@appsforgood/next-supabase-kit 0.1.1 → 0.1.3

package/runtime-skills/content-first-design/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: content-first-design
+description: Use before designing or changing user-facing product screens, dashboards, tools, marketplaces, content experiences, or AI workflow UIs.
+---
+
+Canonical workflow: read `skills/content-first-design.md` or `.agent-kit/skills/content-first-design.md`.
+
+Capture audience, user needs, product category, content inventory, brand constraints, creative options, and non-goals before implementation starts.

package/runtime-skills/conversion-copywriting/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: conversion-copywriting
+description: Use for public-facing or conversion-facing headlines, CTAs, onboarding, pricing, landing pages, and UX copy.
+---
+
+Canonical workflow: read `skills/conversion-copywriting.md` or `.agent-kit/skills/conversion-copywriting.md`.
+
+Use `MESSAGING.md` for audience, pain, desired outcome, proof, objections, voice, and conversion goal. Mark unsupported claims as assumptions.

package/runtime-skills/deployment-observability/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: deployment-observability
+description: Use for release readiness, environment variables, migration order, logs, monitoring, rollback, and post-release verification.
+---
+
+Canonical workflow: read `skills/deployment-observability.md` or `.agent-kit/skills/deployment-observability.md`.
+
+Confirm deployment prerequisites, observable failures, release order, verification commands, and rollback guidance before shipping.

package/runtime-skills/docs-maintainer/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: docs-maintainer
+description: Use after significant architecture, behavior, release, security, adapter, or workflow changes that affect living docs.
+---
+
+Canonical workflow: read `skills/docs-maintainer.md` or `.agent-kit/skills/docs-maintainer.md`.
+
+Update `SPEC.md`, `DECISIONS.md`, `DOCS.md`, `QUALITY_GATES.md`, `TESTING.md`, `UPGRADE.md`, and related docs so another engineer or agent can continue safely.

package/runtime-skills/frontend-design-system/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: frontend-design-system
+description: Use for user-facing screens and components that need design tokens, component states, responsiveness, accessibility, and anti-generic UI review.
+---
+
+Canonical workflow: read `skills/frontend-design-system.md` or `.agent-kit/skills/frontend-design-system.md`.
+
+Require real content, task-first hierarchy, component states, accessibility, mobile behavior, and visual QA evidence before accepting significant frontend work.

package/runtime-skills/frontend-distinctiveness-benchmark/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: frontend-distinctiveness-benchmark
+description: Use when significant frontend work risks looking interchangeable with a generic AI-generated product.
+---
+
+Canonical workflow: read `skills/frontend-distinctiveness-benchmark.md` or `.agent-kit/skills/frontend-distinctiveness-benchmark.md`.
+
+Prove first-screen specificity, product nouns, data shapes, real actions, source-safe references, asset provenance, important states, and desktop/mobile evidence.

package/runtime-skills/frontend-product-quality-rubric/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: frontend-product-quality-rubric
+description: Use to score significant frontend work for user fit, content specificity, visual identity, IA, states, accessibility, and source safety.
+---
+
+Canonical workflow: read `skills/frontend-product-quality-rubric.md` or `.agent-kit/skills/frontend-product-quality-rubric.md`.
+
+Reject critical zeroes, require at least `10/14` for acceptance, and require higher evidence for best-practice frontend claims.

package/runtime-skills/landing-page-copy/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: landing-page-copy
+description: Use for landing-page headlines, subheads, proof, objections, CTAs, and conversion copy.
+---
+
+Canonical workflow: read `skills/landing-page-copy.md` or `.agent-kit/skills/landing-page-copy.md`.
+
+Tie copy to audience, problem, outcome, differentiator, proof, objections, and one clear primary CTA. Avoid generic SaaS claims.

