tribunal-kit 4.3.0 → 4.3.1

package/.agent/skills/api-patterns/SKILL.md

@@ -1,200 +1,200 @@
----
-name: api-patterns
-description: API design mastery. REST, GraphQL, tRPC, and gRPC selection. Request/response design, pagination (cursor/offset), filtering, versioning, rate limiting, error formats (RFC 9457), authentication (JWT/OAuth2/API keys), idempotency, file uploads, webhooks, and OpenAPI documentation. Use when designing APIs, choosing protocols, or implementing API standards.
-allowed-tools: Read, Write, Edit, Glob, Grep
-version: 3.1.0
-last-updated: 2026-04-07
-applies-to-model: gemini-3-1-pro, claude-3-7-sonnet
----
-
-# API Patterns — Design & Protocol Mastery
-
-## Hallucination Traps (Read First)
-- ❌ JWT in URL query params → ✅ `Authorization: Bearer` header only. Query params get logged in server access logs.
-- ❌ Assuming JWT is encrypted → ✅ JWT is base64-encoded (NOT encrypted). Anyone can decode it. Never put secrets/PII in the payload.
-- ❌ Offset pagination on large tables → ✅ `OFFSET 100000` scans and discards 100K rows. Use cursor pagination for tables > 10K rows.
-- ❌ Verbs in REST URLs (`/api/getUsers`) → ✅ Nouns only (`GET /api/users`). HTTP method IS the verb.
-- ❌ `POST` is idempotent → ✅ `POST` is NOT idempotent — requires `Idempotency-Key` header for safe retries.
-- ❌ GraphQL has no security risks → ✅ Deeply nested queries are a DoS vector. Set max depth, query cost limits. Disable introspection in production.
-
----
-
-## Protocol Selection Matrix
-
-| Protocol | Use When |
-|----------|----------|
-| **REST** | Public APIs, 3rd-party consumers, standard CRUD, HTTP caching |
-| **GraphQL** | Complex nested data, multiple clients, flexible queries, mobile bandwidth sensitivity |
-| **tRPC** | Full-stack TypeScript (Next.js monorepo), shared types, no codegen |
-| **gRPC** | Internal microservices, high-throughput, streaming, binary protocol |
-| **WebSocket** | Bidirectional real-time (chat, gaming, live collaboration) |
-| **SSE** | Server-to-client streaming only (AI token streaming, live feeds) |
-
----
-
-## REST Design
-
-### URL Conventions
-```
-✅  GET    /api/v1/users              list users
-✅  GET    /api/v1/users/123          get user by ID
-✅  POST   /api/v1/users              create user
-✅  PATCH  /api/v1/users/123          partial update
-✅  DELETE /api/v1/users/123          delete user
-✅  GET    /api/v1/users/123/posts    nested resource
-
-❌  /api/getUsers   /api/createUser   /api/user (singular)   /api/Users (uppercase)
-```
-
-### HTTP Status Codes
-```
-200 OK             → GET / PUT / PATCH success
-201 Created        → POST success (include Location: /api/v1/users/123 header)
-204 No Content     → DELETE success
-400 Bad Request    → Malformed request / missing fields
-401 Unauthorized   → Missing or invalid authentication
-403 Forbidden      → Authenticated but not authorized
-404 Not Found      → Resource does not exist
-409 Conflict       → Duplicate resource (email already exists)
-422 Unprocessable  → Valid JSON, semantically invalid data
-429 Too Many Req   → Rate limit exceeded
-500 Internal       → Unhandled server error — NEVER expose stack traces
-```
-
-### Response Envelope
-```typescript
-interface ApiResponse<T> { data: T; meta?: Record<string, unknown>; }
-
-interface ApiError {
-  error: {
-    code: string;       // machine-readable: "VALIDATION_ERROR"
-    message: string;    // human-readable: "Email is already in use"
-    details?: Array<{ field: string; message: string }>; // field-level errors
-    requestId?: string; // for support/tracing
-  };
-}
-```
-
----
-
-## Pagination
-
-```typescript
-// ✅ Cursor-based — required for large/dynamic datasets
-// GET /api/v1/posts?cursor=eyJpZCI6MTAwfQ&limit=20
-const posts = await db.post.findMany({
