codebyplan 1.13.60 → 1.13.62

package/templates/skills/cbp-map-architecture/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: cbp-map-architecture
+model: inherit
 effort: xhigh
 description: Orchestrate architecture map generation for one or all modules. Spawns the cbp-map-architecture agent per module, writes per-module .md files to .claude/architecture/, regenerates INDEX.md and graph.md, and stamps each module via the CLI. Idempotent — safe to re-run.
 argument-hint: '[--module <path>] [--deep <path,...>]'
@@ -66,6 +67,10 @@ For each module in `targets[]`:
 Modules may be spawned concurrently (parallel Task calls) when there are multiple targets
 with no inter-module dependency. The agent is read-only and safe to parallelize.
 
+#### Orchestration (optional)
+
+Step B's per-module `cbp-map-architecture` fan-out MAY be authored as a `Workflow(...)` script instead of ad-hoc parallel `Task` calls — for deterministic per-module fan-out and schema-validated map outputs. This is opt-in (ultracode session or explicit user request); the parallel `Task` flow above stays the DEFAULT and is unchanged. See `rules/workflow-orchestration.md`.
+
 ### Step C: Regenerate INDEX.md and graph.md
 
 After all per-module map files are written:

package/templates/skills/cbp-merge-main/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: cbp-merge-main
 description: Merge main into the current feat branch with interactive per-conflict resolution and inline QA re-run
+model: inherit
 effort: high
 ---
 

package/templates/skills/cbp-refresh-arch-map/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: cbp-refresh-arch-map
+model: inherit
 effort: high
 description: Drift-scoped refresh of the .claude/architecture/ map — re-runs the cbp-map-architecture agent for ONLY the modules whose stamped git SHA has changed, regenerates INDEX.md + graph.md, and re-stamps. Idempotent; no-op when no module has drifted.
 argument-hint: '[--module <path>]'

package/templates/skills/cbp-round-build/SKILL.md

@@ -2,6 +2,7 @@
 name: cbp-round-build
 description: Execute the approved plan from /cbp-round-plan — runs per-wave builders, inline testing-qa per wave, and auto-triggers /cbp-verify
 triggers: [cbp-verify]
+model: inherit
 effort: xhigh
 ---
 
@@ -197,6 +198,10 @@ Input contracts: `cbp-testing-qa-agent` receives `executor_output`, `testing_pro
 
 **Independence**: neither agent reads the other's output. Baseline-regression findings surface as a BLOCKING gate at `/cbp-verify` (an explicit accept-or-fix user decision; baselines are NEVER auto-accepted). Per-wave spawns MAY run in parallel with the next wave's builder when dependency order allows. The `cbp-e2e-*` specialists are parallel siblings of `cbp-testing-qa-agent` — they do not share state.
 
+#### Orchestration (optional)
+
+Under heavy fan-out, Step 5's per-wave builders and their parallel `cbp-testing-qa-agent` + `cbp-e2e-*` siblings MAY be authored as a `Workflow(...)` script instead of ad-hoc `Task`/`Agent` spawning — for deterministic fan-out, wave barriers, and schema-validated outputs. This is opt-in (ultracode session or explicit user request); the spawn flow above stays the DEFAULT and is unchanged. See `rules/workflow-orchestration.md`.
+
 ### Step 5b: Post-E2E Screenshot Review (cbp-frontend-ui Phase 6.5)
 
 Aggregate screenshots across ALL specialists that ran: `screenshots = Object.values(round.context.e2e_outputs ?? {}).flatMap(o => o.screenshots ?? [])`. When the aggregated list is non-empty, invoke the `cbp-frontend-ui` skill with `phase: 'screenshot_review'` (input: `files_changed`, `e2e_screenshots: <aggregated screenshots>`, `context: { checkpoint_goal, round_requirements }`). Under this phase the skill runs only Phase 6.5 (Rendered-Output Visual Review) + 7 + 8 — Phases 1-6 (style) already ran inline at builder Step 3.8 with `phase: 'style_only'`.

package/templates/skills/cbp-round-complete/SKILL.md

@@ -4,6 +4,7 @@ description: Reconcile user git-add approvals and complete the round (the ask-ti
 argument-hint: [chk-task-round | task-round]
 disable-model-invocation: true
 triggers: [cbp-round-plan]
+model: inherit
 effort: low
 ---
 

package/templates/skills/cbp-round-plan/SKILL.md

@@ -3,6 +3,7 @@ name: cbp-round-plan
 description: Plan a round — round-1 planning AND round-2+ deep-analysis of unapproved work, then spawn cbp-round-planner and auto-trigger /cbp-round-build
 triggers: [cbp-round-build]
 argument-hint: [chk-task-round | task-round | requirements-text]  # e.g. `108-1-2`, `45-2`, or free-text
+model: inherit
 effort: xhigh
 ---
 
@@ -260,6 +261,10 @@ input:
 
 Wait for planner output. **If the spawn fails, STOP per "Planner Spawn Failure Is A Gate Failure" above** — do not self-certify a plan inline.
 
