nitm-ai-dev-toolkit 3.0.15

package/src/monorepo/.opencode/agents/refactor.md

@@ -0,0 +1,14 @@
+---
+description: "Improve code quality and structure while keeping all tests passing. Part of the TDD red-green-refactor cycle."
+mode: subagent
+temperature: 0.1
+permission:
+  edit: allow
+  bash: allow
+---
+
+# Refactor Agent (TDD — Improve Code Quality)
+
+Improve code quality and structure while keeping all tests passing. Part of the TDD red-green-refactor cycle.
+
+@.claude/agents-snippets/refactor.md

package/src/monorepo/.opencode/agents/researcher.md

@@ -0,0 +1,14 @@
+---
+description: "Research codebase patterns, dependencies, and technical context. Analyze code structure, find relevant examples, and report findings without making changes."
+mode: subagent
+temperature: 0.1
+permission:
+  edit: deny
+  bash: deny
+---
+
+# Researcher Agent
+
+Research codebase patterns, dependencies, and technical context. Analyze code structure, find relevant examples, and report findings without making changes.
+
+@.claude/agents-snippets/researcher.md

package/src/monorepo/.opencode/agents/reviewer.md

@@ -0,0 +1,14 @@
+---
+description: "Review code changes for correctness, code quality, security, and adherence to project patterns. Provide actionable feedback with specific file and line references. Use immediately after writing or modifying code, or as a quality gate in orchestrated workflows."
+mode: subagent
+temperature: 0.1
+permission:
+  edit: deny
+  bash: allow
+---
+
+# Reviewer Agent
+
+Review code changes for correctness, code quality, security, and adherence to project patterns.
+
+@.claude/agents-snippets/reviewer.md

package/src/monorepo/.opencode/agents/tdd.md

@@ -0,0 +1,15 @@
+---
+description: "Implement a feature using test-driven development with red-green-refactor cycle. Coordinates specialized subagents for writing failing tests, implementing code, and refactoring."
+mode: subagent
+temperature: 0.3
+permission:
+  edit: allow
+  bash: allow
+  task: allow
+---
+
+# TDD Coordinator Agent
+
+Implement a feature using test-driven development with red-green-refactor cycle.
+
+@.claude/agents-snippets/tdd.md

package/src/monorepo/.opencode/commands/assign-tasks.md

@@ -0,0 +1,16 @@
+---
+description: "Create {{ISSUE_TRACKER}} tickets from requirements or task files"
+---
+
+# Assign Tasks
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Task assignment and execution
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/assign-tasks.md

package/src/monorepo/.opencode/commands/bootstrap-patch.md

@@ -0,0 +1,18 @@
+---
+description: "Patch AI instructions by fetching updates from the toolkit repo and applying new/updated/missing guidance"
+---
+
+# Patch AI Instructions
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Standard patch — incremental changes to existing config |
+| `planner` | Complex patch — cross-cutting changes needing analysis first |
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/bootstrap-patch.md

package/src/monorepo/.opencode/commands/bootstrap-upgrade.md

@@ -0,0 +1,18 @@
+---
+description: "Upgrade AI instructions from pre-3.0 inline pattern to 3.0+ snippet architecture"
+---
+
+# Bootstrap Upgrade
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Standard upgrade — version bump and migration |
+| `planner` | Complex upgrade — breaking changes needing dependency analysis |
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/bootstrap-upgrade.md

package/src/monorepo/.opencode/commands/bootstrap.md

@@ -0,0 +1,18 @@
+---
+description: "Bootstrap AI instructions for monorepo by analyzing workspace and customizing templates"
+---
+
+# Bootstrap Monorepo AI Instructions
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Standard bootstrap — project analysis and template customization |
+| `planner` | Complex bootstrap — needs requirements gathering and architecture decisions first |
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/bootstrap.md

package/src/monorepo/.opencode/commands/commit-push.md

@@ -0,0 +1,16 @@
+---
+description: "Commit and push changes with conventional commit messages"
+---
+
+# Commit & Push
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Git operations, execution-focused
+
+Commit and push changes using conventional commit format.
+
+@.claude/prompt-snippets/commit-push.md
+
+$ARGUMENTS

package/src/monorepo/.opencode/commands/constitution.md

@@ -0,0 +1,18 @@
+---
+description: "Create or update the project constitution defining core principles and guidelines"
+---
+
+# Project Constitution
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `oracle` | Project principles and governance — architectural decisions |
+| `planner` | Project conventions and standards — team norms and practices |
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/constitution.md

package/src/monorepo/.opencode/commands/create-skill.md

@@ -0,0 +1,16 @@
+---
+description: "Create a new agent skill following VS Code and agentskills.io specifications"
+---
+
+# Create Skill
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Skill file creation
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/create-skill.md

package/src/monorepo/.opencode/commands/implement-feature.md

@@ -0,0 +1,18 @@
+---
+description: "Implement a feature by completing tasks sequentially"
+---
+
+# Implement Feature
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Bounded feature work — spec is clear, files are known |
+| `feature-builder` | Complex feature — needs research, planning, and coordination |
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/implement-feature.md

