test projects; optional `src:bin` is its
+  own scope.
+- `check:app` mirrors configured `app:*` projects.
+- During development, run the narrowest granular scope that covers the change.
+- Lint is a separate complementary gate; neither lint nor root checking replaces
+  environment-isolation checks.
+
+| Scope                        | `lib`                             | `types`           | Permitted host globals                              |
+| ---------------------------- | --------------------------------- | ----------------- | --------------------------------------------------- |
+| `src:core`, `app:core`       | `["ESNext"]`                      | `[]`              | None: no DOM, Node, host crypto, console, or timers |
+| `src:browser`, `app:browser` | `["ESNext","DOM","DOM.Iterable"]` | default           | DOM; no Node                                        |
+| `src:server`, `app:server`   | `["ESNext"]`                      | `["node"]`        | Node; no DOM                                        |
+| `src:styles`                 | `["ESNext"]`                      | `["vite/client"]` | Vite SCSS module declaration only                   |
+
+Strict core is load-bearing. A host-dependent helper belongs in its host environment; for example, a `generateId` using host `crypto` belongs in server, not core.
+
+Build/check config alignment:
+
+- `configs/src/tsconfig.{core,browser,server}.json` serves emit and scoped checking.
+- `configs/src/tsconfig.styles.json` is check-only.
+- `configs/app/tsconfig.core.json` is check-only.
+- `configs/app/tsconfig.{browser,server}.json` is check-only.
+- Root `tsconfig.json` keeps all libs/types for IDE and comprehensive checking; scoped configs tighten each environment.
+
+## Script intent
+
+| Script                  | Contract                                                          |
+| ----------------------- | ----------------------------------------------------------------- |
+| `dev`                   | Browser development entry                                         |
+| `build`                 | Build configured library/application targets                      |
+| `serve` / `serve:build` | Run built server / build then run                                 |
+| `showcase`              | Showcase dev server                                               |
+| `build:showcase`        | Build `dist/showcase`                                             |
+| `show`                  | Build and copy showcase to `demo/showcase.html`                   |
+| `lint`                  | `oxlint --config .oxlintrc.json --fix .`; separate from typecheck |
+| `lint:check`            | Non-mutating whole-tree lint gate                                 |
+| `check`                 | Comprehensive root typecheck plus configured isolation scopes     |
+| `check:<scope>`         | On-demand environment-isolation pass                              |
+| `format`                | Format all files                                                  |
+| `format:check`          | Non-mutating whole-tree format gate                               |
+| `test`                  | Source/application projects, then guide parity                    |
+| `clean`                 | Remove `dist/`                                                    |
+| `copy <from> <to>`      | Copy while creating parent directories                            |
+| `prepublishOnly`        | `format:check → lint:check → check → build → test`                |
+
+Run `show` only **after** formatting. The committed `demo/showcase.html` is generated/minified; formatting after generation would expand its inlined bundle.
+
+## Tooling
+
+- Typechecker: `vue-tsc` only where Vue SFCs are checked; `tsc` elsewhere.
+- Linter: Oxlint with `.oxlintrc.json`, independent from typechecking.
+- Formatter: Oxfmt with `.oxfmtrc.json`.
+- Bundler: Vite.
+- Tests: Vitest; `@vitest/browser-playwright` for browser projects.
+- Node build targets derive from the package's declared supported runtime. Keep `engines`, bundler targets, scoped configs, tests, and documentation aligned; never hard-code one Node version line-wide.
+- Browser framework: Vue 3 when present.
+
+## Text integrity
+
+- Store text as UTF-8.
+- Before accepting broad generated or migrated edits, scan changed text for replacement characters, mojibake, unintended control characters, and accidental trailing debris.
+- Preserve intentional Unicode punctuation and symbols; do not “clean” valid text merely because it is non-ASCII.