+#### Orchestration (optional)
+
+When a plan warrants independent perspectives, Step 7's `cbp-round-planner` spawn MAY be expressed as a `Workflow(...)` script — e.g. a judge-panel of independent plans, scored and synthesized — instead of a single ad-hoc spawn. This is opt-in (ultracode session or explicit user request); the single-spawn flow above stays the DEFAULT and is unchanged. See `rules/workflow-orchestration.md`.
+
 ### Step 8: Present Plan
 
 Present the plan to user:

package/templates/skills/cbp-session-end/SKILL.md

@@ -1,7 +1,8 @@
 ---
 name: cbp-session-end
 description: End a development session
-effort: xhigh
+model: inherit
+effort: high
 ---
 
 # Session End Command

package/templates/skills/cbp-session-start/SKILL.md

@@ -2,6 +2,7 @@
 name: cbp-session-start
 description: Start a development session
 triggers: [cbp-todo]
+model: inherit
 effort: low
 ---
 

package/templates/skills/cbp-setup-cd/SKILL.md

@@ -3,7 +3,8 @@ scope: org-shared
 name: cbp-setup-cd
 description: Detect configured CD surfaces, write/update .codebyplan/cd.json via `codebyplan cd init`, scaffold publish.yml and release-desktop.yml GitHub Actions workflows, and walk through environment/approval/OIDC setup. Interactive, idempotent.
 argument-hint: "[--force]"
-effort: xhigh
+model: inherit
+effort: high
 allowed-tools: Read, Write, Edit, Bash(cat *), Bash(jq *), Bash(test *), Bash(ls *), Bash(diff *), Bash(codebyplan cd *), Bash(npx codebyplan cd *), AskUserQuestion
 ---
 

package/templates/skills/cbp-setup-ci/SKILL.md

@@ -3,7 +3,8 @@ scope: org-shared
 name: cbp-setup-ci
 description: Detect CI platforms, write/update .codebyplan/ci.json, scaffold the GitHub Actions CI workflow, and enforce the required CI status check on the main branch. Interactive, idempotent.
 argument-hint: "[--force]"
-effort: xhigh
+model: inherit
+effort: high
 allowed-tools: Read, Write, Edit, Bash(cat *), Bash(jq *), Bash(test *), Bash(ls *), Bash(codebyplan ci *), Bash(npx codebyplan ci *), Bash(gh api *), Bash(gh auth *), AskUserQuestion
 ---
 

package/templates/skills/cbp-setup-e2e/SKILL.md

@@ -2,7 +2,8 @@
 name: cbp-setup-e2e
 description: Detect installed E2E frameworks, ask which to enable, record credentials source (gitignored env-file path + var names only, never secrets), and write/refresh .codebyplan/e2e.json. Interactive, idempotent.
 argument-hint: "[--force]"
-effort: xhigh
+model: inherit
+effort: high
 allowed-tools: Read, Write, Edit, Bash(cat *), Bash(jq *), Bash(which *), Bash(test *), Bash(mkdir *), Bash(cp *), Bash(echo *), Bash(date *), Bash(mv *), Bash(git check-ignore *), AskUserQuestion, mcp__codebyplan__get_repos
 ---
 

package/templates/skills/cbp-setup-eslint/SKILL.md

@@ -2,7 +2,8 @@
 name: cbp-setup-eslint
 description: Detect each app's tech stack, resolve matching DB ESLint presets, confirm which to enable per app, run `codebyplan eslint init` to generate eslint.config.mjs, and write/refresh .codebyplan/eslint.json. Interactive, idempotent.
 argument-hint: "[--force]"
-effort: xhigh
+model: inherit
+effort: high
 allowed-tools: Read, Write, Edit, Bash(cat *), Bash(jq *), Bash(test *), Bash(ls *), Bash(mkdir *), Bash(cp *), Bash(echo *), Bash(mv *), Bash(npx codebyplan eslint *), AskUserQuestion, mcp__codebyplan__get_repos, mcp__codebyplan__get_eslint_presets
 ---
 

package/templates/skills/cbp-ship/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: cbp-ship
 description: Orchestrate runtime deployment for a checkpoint — Vercel web, EAS mobile (Expo Go dev build / TestFlight preview), Tauri desktop, npm package publish, VS Code extension, Railway backend, Supabase migrations. Detects configured surfaces, walks the user through what to deploy, executes per-surface deploy steps, verifies each landed.
+model: inherit
 effort: xhigh
 ---
 
@@ -202,6 +203,10 @@ If a surface fails:
 
 EXCEPTION: `supabase` migration push failure halts the rest. Schema mismatch downstream is worse than partial shipment.
 