package/runtime-skills/nextjs-app-router/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: nextjs-app-router
+description: Use for Next.js App Router, Server Components, Client Components, Route Handlers, Server Actions, caching, forms, and metadata.
+---
+
+Canonical workflow: read `skills/nextjs-app-router.md` or `.agent-kit/skills/nextjs-app-router.md`.
+
+Keep server/client boundaries explicit, preserve auth context, protect secrets from client bundles, and handle loading, error, empty, and success states.

package/runtime-skills/onboarding-empty-state-copy/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: onboarding-empty-state-copy
+description: Use for onboarding copy, first-run states, empty states, setup prompts, and guided user flows.
+---
+
+Canonical workflow: read `skills/onboarding-empty-state-copy.md` or `.agent-kit/skills/onboarding-empty-state-copy.md`.
+
+Use product-specific nouns and actions, reduce cognitive load, avoid unsupported claims, and align copy with `MESSAGING.md`.

package/runtime-skills/owasp-security-review/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: owasp-security-review
+description: Use for auth, API routes, Server Actions, external fetches, file uploads, webhooks, dependencies, and data mutations.
+---
+
+Canonical workflow: read `skills/owasp-security-review.md` or `.agent-kit/skills/owasp-security-review.md`.
+
+Review broken access control, IDOR, injection, SSRF, misconfiguration, vulnerable dependencies, secret handling, validation, encoding, and safe errors.

package/runtime-skills/planning-council/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: planning-council
+description: Use for planning, roadmaps, ambiguous feature requests, core architecture changes, auth/data work, release work, and multi-agent routing.
+---
+
+Canonical workflow: read `skills/planning-council.md` or `.agent-kit/skills/planning-council.md`.
+
+Classify the request, select the roster workflow, name the maturity target, map affected layers, preserve contracts, assign handoffs, and record evidence.

package/runtime-skills/positioning-messaging/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: positioning-messaging
+description: Use for audience, pain, outcome, alternatives, differentiator, proof, objections, voice, and conversion strategy.
+---
+
+Canonical workflow: read `skills/positioning-messaging.md` or `.agent-kit/skills/positioning-messaging.md`.
+
+Update `MESSAGING.md`, ask only high-impact discovery questions, and connect every public claim to real proof or an explicit assumption.

package/runtime-skills/postgres-migrations/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: postgres-migrations
+description: Use for schema changes, constraints, indexes, SQL functions, triggers, seed data, data migrations, and rollback planning.
+---
+
+Canonical workflow: read `skills/postgres-migrations.md` or `.agent-kit/skills/postgres-migrations.md`.
+
+Order migrations, protect integrity with constraints, add indexes for access patterns, and document rollback or retry guidance.

package/runtime-skills/product-voice-tone/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: product-voice-tone
+description: Use for product voice, tone, microcopy, onboarding language, CTA style, and consistent UX copy.
+---
+
+Canonical workflow: read `skills/product-voice-tone.md` or `.agent-kit/skills/product-voice-tone.md`.
+
+Keep voice grounded in product facts, audience needs, proof, objections, and `MESSAGING.md`; avoid generic AI-looking language.

package/runtime-skills/reference-led-design-critique/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: reference-led-design-critique
+description: Use before accepting significant frontend work that needs references, anti-references, source safety, and design critique.
+---
+
+Canonical workflow: read `skills/reference-led-design-critique.md` or `.agent-kit/skills/reference-led-design-critique.md`.
+
+Use references for lessons without copying protected source design, brand identity, copy, or assets. Record critique verdict and required changes.

package/runtime-skills/supabase-auth-rls/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: supabase-auth-rls
+description: Use for Supabase Auth, SSR clients, sessions, middleware, RLS policies, Storage policies, and service-role usage.
+---
+
+Canonical workflow: read `skills/supabase-auth-rls.md` or `.agent-kit/skills/supabase-auth-rls.md`.
+
+Enforce authorization in RLS, keep service-role keys server-only, test session refresh and redirects, and prevent IDOR at the SQL boundary.