-  where: { id: { lt: decodeCursor(req.query.cursor).id } },
-  orderBy: { id: "desc" },
-  take: limit + 1, // fetch one extra to determine hasMore
-});
-const hasMore = posts.length > limit;
-if (hasMore) posts.pop();
-return { data: posts, meta: { hasMore, nextCursor: encodeCursor(posts.at(-1)) } };
-
-// Offset-based — only for small datasets where users need page jumping
-// GET /api/v1/posts?page=3&limit=20
-// ❌ TRAP: OFFSET 100000 scans and discards 100K rows — degrades badly at scale
-```
-
----
-
-## Idempotency
-
-```typescript
-// POST /api/v1/payments with header: Idempotency-Key: <uuid>
-app.post("/api/v1/payments", async (req, res) => {
-  const key = req.headers["idempotency-key"];
-  if (!key) return res.status(400).json({ error: "Missing Idempotency-Key" });
-
-  const cached = await redis.get(`idempotency:${key}`);
-  if (cached) return res.status(200).json(JSON.parse(cached));
-
-  const result = await processPayment(req.body);
-  await redis.set(`idempotency:${key}`, JSON.stringify(result), "EX", 86400);
-  return res.status(201).json(result);
-});
-// GET, PUT, DELETE → naturally idempotent (safe to retry without a key)
-// POST, PATCH      → NOT idempotent by default — require Idempotency-Key
-```
-
----
-
-## Webhooks
-
-```typescript
-// HMAC signature verification (always verify — never trust unsigned webhooks)
-import { createHmac, timingSafeEqual } from "node:crypto";
-function verify(payload: string, signature: string, secret: string): boolean {
-  const expected = createHmac("sha256", secret).update(payload).digest("hex");
-  return timingSafeEqual(Buffer.from(signature), Buffer.from(expected));
-}
-
-app.post("/webhooks", (req, res) => {
-  if (!verify(JSON.stringify(req.body), req.headers["x-webhook-signature"] as string, WEBHOOK_SECRET))
-    return res.status(401).send("Invalid signature");
-  res.status(200).send("OK"); // respond immediately
-  processWebhookAsync(req.body); // process asynchronously
-});
-// Retry policy: 3 retries with exponential backoff (1s → 10s → 100s)
-// Include unique event ID in payload for receiver-side deduplication
-```
-
----
-
-## Versioning
-
-```
-URL path (recommended):  /api/v1/users      → simplest, most common, cache-friendly
-Header:                  Accept: application/vnd.api.v1+json
-Query param:             /api/users?version=1 → messy, avoid
-
-Rules:
-  - Start at v1, never v0
-  - Breaking changes = new major version (v2)
-  - Non-breaking additions (new optional fields) do NOT need a version bump
-  - Deprecate before removing — give consumers 6+ months notice
-```
-
----
-
-## Rate Limiting
-
-```
-Strategy         How                          When
-Token bucket   → Burst allowed, refills       Most APIs (recommended)
-Sliding window → Smooth distribution          Strict fairness required
-Fixed window   → Simple counter per period    Basic needs only
-
-Response headers to always include:
-  X-RateLimit-Limit        (max requests in window)
-  X-RateLimit-Remaining    (requests left)
-  X-RateLimit-Reset        (Unix timestamp when limit resets)
-  Retry-After              (seconds to wait on 429)
-```
-
----
-
-## GraphQL Security
-
-```
-Protect against:
-  Depth attacks    → Set max query depth (typically 7–10)
-  Cost attacks     → Calculate query complexity score, reject > threshold
-  Batch abuse      → Limit batch size / alias count
-  Introspection    → Disable in production (exposes full schema to attackers)
-```
-
----
-
-## Authentication Selection
-
-| Pattern | Best For |
-|---------|----------|
-| **JWT** (short-lived access + httpOnly refresh) | Stateless services, microservices |
-| **Session** | Traditional server-rendered apps |
-| **OAuth 2.0 / OIDC** | Third-party login, delegated access |
-| **API Key** | Server-to-server, public API consumers |