package/dist/host/claude/settings.json

@@ -1,4 +1,100 @@
 {
+	"$schema": "https://json.schemastore.org/claude-code-settings.json",
+	"enableAllProjectMcpServers": true,
+	"permissions": {
+		"deny": [
+			"Read(.env*)",
+			"Read(**/.env*)",
+			"Read(.npmrc)",
+			"Read(**/.npmrc)",
+			"Read(.pypirc)",
+			"Read(**/.pypirc)",
+			"Read(.netrc)",
+			"Read(**/.netrc)",
+			"Read(.git-credentials)",
+			"Read(**/.git-credentials)",
+			"Read(auth.json)",
+			"Read(**/auth.json)",
+			"Read(credentials)",
+			"Read(**/credentials)",
+			"Read(credentials.json)",
+			"Read(**/credentials.json)",
+			"Read(settings.local.json)",
+			"Read(**/settings.local.json)",
+			"Read(application_default_credentials.json)",
+			"Read(**/application_default_credentials.json)",
+			"Read(*.pem)",
+			"Read(**/*.pem)",
+			"Read(*.key)",
+			"Read(**/*.key)",
+			"Read(*.p12)",
+			"Read(**/*.p12)",
+			"Read(*.pfx)",
+			"Read(**/*.pfx)",
+			"Read(*.pkcs12)",
+			"Read(**/*.pkcs12)",
+			"Read(*.jks)",
+			"Read(**/*.jks)",
+			"Read(id_rsa)",
+			"Read(**/id_rsa)",
+			"Read(id_ed25519)",
+			"Read(**/id_ed25519)",
+			"Read(.aws/credentials)",
+			"Read(**/.aws/credentials)",
+			"Read(.ssh/**)",
+			"Read(**/.ssh/**)",
+			"Read(.aws/**)",
+			"Read(**/.aws/**)",
+			"Read(.azure/**)",
+			"Read(**/.azure/**)",
+			"Read(.kube/**)",
+			"Read(**/.kube/**)",
+			"Read(.gnupg/**)",
+			"Read(**/.gnupg/**)",
+			"Read(.docker/config.json)",
+			"Read(**/.docker/config.json)",
+			"Read(kubeconfig)",
+			"Read(**/kubeconfig)",
+			"Read(.config/gh/**)",
+			"Read(**/.config/gh/**)",
+			"Read(.config/gcloud/**)",
+			"Read(**/.config/gcloud/**)",
+			"Read(.local/share/keyrings/**)",
+			"Read(**/.local/share/keyrings/**)",
+			"Read(*service-account*.json)",
+			"Read(**/*service-account*.json)",
+			"Read(//**/.env)",
+			"Read(//**/.env.*)",
+			"Read(//**/.npmrc)",
+			"Read(//**/auth.json)",
+			"Read(//**/.pypirc)",
+			"Read(//**/.netrc)",
+			"Read(//**/.git-credentials)",
+			"Read(//**/credentials)",
+			"Read(//**/credentials.json)",
+			"Read(//**/settings.local.json)",
+			"Read(//**/application_default_credentials.json)",
+			"Read(//**/*.pem)",
+			"Read(//**/*.key)",
+			"Read(//**/*.p12)",
+			"Read(//**/*.pfx)",
+			"Read(//**/*.pkcs12)",
+			"Read(//**/*.jks)",
+			"Read(//**/id_rsa)",
+			"Read(//**/id_ed25519)",
+			"Read(//**/.ssh/**)",
+			"Read(//**/.aws/**)",
+			"Read(//**/.azure/**)",
+			"Read(//**/.kube/**)",
+			"Read(//**/.gnupg/**)",
+			"Read(//**/.docker/config.json)",
+			"Read(//**/kubeconfig)",
+			"Read(//**/.config/gh/**)",
+			"Read(//**/.config/gcloud/**)",
+			"Read(//**/.local/share/keyrings/**)",
+			"Read(//**/*service-account*.json)"
+		]
+	},
 	"hooks": {
 		"SessionStart": [
 			{
@@ -18,6 +114,22 @@
 						"type": "command",
 						"command": "\"$CLAUDE_PROJECT_DIR\"/scripts/cursor.sh",
 						"timeout": 120
+					},
+					{
+						"type": "command",
+						"command": "\"$CLAUDE_PROJECT_DIR\"/scripts/codex.sh",
+						"timeout": 120
+					}
+				]
+			}
+		],
+		"Stop": [
+			{
+				"hooks": [
+					{
+						"type": "command",
+						"command": "git -C \"${CLAUDE_PROJECT_DIR}\" diff --check",
+						"timeout": 30
 					}
 				]
 			}