package/runtime-skills/testing-qa/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: testing-qa
+description: Use for unit tests, regression tests, smoke checks, Playwright coverage, visual QA, and acceptance evidence.
+---
+
+Canonical workflow: read `skills/testing-qa.md` or `.agent-kit/skills/testing-qa.md`.
+
+Cover core logic, preserved behavior, critical paths, auth/data mutations, network failures, empty/error states, and explicitly document gaps.

package/runtime-skills/upgrade-maintenance/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: upgrade-maintenance
+description: Use for Agent Kit, Next.js, Supabase, UI library, testing tool, release workflow, adapter, and dependency upgrades.
+---
+
+Canonical workflow: read `skills/upgrade-maintenance.md` or `.agent-kit/skills/upgrade-maintenance.md`.
+
+Run `agent-kit diff`, preserve overrides, review conflicts, check release notes/migrations/codemods, run audit, and record rollback evidence.

package/runtime-skills/visual-regression-qa/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: visual-regression-qa
+description: Use for user-facing screen changes, reusable components, visual design tokens, responsive layouts, image-heavy pages, and visual acceptance.
+---
+
+Canonical workflow: read `skills/visual-regression-qa.md` or `.agent-kit/skills/visual-regression-qa.md`.
+
+Name the visual QA tier, capture important states and breakpoints, handle volatile regions, and keep visual checks separate from accessibility and data-boundary tests.

package/schemas/onboarding-state.schema.json

@@ -0,0 +1,33 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://agent-skills.dev/schemas/onboarding-state.schema.json",
+  "title": "Agent Kit Onboarding State",
+  "type": "object",
+  "required": [
+    "schemaVersion",
+    "depth",
+    "startedAt",
+    "lastVisitedAt",
+    "completedSections",
+    "skippedSections",
+    "currentSection",
+    "currentStep",
+    "wizardVersion"
+  ],
+  "additionalProperties": false,
+  "properties": {
+    "schemaVersion": { "const": 1 },
+    "depth": { "type": "string", "enum": ["quick", "standard", "complete", "undecided"] },
+    "startedAt": { "type": "string", "format": "date-time" },
+    "lastVisitedAt": { "type": "string", "format": "date-time" },
+    "completedAt": { "type": "string", "format": "date-time" },
+    "completedSections": { "type": "array", "items": { "type": "string" } },
+    "skippedSections": { "type": "array", "items": { "type": "string" } },
+    "currentSection": { "type": "string" },
+    "currentStep": { "type": "integer", "minimum": 0 },
+    "wizardVersion": { "type": "string" },
+    "ideSurface": { "type": "string", "enum": ["cursor", "copilot", "claude", "codex", "other"] },
+    "ideVerifiedAt": { "type": "string", "format": "date-time" },
+    "visualQaTier": { "type": "string", "enum": ["baseline", "strong", "mature"] }
+  }
+}

package/templates/next-supabase/.github/workflows/agent-kit-audit.yml

@@ -0,0 +1,35 @@
+name: Agent Kit Audit
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  audit:
+    name: Agent kit readiness
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      - name: Setup Node
+        uses: actions/setup-node@v6
+        with:
+          node-version: "24"
+          cache: npm
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Run baseline audit gate
+        run: npx agent-kit audit --json --min-readiness baseline-setup

package/templates/next-supabase/AGENTS.md

@@ -2,7 +2,7 @@
 
 This project uses explicit agent roles so implementation, security, quality, and documentation do not collapse into one vague assistant.
 