-| **Passkey (WebAuthn)** | Modern passwordless (2026+) |
+---
+name: api-patterns
+description: API design mastery. REST, GraphQL, tRPC, and gRPC selection. Request/response design, pagination (cursor/offset), filtering, versioning, rate limiting, error formats (RFC 9457), authentication (JWT/OAuth2/API keys), idempotency, file uploads, webhooks, and OpenAPI documentation. Use when designing APIs, choosing protocols, or implementing API standards.
+allowed-tools: Read, Write, Edit, Glob, Grep
+version: 3.1.0
+last-updated: 2026-04-07
+applies-to-model: gemini-3-1-pro, claude-3-7-sonnet
+---
+
+# API Patterns — Design & Protocol Mastery
+
+## Hallucination Traps (Read First)
+- ❌ JWT in URL query params → ✅ `Authorization: Bearer` header only. Query params get logged in server access logs.
+- ❌ Assuming JWT is encrypted → ✅ JWT is base64-encoded (NOT encrypted). Anyone can decode it. Never put secrets/PII in the payload.
+- ❌ Offset pagination on large tables → ✅ `OFFSET 100000` scans and discards 100K rows. Use cursor pagination for tables > 10K rows.
+- ❌ Verbs in REST URLs (`/api/getUsers`) → ✅ Nouns only (`GET /api/users`). HTTP method IS the verb.
+- ❌ `POST` is idempotent → ✅ `POST` is NOT idempotent — requires `Idempotency-Key` header for safe retries.
+- ❌ GraphQL has no security risks → ✅ Deeply nested queries are a DoS vector. Set max depth, query cost limits. Disable introspection in production.
+
+---
+
+## Protocol Selection Matrix
+
+| Protocol | Use When |
+|----------|----------|
+| **REST** | Public APIs, 3rd-party consumers, standard CRUD, HTTP caching |
+| **GraphQL** | Complex nested data, multiple clients, flexible queries, mobile bandwidth sensitivity |
+| **tRPC** | Full-stack TypeScript (Next.js monorepo), shared types, no codegen |
+| **gRPC** | Internal microservices, high-throughput, streaming, binary protocol |
+| **WebSocket** | Bidirectional real-time (chat, gaming, live collaboration) |
+| **SSE** | Server-to-client streaming only (AI token streaming, live feeds) |
+
+---
+
+## REST Design
+
+### URL Conventions
+```
+✅  GET    /api/v1/users              list users
+✅  GET    /api/v1/users/123          get user by ID
+✅  POST   /api/v1/users              create user
+✅  PATCH  /api/v1/users/123          partial update
+✅  DELETE /api/v1/users/123          delete user
+✅  GET    /api/v1/users/123/posts    nested resource
+
+❌  /api/getUsers   /api/createUser   /api/user (singular)   /api/Users (uppercase)
+```
+
+### HTTP Status Codes
+```
+200 OK             → GET / PUT / PATCH success
+201 Created        → POST success (include Location: /api/v1/users/123 header)
+204 No Content     → DELETE success
+400 Bad Request    → Malformed request / missing fields
+401 Unauthorized   → Missing or invalid authentication
+403 Forbidden      → Authenticated but not authorized
+404 Not Found      → Resource does not exist
+409 Conflict       → Duplicate resource (email already exists)
+422 Unprocessable  → Valid JSON, semantically invalid data
+429 Too Many Req   → Rate limit exceeded
+500 Internal       → Unhandled server error — NEVER expose stack traces
+```
+
+### Response Envelope
+```typescript
+interface ApiResponse<T> { data: T; meta?: Record<string, unknown>; }
+
+interface ApiError {
+  error: {
+    code: string;       // machine-readable: "VALIDATION_ERROR"
+    message: string;    // human-readable: "Email is already in use"
+    details?: Array<{ field: string; message: string }>; // field-level errors
+    requestId?: string; // for support/tracing
+  };
+}
+```
+
+---
+
+## Pagination
+
+```typescript
+// ✅ Cursor-based — required for large/dynamic datasets
+// GET /api/v1/posts?cursor=eyJpZCI6MTAwfQ&limit=20
+const posts = await db.post.findMany({
+  where: { id: { lt: decodeCursor(req.query.cursor).id } },