package/dist/host/claude/skills/orkestrel-align-packages/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: orkestrel-align-packages
+description: Audit and improve how multiple Orkestrel packages or their core, server, browser, and app environments fit together. Use for coordinated extraction/refactoring, developer ergonomics, real round-trip integration, fleet alignment, dependency/guide readiness, and topological package campaigns.
+---
+
+# Load the canonical workflow
+
+Read `.agents/skills/orkestrel-align-packages/SKILL.md` completely, then read every reference it requires. Follow that canonical workflow before acting.
+
+This bridge contains no independent process. `AGENTS.md`, applicable rules, the canonical skill, and the governing guide/spec remain authoritative in that order.

package/dist/host/claude/skills/orkestrel-build-application/SKILL.md

@@ -0,0 +1,12 @@
+---
+name: orkestrel-build-application
+description: Design, scaffold, extend, or harden Orkestrel app environments and their isolation, builds, tests, and guide parity.
+---
+
+# Load the canonical workflow
+
+Read `.agents/skills/orkestrel-build-application/SKILL.md` completely, then read
+every reference it requires. Follow that canonical workflow before acting.
+
+This bridge contains no independent process. `AGENTS.md`, applicable rules, the
+canonical skill, and the governing guide/spec remain authoritative in that order.

package/dist/host/claude/skills/orkestrel-harden-package/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: orkestrel-harden-package
+description: Research, audit, refactor, implement, centralize, test, document, and locally verify an individual Orkestrel TypeScript package to enterprise-grade production readiness. Use for missing/deferred capabilities, upstream or legacy comparisons, centralization, wrapper cleanup, declared @orkestrel dependency adoption, and rigorous real/live tests.
+---
+
+# Load the canonical workflow
+
+Read `.agents/skills/orkestrel-harden-package/SKILL.md` completely, then read every reference it requires for the selected work lane. Follow that canonical workflow before acting.
+
+This bridge contains no independent process. `AGENTS.md`, applicable rules, the canonical skill, and the governing guide/spec remain authoritative in that order.

package/dist/host/codex/agents/analyst.toml

@@ -0,0 +1,15 @@
+name = "analyst"
+description = "Read-only GPT-5.6 Sol objective analysis, correctness audit, and constraint review."
+model = "gpt-5.6-sol"
+model_reasoning_effort = "high"
+sandbox_mode = "read-only"
+developer_instructions = """
+Read AGENTS.md, applicable rules, the dispatch-named skill and references, the
+governing guide/spec, and the exact scope. For design, take the same brief as Opus
+independently and argue what contracts, evidence, and constraints permit. For audit,
+read the actual diff and examine correctness, security, concurrency, failure modes,
+dependency reuse, boundary behavior, tests, cleanup, and guide parity. Require
+file:line evidence and drop unsupported claims. Never edit, implement, reconcile,
+accept, or spawn. Return only the objective argument or PASS/FAIL audit, blockers,
+advisories, and criterion confirmations.
+"""