-Use `.agent-kit/agent-roster.json` as the default council contract. Use `MODEL_ROUTING.md` and `.agent-kit/model-routing.json` to choose model profiles for each agent. Before meaningful work, read `.agent-kit/project-context.json` and `.agent-kit/project-context.md` when present, then apply active corrections from `.agent-kit/corrections/project-rules.json` and `.agent-kit/corrections/agent-rules.json`. When a request is ambiguous, planning-oriented, or cross-layer, start with Planner and follow the matching workflow in `AGENT_ROSTER.md`. Use `ASSISTANT_ADAPTERS.md` to confirm which AI coding tools load these instructions and how model selection is handled. Record meaningful council sessions in `COUNCIL.md` or the local Agent Studio files under `.agent-kit/council-sessions/`.
+Use `.agent-kit/agent-roster.json` as the default council contract. Use `MODEL_ROUTING.md` and `.agent-kit/model-routing.json` to choose model profiles for each agent. Before meaningful work, read `.agent-kit/project-context.json`, `.agent-kit/project-context.md`, and `.agent-kit/agent-briefs.md` when present, then apply active corrections from `.agent-kit/corrections/project-rules.json` and `.agent-kit/corrections/agent-rules.json`. When a request is ambiguous, planning-oriented, or cross-layer, start with Planner and follow the matching workflow in `AGENT_ROSTER.md`. Use `ASSISTANT_ADAPTERS.md` to confirm which AI coding tools load these instructions and how model selection is handled. Record meaningful council sessions in `COUNCIL.md` or the local Agent Studio files under `.agent-kit/council-sessions/`.
 
 ## Planner
 

package/templates/next-supabase/ASSISTANT_ADAPTERS.md

@@ -26,10 +26,11 @@ Canonical source of truth:
 
 | Tool | Instruction surface | Instruction status | Model-selection status | Enforcement | Evidence | Notes |
 | --- | --- | --- | --- | --- | --- | --- |
-| Codex / AGENTS.md-compatible tools | `AGENTS.md`, optional `.codex/config.toml`, optional `.codex/agents/*.toml` | TBD | TBD | Partial | TBD | Confirm the tool loads root `AGENTS.md`, follows council routing, and uses `MODEL_ROUTING.md` for model choice. |
-| GitHub Copilot / VS Code | `.github/copilot-instructions.md` and `.github/instructions/*.instructions.md` | TBD | TBD | Advisory | TBD | Use `.agent-kit/assistant-adapters/github-copilot-instructions.md`, `github-next-supabase.instructions.md`, and `model-selection/github-copilot-model-selection.md` as starting points. |
+| Codex / AGENTS.md-compatible tools | `AGENTS.md`, optional `.codex/config.toml`, optional `.codex/agents/*.toml` | TBD | TBD | Partial | TBD | Run `agent-kit init --activate codex` to copy optional `.codex/config.toml`. Confirm the tool loads root `AGENTS.md`. |
+| GitHub Copilot / VS Code | `.github/copilot-instructions.md` and `.github/instructions/*.instructions.md` | TBD | TBD | Advisory | TBD | Run `agent-kit init --activate copilot` to promote Copilot instruction files. |
 | Cursor | `.cursor/rules/cursor-agent-kit.mdc` and `.cursor/rules/cursor-model-selection.mdc` | Active on init | Advisory | Advisory | `agent-kit init` copies canonical rules from `.agent-kit/assistant-adapters/`; verify in Cursor Settings > Rules that both rules load. | `agent-kit init` installs `.cursor/rules/cursor-agent-kit.mdc` and `.cursor/rules/cursor-model-selection.mdc`. Re-run `agent-kit diff` after kit updates if the canonical adapter files changed. |
-| Claude Code | `.claude/agents/*.md` and optional `CLAUDE.md` | TBD | TBD | Partial | TBD | Use `.agent-kit/assistant-adapters/claude-code-subagents.md` and `model-selection/claude-code-subagents-with-models.md` as starting points. |
+| Claude Code | `.claude/agents/*.md` and optional `CLAUDE.md` | TBD | TBD | Partial | TBD | Run `agent-kit init --activate claude` to generate subagents from `.agent-kit/agent-roster.json` and install `CLAUDE.md`. |
+| Antigravity | `.antigravity/agent-kit/plugin.json`, `.antigravity/agent-kit/commands/*.toml`, `.antigravity/runtime-skills/*/SKILL.md` | TBD | TBD | Advisory | TBD | Run `agent-kit init --activate antigravity`, then `agent-kit adapter validate antigravity`; optional native validation is `agy plugin validate` when available. |
 
 ## Model Selection
 
@@ -68,6 +69,23 @@ Verification steps:
 
 If a project already customized `.cursor/rules/`, review `.agent-kit/conflicts/` after `agent-kit update` before adopting newer adapter wording.
 