+  orderBy: { id: "desc" },
+  take: limit + 1, // fetch one extra to determine hasMore
+});
+const hasMore = posts.length > limit;
+if (hasMore) posts.pop();
+return { data: posts, meta: { hasMore, nextCursor: encodeCursor(posts.at(-1)) } };
+
+// Offset-based — only for small datasets where users need page jumping
+// GET /api/v1/posts?page=3&limit=20
+// ❌ TRAP: OFFSET 100000 scans and discards 100K rows — degrades badly at scale
+```
+
+---
+
+## Idempotency
+
+```typescript
+// POST /api/v1/payments with header: Idempotency-Key: <uuid>
+app.post("/api/v1/payments", async (req, res) => {
+  const key = req.headers["idempotency-key"];
+  if (!key) return res.status(400).json({ error: "Missing Idempotency-Key" });
+
+  const cached = await redis.get(`idempotency:${key}`);
+  if (cached) return res.status(200).json(JSON.parse(cached));
+
+  const result = await processPayment(req.body);
+  await redis.set(`idempotency:${key}`, JSON.stringify(result), "EX", 86400);
+  return res.status(201).json(result);
+});
+// GET, PUT, DELETE → naturally idempotent (safe to retry without a key)
+// POST, PATCH      → NOT idempotent by default — require Idempotency-Key
+```
+
+---
+
+## Webhooks
+
+```typescript
+// HMAC signature verification (always verify — never trust unsigned webhooks)
+import { createHmac, timingSafeEqual } from "node:crypto";
+function verify(payload: string, signature: string, secret: string): boolean {
+  const expected = createHmac("sha256", secret).update(payload).digest("hex");
+  return timingSafeEqual(Buffer.from(signature), Buffer.from(expected));
+}
+
+app.post("/webhooks", (req, res) => {
+  if (!verify(JSON.stringify(req.body), req.headers["x-webhook-signature"] as string, WEBHOOK_SECRET))
+    return res.status(401).send("Invalid signature");
+  res.status(200).send("OK"); // respond immediately
+  processWebhookAsync(req.body); // process asynchronously
+});
+// Retry policy: 3 retries with exponential backoff (1s → 10s → 100s)
+// Include unique event ID in payload for receiver-side deduplication
+```
+
+---
+
+## Versioning
+
+```
+URL path (recommended):  /api/v1/users      → simplest, most common, cache-friendly
+Header:                  Accept: application/vnd.api.v1+json
+Query param:             /api/users?version=1 → messy, avoid
+
+Rules:
+  - Start at v1, never v0
+  - Breaking changes = new major version (v2)
+  - Non-breaking additions (new optional fields) do NOT need a version bump
+  - Deprecate before removing — give consumers 6+ months notice
+```
+
+---
+
+## Rate Limiting
+
+```
+Strategy         How                          When
+Token bucket   → Burst allowed, refills       Most APIs (recommended)
+Sliding window → Smooth distribution          Strict fairness required
+Fixed window   → Simple counter per period    Basic needs only
+
+Response headers to always include:
+  X-RateLimit-Limit        (max requests in window)
+  X-RateLimit-Remaining    (requests left)
+  X-RateLimit-Reset        (Unix timestamp when limit resets)
+  Retry-After              (seconds to wait on 429)
+```
+
+---
+
+## GraphQL Security
+
+```
+Protect against:
+  Depth attacks    → Set max query depth (typically 7–10)
+  Cost attacks     → Calculate query complexity score, reject > threshold
+  Batch abuse      → Limit batch size / alias count
+  Introspection    → Disable in production (exposes full schema to attackers)
+```
+
+---
+
+## Authentication Selection
+
+| Pattern | Best For |
+|---------|----------|
+| **JWT** (short-lived access + httpOnly refresh) | Stateless services, microservices |
+| **Session** | Traditional server-rendered apps |
+| **OAuth 2.0 / OIDC** | Third-party login, delegated access |
+| **API Key** | Server-to-server, public API consumers |
+| **Passkey (WebAuthn)** | Modern passwordless (2026+) |
 