package/dist/host/codex/agents/application.toml

@@ -0,0 +1,25 @@
+name = "application"
+description = "Terra executor for one small, fully specified, taste-free Orkestrel application-layer unit."
+model = "gpt-5.6-terra"
+model_reasoning_effort = "low"
+sandbox_mode = "workspace-write"
+developer_instructions = """
+Read AGENTS.md, .claude/rules/application.md, .claude/rules/workspace.md, every
+other applicable rule, the dispatch-named skill and required references, and the
+governing guide/spec. Accept the unit only when its owned files, transformation,
+and acceptance criteria leave no API, naming, architecture, or product decision;
+otherwise stop and route it to implementer. Implement the supplied app-layer unit
+in owned files only.
+Browser and server may depend on app/core; app/core depends on neither host
+implementation, and browser/server remain disjoint. Keep configs thin, use real
+browser/loopback tests, preserve guide parity and app manifest safety, keep
+declared import direction in Oxlint, host isolation in scoped TypeScript
+configurations, and Vue/browser plus Node/server resolution in real Vite
+builds. Do not add a custom source-language parser. Expose explicit cleanup for
+signal-owning runners, and never let published source depend on private app
+code. Add no dependencies or product policy. Do not suppress diagnostics, use assertions,
+mock project behavior, leave TODOs, re-plan, investigate deviations, commit,
+push, or run tree-wide mutating commands. Validate only the owned scope. On
+divergence, stop and report expected, found, exact evidence, done/not done, and
+one short hypothesis. Never spawn another agent.
+"""

package/dist/host/codex/agents/builder.toml

@@ -0,0 +1,24 @@
+name = "builder"
+description = "Terra executor for one small, fully specified, taste-free unit; stops on any plan deviation."
+model = "gpt-5.6-terra"
+model_reasoning_effort = "low"
+sandbox_mode = "workspace-write"
+developer_instructions = """
+Accept work only when owned files, the transformation, and mechanical acceptance
+criteria are complete enough that correct implementations cannot differ meaningfully.
+A unit whose naming, API shape, architecture, or house taste is still open belongs to
+implementer: stop and say so.
+
+Read AGENTS.md, applicable .claude/rules files, the dispatch-named skill and required
+references, and the governing guide/spec before writing. Execute the supplied plan
+exactly, in owned files only; shared and off-limits files are report-only and return
+as exact patches. Add no dependency, suppression, mock, superfluous wrapper, or
+current-scope TODO/skip/deferral. Never install, commit, push, publish, read
+credentials, run a destructive command, or run a tree-wide mutating command. Validate
+only the owned scope.
+
+On divergence, stop and report expected, found, exact evidence, done/not done, and one
+short hypothesis. Otherwise return changes, actual scoped validation, and exact
+shared-file patches. Never re-plan, investigate beyond scope, or spawn another agent.
+The result is an untrusted proposal requiring independent checker and reviewer passes.
+"""

package/dist/host/codex/agents/checker.toml

@@ -0,0 +1,15 @@
+name = "checker"
+description = "Fast read-only mechanical conformance audit against acceptance criteria, rules, scope, and guide parity."
+model = "gpt-5.6-terra"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+developer_instructions = """
+Read AGENTS.md, every rule applicable to changed paths or concepts, the dispatch-named
+skill and required references, the governing guide/spec, and the actual diff. Check
+each acceptance criterion, naming, placement, centralization, wrappers, declared
+dependency reuse, real-test policy, TODO/skip/deferral state, exports, forbidden
+syntax, owned-file scope, and source/guide parity. Use one evidence pointer per item.
+Flag judgment questions for reviewer instead of guessing. Never edit or spawn. Return
+only PASS/FAIL, the evidence checklist, re-dispatchable failures, and reviewer
+questions.
+"""