+## Antigravity Activation
+
+`agent-kit init --activate antigravity` installs a native runtime adapter without changing the canonical Agent Kit operating model:
+
+- `.antigravity/agent-kit/plugin.json`
+- `.antigravity/agent-kit/commands/*.toml`
+- `.antigravity/runtime-skills/*/SKILL.md`
+- `.antigravity/agent-kit/README.md`
+
+Validate the structural package with:
+
+```bash
+agent-kit adapter validate antigravity
+```
+
+If the local machine has the Antigravity CLI, teams may also run native plugin validation and record that evidence here. Runtime command files are adapters only; `AGENTS.md`, `.agent-kit/agent-roster.json`, `QUALITY_GATES.md`, and Agent Studio sessions remain canonical.
+
 ## Acceptance Evidence
 
 Before claiming strong or best-practice maturity, replace the TBD rows above with:

package/templates/next-supabase/CLAUDE.md

@@ -0,0 +1,39 @@
+# Claude Code Project Instructions
+
+This repository uses Agent Kit. Treat the following as the source of truth for council routing, project context, correction rules, model profiles, quality gates, and handoff evidence:
+
+- `AGENTS.md`
+- `AGENT_ROSTER.md`
+- `.agent-kit/agent-roster.json`
+- `MODEL_ROUTING.md`
+- `.agent-kit/model-routing.json`
+- `.agent-kit/project-context.json`
+- `.agent-kit/project-context.md`
+- `.agent-kit/agent-briefs.md` when present
+- `.agent-kit/corrections/project-rules.json`
+- `.agent-kit/corrections/agent-rules.json`
+- `COUNCIL.md`
+- `.agent-kit/council-sessions/`
+- `QUALITY_GATES.md`
+
+## Subagents
+
+Project subagents live in `.claude/agents/*.md` and are generated from `.agent-kit/agent-roster.json` when you run:
+
+```sh
+agent-kit init --activate claude
+```
+
+Use the matching subagent for the active workflow instead of treating every request as a generic implementation pass.
+
+## Validation
+
+```sh
+agent-kit audit --min-readiness baseline-setup
+```
+
+Use `agent-kit session checkpoint --file <json>` to batch-record council evidence instead of many individual session commands.
+
+## Model Selection
+
+Use Claude Code model settings with the profiles in `MODEL_ROUTING.md`. Exact model names are dated recommendations — review when provider docs change.

package/templates/next-supabase/DECISIONS.md

@@ -30,6 +30,20 @@ Add new decisions above this line or keep newest first.
 
 Record major frontend choices here when a creative direction, reference set, anti-reference, brand constraint, information architecture, visual QA tier, or component-system rule materially affects implementation.
 
+## Runtime Adapter Rule
+
+### Context
+
+Agent Kit may expose runtime-native command surfaces such as Antigravity plugin commands.
+
+### Decision
+
+Runtime command files are adapters. `AGENTS.md`, `.agent-kit/agent-roster.json`, `QUALITY_GATES.md`, canonical `.agent-kit/skills/`, and Agent Studio session records remain the source of truth.
+
+### Consequences
+
+Native commands improve invocation ergonomics, but project policy, security gates, handoff rules, model routing, and documentation contracts stay centralized in Agent Kit files.
+
 ## Agent Kit Model Routing
 
 ### Context

package/templates/next-supabase/DOCS.md

@@ -17,6 +17,7 @@ Document:
 