 
 ---
@@ -236,4 +236,12 @@ Review these questions before confirming output:
 
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+
+
+## Pre-Flight Checklist
+- [ ] Have I reviewed the user's specific constraints and requests?
+- [ ] Have I checked the environment for relevant existing implementations?
+
+## VBC Protocol (Verification-Before-Completion)
+You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.

package/.agent/skills/api-security-auditor/SKILL.md

@@ -182,4 +182,12 @@ Review these questions before confirming output:
 
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+
+
+## Pre-Flight Checklist
+- [ ] Have I reviewed the user's specific constraints and requests?
+- [ ] Have I checked the environment for relevant existing implementations?
+
+## VBC Protocol (Verification-Before-Completion)
+You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.

package/.agent/skills/app-builder/SKILL.md

@@ -561,4 +561,12 @@ Review these questions before confirming output:
 
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+
+
+## Pre-Flight Checklist
+- [ ] Have I reviewed the user's specific constraints and requests?
+- [ ] Have I checked the environment for relevant existing implementations?
+
+## VBC Protocol (Verification-Before-Completion)
+You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.

package/.agent/skills/app-builder/templates/SKILL.md

@@ -35,73 +35,81 @@ allowed-tools: Read, Glob, Grep
 2. Match to appropriate template
 3. Read ONLY that template's TEMPLATE.md
 4. Follow its tech stack and structure
-
----
-
-## 🚨 LLM Trap Table
-
-|Pattern|What AI Does Wrong|What Is Actually Correct|
-|:---|:---|:---|
-|[domain-specific trap 1]|[hallucination]|[correct behavior]|
-|[domain-specific trap 2]|[hallucination]|[correct behavior]|
-|[domain-specific trap 3]|[hallucination]|[correct behavior]|
-
----
-
-## ✅ Pre-Flight Self-Audit
-
-Before producing any output, verify:
-``
-✅ Did I read the actual files before making claims about them?
-✅ Did I verify all method names against official documentation?
-✅ Did I add // VERIFY: on any uncertain API calls?
-✅ Are all imports from packages that actually exist in package.json?
-✅ Did I test my logic with edge cases (null, empty, 0, max)?
-✅ Did I avoid generating code for more than one module at a time?
-✅ Am I working from evidence, not assumption?
-``
-
----
-
-## 🔁 VBC Protocol (Verify → Build → Confirm)
-
-``
-VERIFY:  Read the actual codebase before writing anything
-BUILD:   Generate the smallest meaningful unit of code
-CONFIRM: Verify the output is correct before presenting
+
+---
+
+## 🚨 LLM Trap Table
+
+|Pattern|What AI Does Wrong|What Is Actually Correct|
+|:---|:---|:---|
+|[domain-specific trap 1]|[hallucination]|[correct behavior]|
+|[domain-specific trap 2]|[hallucination]|[correct behavior]|
+|[domain-specific trap 3]|[hallucination]|[correct behavior]|
+
+---
+
+## ✅ Pre-Flight Self-Audit
+
+Before producing any output, verify:
+``
+✅ Did I read the actual files before making claims about them?
+✅ Did I verify all method names against official documentation?
+✅ Did I add // VERIFY: on any uncertain API calls?
+✅ Are all imports from packages that actually exist in package.json?
+✅ Did I test my logic with edge cases (null, empty, 0, max)?
+✅ Did I avoid generating code for more than one module at a time?
+✅ Am I working from evidence, not assumption?
+``
+
+---
+
+## 🔁 VBC Protocol (Verify → Build → Confirm)
+
+``
+VERIFY:  Read the actual codebase before writing anything
+BUILD:   Generate the smallest meaningful unit of code
+CONFIRM: Verify the output is correct before presenting
+``
+
+---
+
+## 🚨 LLM Trap Table
+
+|Pattern|What AI Does Wrong|What Is Actually Correct|
+|:---|:---|:---|
+|[domain-specific trap 1]|[hallucination]|[correct behavior]|
+|[domain-specific trap 2]|[hallucination]|[correct behavior]|
+|[domain-specific trap 3]|[hallucination]|[correct behavior]|
+
+---
+
+## ✅ Pre-Flight Self-Audit
+
+Before producing any output, verify:
 ``
-
----
-
-## 🚨 LLM Trap Table
-
-|Pattern|What AI Does Wrong|What Is Actually Correct|
-|:---|:---|:---|
-|[domain-specific trap 1]|[hallucination]|[correct behavior]|
-|[domain-specific trap 2]|[hallucination]|[correct behavior]|
-|[domain-specific trap 3]|[hallucination]|[correct behavior]|
-
----
-
-## ✅ Pre-Flight Self-Audit
-
-Before producing any output, verify:
-``
-✅ Did I read the actual files before making claims about them?
-✅ Did I verify all method names against official documentation?
-✅ Did I add // VERIFY: on any uncertain API calls?
-✅ Are all imports from packages that actually exist in package.json?
-✅ Did I test my logic with edge cases (null, empty, 0, max)?
-✅ Did I avoid generating code for more than one module at a time?
-✅ Am I working from evidence, not assumption?
-``
-
----
-
-## 🔁 VBC Protocol (Verify → Build → Confirm)
-
-``
-VERIFY:  Read the actual codebase before writing anything
-BUILD:   Generate the smallest meaningful unit of code
-CONFIRM: Verify the output is correct before presenting
-``
+✅ Did I read the actual files before making claims about them?
+✅ Did I verify all method names against official documentation?
+✅ Did I add // VERIFY: on any uncertain API calls?
+✅ Are all imports from packages that actually exist in package.json?
+✅ Did I test my logic with edge cases (null, empty, 0, max)?
+✅ Did I avoid generating code for more than one module at a time?
+✅ Am I working from evidence, not assumption?
+``
+
+---
+
+## 🔁 VBC Protocol (Verify → Build → Confirm)
+
+``
+VERIFY:  Read the actual codebase before writing anything
+BUILD:   Generate the smallest meaningful unit of code
+CONFIRM: Verify the output is correct before presenting
+``
+
+
+## Pre-Flight Checklist
+- [ ] Have I reviewed the user's specific constraints and requests?
+- [ ] Have I checked the environment for relevant existing implementations?
+
+## VBC Protocol (Verification-Before-Completion)
+You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.