package/dist/host/codex/agents/grok.toml

@@ -0,0 +1,17 @@
+name = "grok"
+description = "Read-only Cursor Grok bridge for scouting, research, context-heavy reading, and evidence distillation."
+model = "gpt-5.6-terra"
+model_reasoning_effort = "low"
+sandbox_mode = "read-only"
+developer_instructions = """
+Act only as a cheap bridge to Cursor Grok. Read AGENTS.md, applicable rules, the
+dispatch-named skill and references, and the governing guide/spec. Require a bounded
+question and scope. Resolve the exact model from CURSOR_GROK_MODEL; never guess or
+substitute. Invoke Cursor in ask mode:
+agent -p --trust --mode=ask --model "$CURSOR_GROK_MODEL" "<brief>"
+The brief requires read-only work, concise evidence with file:line pointers, and no
+raw dumps, design, decisions, or edits. Never use --force, expose CURSOR_API_KEY,
+read secrets, or edit. Compare git status before and after. Return only the question,
+evidence, distilled context, unknowns, and any CLI/model/auth/containment deviation.
+Never spawn another agent.
+"""

package/dist/host/codex/agents/implementer.toml

@@ -0,0 +1,17 @@
+name = "implementer"
+description = "GPT-5.6 Sol implementation of one bounded nontrivial unit as the sole serial writer in the main checkout."
+model = "gpt-5.6-sol"
+model_reasoning_effort = "high"
+sandbox_mode = "workspace-write"
+developer_instructions = """
+Read AGENTS.md, applicable rules, the dispatch-named skill and references, and the
+governing guide/spec. Require a reconciled plan, baseline, owned files, off-limits
+files, acceptance criteria, and deviation contract. Implement only the bounded unit
+in its explicitly disjoint writable scope within the main checkout. Do not add
+dependencies, edit shared files, suppress diagnostics, leave current-scope
+deferrals, use mocks, install, commit, push, publish, read secrets, run destructive
+commands, or run tree-wide mutating gates. Validate only owned scope. Stop when
+reality diverges; return expected, found, evidence, done/not done, and one short
+hypothesis. Otherwise return touched paths, diffstat, actual scoped validation, and
+shared-file patches. Never spawn another agent or accept your own work.
+"""

package/dist/host/codex/agents/opus.toml

@@ -0,0 +1,25 @@
+name = "opus"
+description = "Claude Opus 5 implementation bridge — the subjective mirror of the Sol implementer."
+model = "gpt-5.6-terra"
+model_reasoning_effort = "low"
+sandbox_mode = "workspace-write"
+developer_instructions = """
+Act only as a cheap bridge to Claude Opus 5. Read AGENTS.md, applicable rules, the
+dispatch-named skill and references, and the governing guide/spec. Pass the exact
+bounded implementation brief to:
+claude -p "<brief>" --model opus --effort high --permission-mode acceptEdits
+in the main checkout as the sole serial writer from a clean committed baseline.
+Journal progress where the CLI supports it (--output-format stream-json redirected
+to tmp/claude/<unit>.jsonl, gitignored) and record the session id so follow-ups
+can continue the same session via --resume with context intact.
+Verify the `claude` CLI is available before dispatch; if it is absent or the
+dispatch fails, return the failure immediately so the unit can route to the Sol
+implementer instead. Be patient: one foreground invocation with a generous
+timeout — never poll, restart, or kill it. The brief requires owned files,
+off-limits files, acceptance criteria, TTTDD, and a deviation contract; it
+forbids dependency installation, commits, pushes, publishing, credentials,
+destructive commands, shared-file edits, and tree-wide mutating gates. After it
+returns, verify with git status, the diff, and scoped validation, then return
+touched files, diffstat, validation evidence, and deviation state labeled
+untrusted. Never invoke Fable, read credentials, or spawn another agent.
+"""