 - Agent council routing in `.agent-kit/agent-roster.json`
 - Assistant activation surfaces in `ASSISTANT_ADAPTERS.md`
+- Optional runtime adapter surfaces such as `.antigravity/agent-kit/` and `.antigravity/runtime-skills/`
 - Model profile routing in `MODEL_ROUTING.md` and `.agent-kit/model-routing.json`
 - Council-session evidence in `COUNCIL.md`
 - Agent, council-session, model-routing, and audit-report schemas in `.agent-kit/schemas/`
@@ -38,6 +39,7 @@ Document primary workflows, including:
 
 - Planning and core-change handoffs from `AGENT_ROSTER.md`
 - Tool-specific assistant activation from `ASSISTANT_ADAPTERS.md`
+- Runtime command validation with `agent-kit adapter validate antigravity` when Antigravity is active
 - Model-selection setup, enforcement status, and limitations from `MODEL_ROUTING.md`
 - Council-session evidence capture from `COUNCIL.md`
 - Upgrade review, conflict handling, migration review, and rollback evidence from `UPGRADE.md`
@@ -53,6 +55,8 @@ Document primary workflows, including:
 - Data creation and update workflow
 - Deployment workflow
 
+Runtime command files are adapters only. Native commands such as `/plan`, `/security`, `/frontend`, `/copy`, `/handoff`, `/audit`, `/setup`, `/upgrade`, and `/ship` should point back to `AGENTS.md`, `.agent-kit/agent-roster.json`, `QUALITY_GATES.md`, `.agent-kit/skills/`, and Agent Studio evidence.
+
 ## Integration Points
 
 Document external APIs, webhooks, storage buckets, cron jobs, email providers, analytics, and monitoring.

package/templates/next-supabase/MODEL_ROUTING.md

@@ -40,6 +40,7 @@ Canonical source of truth:
 | Claude Code | `CLAUDE.md`, `.claude/agents/*.md` | Unverified | Partial | Record date, owner, subagent files, and model frontmatter behavior. |
 | Cursor | `.cursor/rules/*.mdc` | Unverified | Advisory | Record date, owner, model picker/team setting, and loaded rule evidence. |
 | GitHub Copilot | `.github/copilot-instructions.md`, `.github/instructions/*.instructions.md` | Unverified | Advisory | Record date, owner, selected chat/coding-agent model, and loaded instruction evidence. |
+| Antigravity | `.antigravity/agent-kit/plugin.json`, `.antigravity/agent-kit/commands/*.toml`, `.antigravity/runtime-skills/*/SKILL.md` | Unverified | Advisory | Record date, owner, `agent-kit adapter validate antigravity`, and optional native `agy plugin validate` output. |
 