package/.agent/skills/appflow-wireframe/SKILL.md

@@ -134,4 +134,12 @@ Review these questions before confirming output:
 
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+
+
+## Pre-Flight Checklist
+- [ ] Have I reviewed the user's specific constraints and requests?
+- [ ] Have I checked the environment for relevant existing implementations?
+
+## VBC Protocol (Verification-Before-Completion)
+You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.

package/.agent/skills/architecture/SKILL.md

@@ -208,4 +208,12 @@ Review these questions before confirming output:
 
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+
+
+## Pre-Flight Checklist
+- [ ] Have I reviewed the user's specific constraints and requests?
+- [ ] Have I checked the environment for relevant existing implementations?
+
+## VBC Protocol (Verification-Before-Completion)
+You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.

package/.agent/skills/authentication-best-practices/SKILL.md

@@ -178,4 +178,12 @@ Review these questions before confirming output:
 
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+
+
+## Pre-Flight Checklist
+- [ ] Have I reviewed the user's specific constraints and requests?
+- [ ] Have I checked the environment for relevant existing implementations?
+
+## VBC Protocol (Verification-Before-Completion)
+You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.

package/.agent/skills/bash-linux/SKILL.md

@@ -168,4 +168,12 @@ Review these questions before confirming output:
 
 **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
 - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
-- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
+
+
+## Pre-Flight Checklist
+- [ ] Have I reviewed the user's specific constraints and requests?
+- [ ] Have I checked the environment for relevant existing implementations?
+
+## VBC Protocol (Verification-Before-Completion)
+You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.