+#### Orchestration (optional)
+
+Step 5's per-surface deploys — the independent tails after the mandatory `supabase`-first step — MAY be authored as a `Workflow(...)` script for deterministic parallel fan-out instead of ad-hoc sequencing. This is opt-in (ultracode session or explicit user request); the sequential flow above (including the `supabase`-first ordering) stays the DEFAULT and is unchanged. See `rules/workflow-orchestration.md`.
+
 ### Step 6 — Verify each surface landed
 
 After each surface deploys, run its verification:

package/templates/skills/cbp-ship-configure/SKILL.md

@@ -3,7 +3,8 @@ name: cbp-ship-configure
 description: Configure shipment for one or more surfaces in the current repo — Vercel link, EAS project + eas.json scaffold, Apple credentials probe, npm publish auth check (including `codebyplan` asset-publish automation via the publish-on-main workflow), Railway project link, Supabase access token verify; Supabase GitHub branching integration via /cbp-supabase-setup. Interactive step-by-step; never stores credentials in the repo.
 argument-hint: [--surface=<id>]
 allowed-tools: Read, Write, Edit, Bash(which *), Bash(vercel *), Bash(eas *), Bash(npm *), Bash(railway *), Bash(jq *), Bash(mkdir *), Bash(cp *), Bash(echo *), Skill(cbp-supabase-setup)
-effort: xhigh
+model: inherit
+effort: high
 ---
 
 # Ship Configure Command

package/templates/skills/cbp-ship-main/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: cbp-ship-main
 description: Ship feat branch to production branch via PR — thin wrapper around `codebyplan ship`
+model: inherit
 effort: high
 ---
 

package/templates/skills/cbp-standalone-task-check/SKILL.md

@@ -4,6 +4,7 @@ name: cbp-standalone-task-check
 description: AI production review for the current standalone task
 argument-hint: [task]  # e.g. `45` (standalone TASK-45)
 triggers: [cbp-standalone-task-testing]
+model: inherit
 effort: high
 ---
 

package/templates/skills/cbp-standalone-task-complete/SKILL.md

@@ -3,6 +3,7 @@ scope: repo-only:codebyplan
 name: cbp-standalone-task-complete
 description: Complete a standalone task — ship feat branch to production via PR and mark done
 argument-hint: [task]  # e.g. `45` (standalone TASK-45)
+model: inherit
 effort: xhigh
 ---
 

package/templates/skills/cbp-standalone-task-create/SKILL.md

@@ -2,7 +2,8 @@
 scope: repo-only:codebyplan
 name: cbp-standalone-task-create
 description: Creates a standalone task (not checkpoint-bound) via create_standalone_task MCP tool
-effort: xhigh
+model: inherit
+effort: high
 ---
 
 # Standalone Task Create Command

package/templates/skills/cbp-standalone-task-start/SKILL.md

@@ -3,7 +3,8 @@ scope: repo-only:codebyplan
 name: cbp-standalone-task-start
 description: Start a standalone task, load context from DB
 argument-hint: [task]  # e.g. `45` (standalone TASK-45)
-effort: xhigh
+model: inherit
+effort: high
 ---
 
 # Standalone Task Start Command

package/templates/skills/cbp-standalone-task-testing/SKILL.md

@@ -4,7 +4,8 @@ name: cbp-standalone-task-testing
 description: Run comprehensive task-level testing after /cbp-standalone-task-check passes
 argument-hint: [task]  # e.g. `45` (standalone TASK-45)
 triggers: [cbp-standalone-task-complete]
-effort: xhigh
+model: inherit
+effort: high
 ---
 
 # Standalone Task Testing Command

package/templates/skills/cbp-stripe/SKILL.md

@@ -2,7 +2,8 @@
 scope: org-shared
 name: cbp-stripe
 description: "Stripe integration guidance — load when implementing or reviewing payments, Checkout, subscriptions/billing, webhooks, Connect, Tax, or Treasury. Encodes the API-selection routing table, the no-payment_method_types rule, restricted-key security, and Stripe SDK conventions."
-effort: xhigh
+model: inherit
+effort: high
 ---
 
 # Stripe Integration (CBP)

package/templates/skills/cbp-supabase-branch-check/SKILL.md

@@ -3,7 +3,8 @@ name: cbp-supabase-branch-check
 description: Gate skill called by /cbp-ship-main (pre-merge) to verify the Supabase preview branch health check is green before allowing a PR to be merged; skips when no DB-path changes are detected.
 argument-hint: "[--mode pre_pr_create|pre_merge] [--target integration|production]"
 allowed-tools: Bash(git *), Bash(gh *), Bash(jq *), Bash(supabase *), Bash(sleep *), Bash(echo *), Read, mcp__supabase__list_branches, mcp__supabase__get_logs
-effort: xhigh
+model: inherit
+effort: high
 ---
 