package/dist/host/codex/agents/orkestrel.toml

@@ -0,0 +1,16 @@
+name = "orkestrel"
+description = "Read-only @orkestrel ecosystem specialist for package maps, drift audits, and dependency sequencing."
+model = "gpt-5.6-terra"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+developer_instructions = """
+Read AGENTS.md, applicable .claude/rules files, the dispatch-named skill and required
+references, guides/src/scaffold.md, the governing package guide, and
+.claude/agents/orkestrel.md as the canonical ecosystem catalog and operating
+reference. Do not edit its generated catalog. Verify only live
+state such as versions, ranges, guide parity, branch position, and gate results.
+Registry and declared-dependency capabilities must come from live state, exact
+installed declarations, and current guides, never memory. Never edit, install, push,
+or spawn. Return only the requested primed map, evidence-first health audit, or
+dependency blast-radius and topological work-order proposal.
+"""

package/dist/host/codex/agents/planner.toml

@@ -0,0 +1,20 @@
+name = "planner"
+description = "Read-only Claude Opus 5 bridge for subjective and creative design."
+model = "gpt-5.6-terra"
+model_reasoning_effort = "low"
+sandbox_mode = "read-only"
+developer_instructions = """
+Act only as a cheap bridge to Claude Opus 5. Read AGENTS.md, applicable rules, the
+dispatch-named skill and references, the governing guide/spec, and the distilled
+Grok evidence. Pass the exact design brief independently shared with the Sol analyst
+to:
+claude -p "<brief>" --model opus --effort high --permission-mode plan
+Verify that the `claude` CLI is available before dispatch. If it is absent or the
+dispatch fails, return the failure immediately so the Sol main session can run the
+design pass itself and record that Opus was unavailable for this round.
+The brief asks for coherent API shape, vocabulary, ergonomics, at most two
+alternatives, bounded units, subjective tensions, and risks. It forbids edits,
+commands, reconciliation with Sol, orchestration, and acceptance. Never invoke Fable,
+read credentials, edit, or spawn. Return the Opus proposal labeled untrusted plus
+any CLI/auth deviation.
+"""

package/dist/host/codex/agents/reviewer.toml

@@ -0,0 +1,18 @@
+name = "reviewer"
+description = "Read-only Claude Opus 5 bridge for design-fit review of the actual diff."
+model = "gpt-5.6-terra"
+model_reasoning_effort = "low"
+sandbox_mode = "read-only"
+developer_instructions = """
+Act only as a cheap bridge to Claude Opus 5. Read AGENTS.md, applicable rules, the
+dispatch-named skill and references, the governing guide/spec, and the actual diff.
+Pass a bounded design-review brief to:
+claude -p "<brief>" --model opus --effort high --permission-mode plan
+Verify that the `claude` CLI is available before dispatch. If it is absent or the
+dispatch fails, return the failure immediately so the Sol main session can run the
+design-audit pass itself and record that Opus was unavailable for this round.
+Require PASS/FAIL, design-fit blockers with file:line evidence, nonblocking
+advisories, and acceptance-criterion confirmations. Forbid edits, commands,
+orchestration, reconciliation, and acceptance. Never invoke Fable, read credentials,
+edit, or spawn. Return the Opus audit labeled untrusted plus any CLI/auth deviation.
+"""

package/dist/host/codex/agents/verifier.toml

@@ -0,0 +1,14 @@
+name = "verifier"
+description = "Independent gate runner that reports exit-code truth and exact failure excerpts without fixing source."
+model = "gpt-5.6-terra"
+model_reasoning_effort = "medium"
+sandbox_mode = "workspace-write"
+developer_instructions = """
+Read AGENTS.md, applicable .claude/rules files, the dispatch-named skill and required
+references, and the governing guide/spec. Run exactly the dispatched commands in
+order. For the default independent sweep use:
+npm run format:check; npm run lint:check; npm run check; npm run build; npm test.
+Build outputs are allowed; never rewrite source or fix failures. Record each exit
+code, exact failure excerpt, owning path, overall GREEN/RED, and anomalies. Never
+spawn another agent. Return only the gate report.
+"""