 ## June 2026 Commented Recommendations
 
@@ -98,6 +99,17 @@ June 2026 Agent Kit suggestion:
 -->
 ```
 
+### Antigravity
+
+```md
+<!--
+June 2026 Agent Kit suggestion:
+- Use native `/plan`, `/security`, `/frontend`, `/copy`, `/handoff`, `/audit`, `/setup`, `/upgrade`, and `/ship` commands as runtime entrypoints.
+- Keep model choice aligned with MODEL_ROUTING.md profiles, but record that Antigravity model enforcement is advisory unless the runtime/workspace provides stronger controls.
+- Validate structural assets with `agent-kit adapter validate antigravity`; native `agy plugin validate` is optional when the CLI is installed.
+-->
+```
+
 ## Acceptance Evidence
 
 Before claiming strong or best-practice maturity, record:

package/templates/next-supabase/QUALITY_GATES.md

@@ -20,6 +20,7 @@ Baseline means the project is usable and the agent kit can audit it.
 - `AGENTS.md`, `AGENT_ROSTER.md`, `ASSISTANT_ADAPTERS.md`, `COUNCIL.md`, `SPEC.md`, `DECISIONS.md`, `DOCS.md`, `DESIGN.md`, `MESSAGING.md`, `MODEL_ROUTING.md`, `STYLE_GUIDE.md`, `SECURITY.md`, `TESTING.md`, `DEPLOYMENT.md`, and `UPGRADE.md` exist.
 - `.agent-kit/agent-roster.json`, `.agent-kit/model-routing.json`, and `.agent-kit/schemas/` exist.
 - `.agent-kit/assistant-adapters/` exists.
+- Runtime adapters such as Antigravity are validated with `agent-kit adapter validate <target>` before being treated as active.
 - Agent Studio schemas for project context, correction rules, session events, and studio sessions exist when the installed kit version includes them.
 - Planner is the default planning route.
 - Lead Architect reviews core changes.
@@ -59,6 +60,7 @@ Best-practice means evidence can survive handoff, release, and later audit.
 - Public-facing and conversion-facing copy starts from discovery questions, audience, pain, outcome, differentiator, proof, objections, voice/tone, and CTA hierarchy, with unsupported claims marked as assumptions.
 - Test evidence includes the smallest useful unit/regression checks plus critical-path smoke coverage.
 - Release evidence includes install or production smoke, migration order, dependency audit, package or deployment verification, logs, and rollback notes.
+- Runtime adapter evidence includes command/plugin validation, portable `SKILL.md` coverage, package allowlist coverage, and proof that adapter files point back to Agent Kit source-of-truth contracts.
 - Repo health includes issue/PR templates, CODEOWNERS, dependency updates, CodeQL or equivalent scanning, dependency review, provenance expectations, support, conduct, and governance.
 - Public or shared package releases use Trusted Publishing or equivalent identity-bound release provenance.
 
@@ -73,6 +75,7 @@ Best-practice means evidence can survive handoff, release, and later audit.
 | Marketing/copy | Marketing Copy Lead, Frontend Design Lead, QA, Docs | `MESSAGING.md`, audience and pain, value proposition, proof, objections, voice/tone, CTA hierarchy, risky-claim review |
 | Security-sensitive | Security Reviewer, Lead Architect, QA | OWASP review, boundary validation, dependency/secret review, regression or smoke evidence |
 | Release/package | Deployment/Observability Engineer, Security Reviewer, QA, Docs | Release gate output, dependency audit, install/deploy smoke, provenance or publish identity evidence |
+| Runtime adapter/package | Planner, Lead Architect, Security Reviewer, QA, Docs | `agent-kit adapter validate`, `agent-kit package validate`, command/skill asset coverage, source-of-truth references, no secret-like runtime assets |
 | Upgrade/dependency | Planner, Lead Architect, Security Reviewer, QA, Docs, Deployment/Observability Engineer | Release notes, codemods or migration guide, `agent-kit diff`, conflict review, audit output, rollback notes |
 
 ## Evidence Rules
@@ -81,6 +84,7 @@ Best-practice means evidence can survive handoff, release, and later audit.
 - A test is not evidence unless it covers the behavior, risk, or contract being claimed.
 - A screenshot is not visual QA unless it covers the important viewport, state, and content.
 - A research finding is not a best practice until it is promoted into templates, skills, checklists, audit checks, tests, release gates, or documented decisions.