 # Supabase Branch Check

package/templates/skills/cbp-supabase-migrate/SKILL.md

@@ -3,6 +3,7 @@ name: cbp-supabase-migrate
 description: Scaffold or adopt a Supabase migration for the current PR branch, apply to the branch's preview DB, run advisor checks, regenerate TypeScript types. Includes a fresh-branch dry-run pre-flight that uses one persistent dry-run ephemeral branch per feature branch.
 argument-hint: "[--new <name> | <path-to-sql>]"
 allowed-tools: Read, Edit, Write, Bash(codebyplan supabase *), Bash(npx codebyplan supabase *), Bash(npx codebyplan checkpoint update *), Bash(npx codebyplan task update *), Bash(git *), Bash(supabase *), Bash(jq *), Bash(date *), Bash(which *), Bash(cp *), Bash(mv *), Bash(test *), Bash(ls *), mcp__supabase__apply_migration, mcp__supabase__list_migrations, mcp__supabase__get_advisors, mcp__supabase__generate_typescript_types, mcp__supabase__reset_branch, mcp__supabase__list_branches, mcp__supabase__create_branch, mcp__supabase__get_cost, mcp__supabase__confirm_cost, mcp__codebyplan__update_checkpoint, mcp__codebyplan__update_task
+model: inherit
 effort: xhigh
 ---
 

package/templates/skills/cbp-supabase-setup/SKILL.md

@@ -3,7 +3,8 @@ name: cbp-supabase-setup
 description: Enable Supabase GitHub branching integration — GitHub app authorization, required-status-check enforcement on main + integration branch, persistent branch creation, and idempotency marker in .codebyplan/shipment.json.
 argument-hint: "[--force]"
 allowed-tools: Read, Edit, Bash(supabase *), Bash(jq *), Bash(mv *), Bash(date *), Bash(test *), Bash(which *)
-effort: xhigh
+model: inherit
+effort: high
 ---
 
 # Supabase Branching Setup

package/templates/skills/cbp-task-create/SKILL.md

@@ -1,7 +1,8 @@
 ---
 name: cbp-task-create
 description: Create a new task within the active checkpoint
-effort: xhigh
+model: inherit
+effort: high
 ---
 
 # Task Create Command

package/templates/skills/cbp-task-start/SKILL.md

@@ -3,6 +3,7 @@ name: cbp-task-start
 description: Start a task, load context from DB
 triggers: [cbp-round-plan]
 argument-hint: [chk-task]  # e.g. `108-1` (CHK-108 TASK-1)
+model: inherit
 effort: xhigh
 ---
 

package/templates/skills/cbp-todo/SKILL.md

@@ -1,7 +1,8 @@
 ---
 name: cbp-todo
 description: Entry point - what to work on next
-effort: low
+model: inherit
+effort: medium
 ---
 
 # Todo Command

package/templates/skills/cbp-verify/SKILL.md

@@ -3,6 +3,7 @@ name: cbp-verify
 description: Unified verify stage — deterministic gates, real-execution proof, and a fresh-context diff review at round or task scope. Auto-triggered by cbp-round-build; escalates to task scope on the last clean round.
 argument-hint: [chk-task[-round] | task[-round]]
 triggers: [cbp-round-plan, cbp-round-complete, cbp-finalize]
+model: inherit
 effort: xhigh
 ---
 
@@ -98,6 +99,10 @@ Triage the returned findings: in-scope mechanical fixes the orchestrator applies
 (`Edit`/`Write`); blocking out-of-scope findings → `/cbp-round-plan` fix round. A baseline
 regression is a **blocking user-accept gate** — never auto-accepted.
 
+#### Orchestration (optional)
+
+When a finding warrants adversarial confirmation, Phase 4's `cbp-verify-reviewer` spawn MAY be expressed as a `Workflow(...)` script — e.g. N independent multi-vote reviewers — instead of a single ad-hoc spawn. This is opt-in (ultracode session or explicit user request); the single-spawn flow above stays the DEFAULT and is unchanged. See `rules/workflow-orchestration.md`.
+
 ### PHASE 5 — VERDICT + ROUTE (single directive, never an A/B/C menu)
 
 Combine Phase 2 + 3 + 4. Route on one directive (`feedback-close-out-routing.md`):

package/templates/skills/supabase/SKILL.md

@@ -1,6 +1,8 @@
 ---
 name: supabase
 description: "Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector)."
+model: inherit
+effort: medium
 metadata:
   author: supabase
   version: "0.1.2"

package/templates/skills/supabase-postgres-best-practices/SKILL.md

@@ -2,6 +2,8 @@
 name: supabase-postgres-best-practices
 description: Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.
 license: MIT
+model: inherit
+effort: low
 metadata:
   author: supabase
   version: "1.1.1"