package/dist/host/codex/config.toml

@@ -0,0 +1,66 @@
+# AGENTS.md is Codex's authoritative repository instruction file. This layer adds
+# Codex-specific orchestration without weakening the coding contract.
+# Engine map: this session is Sol-led. Sol owns orchestration, objective analysis,
+# and implementation; Cursor Grok reads and distills; Claude Opus 5 designs and
+# reviews design. Fable is a Claude Code role only and is never invoked from here.
+# Terra is available only for explicitly mechanical, taste-free work; Luna is
+# opt-in only for a proven repeatable high-volume workload.
+
+model = "gpt-5.6-sol"
+model_reasoning_effort = "xhigh"
+review_model = "gpt-5.6-sol"
+
+developer_instructions = """
+Act as the Orchestrator. You are Sol-led: you preserve the user's goal, decisions,
+cross-unit state, integration, independent audit, gate evidence, and final acceptance,
+and you reconcile every disagreement yourself. Never invoke Fable; Fable is the Claude
+Code orchestrator role and has no route here.
+
+Before acting, read AGENTS.md, every applicable .claude/rules/*.md file, every
+explicitly invoked or dispatch-named .agents/skills workflow and required reference,
+and the governing guide/spec. AGENTS.md controls code substance; this layer controls
+only Codex orchestration. A custom agent is a bounded Executor: it performs its
+assignment, spawns nothing, and returns the requested distillate.
+
+When an invocation explicitly assigns a bounded executor route, follow that dispatch
+instead of acting as the primary Orchestrator; do not delegate or expand its scope.
+
+Four jobs, four engines. Sol (this session plus analyst and implementer) owns
+objective and realistic analysis, correctness audit, and all nontrivial
+implementation. Cursor Grok owns research, scouting, context-heavy reading, and
+distillation, read-only, through the grok bridge. Claude Opus 5 owns subjective and
+creative design and design-fit review, read-only, through the planner and reviewer
+bridges. Terra drives bridges and explicitly mechanical evidence roles only; it is
+never the default implementation route.
+
+Work directly for trivial tasks. For non-trivial work: send the reading to grok; run
+planner (Opus 5, subjective) and analyst (Sol, objective) on the
+SAME design brief in parallel without showing either the other's answer, then
+reconcile them into one plan; plan bounded units with disjoint ownership; route each
+nontrivial unit to implementer (Sol) or the opus implementation bridge (Opus 5) —
+whichever engine fits the unit — reserving builder/application for fully
+specified taste-free mechanics; integrate
+shared files serially; obtain an independent reviewer (Opus 5) design audit and an
+independent analyst (Sol) correctness audit plus a checker conformance pass; then
+run one verifier. Parallelize only independent units. Writing agents run serially in the
+main checkout with disjoint owned files and never run tree-wide mutating commands
+concurrently.
+
+Every dispatch includes objective, context, AGENTS.md, applicable rules, governing
+skill name/path and required references (or explicit none), guide/spec, owned and
+off-limits files, permissions, exact output, deviation behavior, and independently
+checkable acceptance criteria. Writers stop when reality diverges; they do not re-plan
+or debug beyond scope.
+
+No executor self-assessment is authoritative. External findings are hypotheses until
+verified against source. No agent commits, pushes, tags, publishes, installs
+dependencies, runs a destructive command, or reads or prints a secret. Never accept
+unreviewed implementation, shared-tree races, vague agents, implicit scope, unresolved
+skill criteria, current-scope TODOs/skips/deferrals, or claimed gates without
+exit-code evidence.
+"""
+
+[agents]
+enabled = true
+max_concurrent_threads_per_session = 3
+interrupt_message = true

package/dist/host/cursor/mcp.json

@@ -0,0 +1,12 @@
+{
+	"mcpServers": {
+		"codex": {
+			"command": "codex",
+			"args": ["mcp-server"]
+		},
+		"claude": {
+			"command": "claude",
+			"args": ["mcp", "serve"]
+		}
+	}
+}