+- A runtime command is not canonical policy; it is accepted only when it wraps `AGENTS.md`, `.agent-kit/agent-roster.json`, `QUALITY_GATES.md`, canonical skills, and Agent Studio evidence.
 - A fresh install can be baseline setup while still warning on `TBD`, example rows, or starter instruction text; those placeholders must be replaced before claiming strong or best-practice maturity.
 - A local customization is acceptable only when `.agent-kit/overrides.json` explains why and when it was reviewed.
 - A human correction is not durable until it is stored in `.agent-kit/corrections/`, remains secret-safe, has a clear scope, and is visible to future agents through installed instructions.

package/templates/next-supabase/SPEC.md

@@ -24,6 +24,7 @@ List behavior that must be preserved during changes:
 
 - Agent council routing in `.agent-kit/agent-roster.json`
 - Model profile routing in `MODEL_ROUTING.md` and `.agent-kit/model-routing.json`
+- Optional runtime adapter commands and portable `SKILL.md` wrappers, when activated
 - Council-session evidence in `COUNCIL.md`
 - Agent, council-session, model-routing, and audit-report schema contracts in `.agent-kit/schemas/`
 - Planner default ownership for planning and Lead Architect review for core changes
@@ -65,6 +66,7 @@ Record the current maturity target and evidence.
 | --- | --- | --- | --- | --- |
 | Council routing | TBD | TBD | TBD | `AGENT_ROSTER.md`, `COUNCIL.md` |
 | Model routing | TBD | TBD | TBD | `MODEL_ROUTING.md`, `ASSISTANT_ADAPTERS.md` |
+| Runtime adapters | TBD | TBD | TBD | `agent-kit adapter validate antigravity`, `.antigravity/agent-kit/`, `.antigravity/runtime-skills/` |
 | Architecture | TBD | TBD | TBD | Affected-layer map, `DECISIONS.md` |
 | Supabase/RLS | TBD | TBD | TBD | RLS inventory, migration tests |
 | Messaging | TBD | TBD | TBD | `MESSAGING.md`, proof map, objection handling, CTA hierarchy |

package/templates/next-supabase/TESTING.md

@@ -9,6 +9,7 @@ Testing should be proportional to risk. Auth, data mutations, payments, admin ac
 - Integration tests for API, Server Actions, and Supabase interactions where practical.
 - Playwright smoke tests for auth and critical user workflows.
 - Visual QA for important user-facing screens and reusable component states.
+- Runtime adapter validation for plugin manifests, native commands, portable `SKILL.md` wrappers, source-of-truth references, package allowlists, and secret safety.
 
 ## Critical Smoke Paths
 
@@ -52,6 +53,7 @@ Recommended baseline:
 - `agent-kit audit --min-readiness baseline-setup`
 - Playwright smoke tests for critical paths
 - Visual QA evidence for high-risk UI changes
+- `agent-kit adapter validate antigravity` and `agent-kit package validate` when adapter/package assets change
 
 ## Security-Focused Tests
 
@@ -62,6 +64,7 @@ Prioritize:
 - Unauthorized API calls
 - RLS-protected reads and writes
 - Service-role-only operations
+- Secret-like values in runtime adapter assets, generated sessions, static exports, docs, and package files
 
 ## Test Gaps
 

package/templates/next-supabase/UPGRADE.md

@@ -8,6 +8,8 @@ Use this file when upgrading Agent Kit, Next.js, Supabase, shared UI primitives,
 npx @appsforgood/next-supabase-kit@latest doctor
 npx @appsforgood/next-supabase-kit@latest diff
 npx @appsforgood/next-supabase-kit@latest update
+npx @appsforgood/next-supabase-kit@latest adapter validate antigravity
+npx @appsforgood/next-supabase-kit@latest setup --status
 npx @appsforgood/next-supabase-kit@latest audit --min-readiness baseline-setup
 ```
 
@@ -20,6 +22,8 @@ Use `agent-kit audit --min-readiness best-practice-candidate` only after starter
 - Review `.agent-kit/conflicts/` before accepting changed templates.
 - Preserve valid local customizations in `.agent-kit/overrides.json`.
 - Review `AGENTS.md`, `AGENT_ROSTER.md`, `ASSISTANT_ADAPTERS.md`, `MODEL_ROUTING.md`, `COUNCIL.md`, `QUALITY_GATES.md`, `SECURITY.md`, `TESTING.md`, and `DEPLOYMENT.md`.
+- If using Antigravity, review `.antigravity/agent-kit/plugin.json`, `.antigravity/agent-kit/commands/*.toml`, and `.antigravity/runtime-skills/*/SKILL.md`.
+- Validate runtime adapter assets with `agent-kit adapter validate antigravity`.
 - Record accepted tradeoffs in `DECISIONS.md`.
 - Update this file with package version, release notes, migration status, rollback notes, owner, and date.