package/src/monorepo/.opencode/commands/implement-fixes.md

@@ -0,0 +1,20 @@
+---
+description: Implement bug fixes with proper tracking and validation
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: "bug description or fix requirements"
+---
+
+# Implement Fixes
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Bounded fixes — clear root cause, known scope |
+| `oracle` | Ambiguous fixes — root cause unclear, needs investigation first |
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/implement-fixes.md

package/src/monorepo/.opencode/commands/implement.md

@@ -0,0 +1,18 @@
+---
+description: "Execute implementation tasks from a task list or specification"
+---
+
+# Execute Implementation Tasks
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Bounded implementation — clear spec, known target |
+| `oracle` | Ambiguous implementation — needs architectural judgment first |
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/implement.md

package/src/monorepo/.opencode/commands/plan.md

@@ -0,0 +1,18 @@
+---
+description: "Create an implementation plan from a feature specification or requirement"
+---
+
+# Create Implementation Plan
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `planner` | Standard implementation plan — breaking work into tasks |
+| `oracle` | Architectural planning — trade-offs, system design, risk analysis |
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/plan.md

package/src/monorepo/.opencode/commands/playwright-test.md

@@ -0,0 +1,16 @@
+---
+description: "Run or create E2E tests using Playwright"
+---
+
+# Playwright E2E Tests
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Test generation and execution
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/playwright-test.md

package/src/monorepo/.opencode/commands/ponytail-audit.md

@@ -0,0 +1,10 @@
+---
+description: "Whole-repo audit for over-engineering. Scans entire codebase for what to delete, simplify, replace."
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `oracle`
+> Whole-repo over-engineering analysis
+
+@.claude/prompt-snippets/ponytail-audit.md

package/src/monorepo/.opencode/commands/ponytail-debt.md

@@ -0,0 +1,10 @@
+---
+
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Debt ledger harvesting
+
+@.claude/prompt-snippets/ponytail-debt.md

package/src/monorepo/.opencode/commands/ponytail-gain.md

@@ -0,0 +1,10 @@
+---
+
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Impact scoreboard display
+
+@.claude/prompt-snippets/ponytail-gain.md

package/src/monorepo/.opencode/commands/ponytail-help.md

@@ -0,0 +1,10 @@
+---
+
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Quick-reference display
+
+@.claude/prompt-snippets/ponytail-help.md

package/src/monorepo/.opencode/commands/ponytail-review.md

@@ -0,0 +1,10 @@
+---
+
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `oracle`
+> Diff-level over-engineering review
+
+@.claude/prompt-snippets/ponytail-review.md

package/src/monorepo/.opencode/commands/ponytail.md

@@ -0,0 +1,10 @@
+---
+description: "Forces the laziest solution that actually works — YAGNI, stdlib, native, one-line, minimum."
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Apply YAGNI/stdlib discipline
+
+@.claude/prompt-snippets/ponytail.md

package/src/monorepo/.opencode/commands/release-notes.md

@@ -0,0 +1,16 @@
+---
+description: "Generate release notes from git commits (web, git tag, or documentation)"
+---
+
+# Generate Release Notes
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Release notes generation
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/release-notes.md

package/src/monorepo/.opencode/commands/review-pr.md

@@ -0,0 +1,18 @@
+---
+description: "Conduct comprehensive pull request code review"
+---
+
+# PR Review
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `reviewer` | Standard PR review — correctness, test coverage, patterns |
+| `oracle` | Complex PR review — architecture, security, cross-system impact |
+
+Conduct comprehensive code review for pull requests.
+
+@.claude/prompt-snippets/review-pr.md
+
+$ARGUMENTS

package/src/monorepo/.opencode/commands/review-staged.md

@@ -0,0 +1,11 @@
+---
+description: "Review currently staged files before committing"
+---
+
+# Review Staged Files
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `reviewer` | Standard pre-commit review — correctness, style, patterns |
+| `oracle` | Complex staged change — trade-offs, security, scalability |

package/src/monorepo/.opencode/commands/review.md

@@ -0,0 +1,18 @@
+---
+description: "Conduct code review for files or features"
+---
+
+# Code Review
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `reviewer` | Standard code review — correctness, style, patterns |
+| `oracle` | Complex architectural review — trade-offs, security, scalability |
+
+Review code for quality, security, and adherence to project patterns.
+
+@.claude/prompt-snippets/review.md
+
+$ARGUMENTS

package/src/monorepo/.opencode/commands/specify.md

@@ -0,0 +1,18 @@
+---
+description: "Create a feature specification from a natural language description"
+---
+
+# Create Feature Specification
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `planner` | Standard feature specification — requirements and acceptance criteria |
+| `oracle` | Complex specification — cross-system design, API contracts, security |
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/specify.md

package/src/monorepo/.opencode/commands/tasks.md

@@ -0,0 +1,16 @@
+---
+description: "Generate an actionable task list from a specification or plan"
+---
+
+# Generate Task List
+
+## Agent Dispatch
+
+> **Recommended agent:** `planner`
+> Task breakdown and management
+
+## Arguments
+
+$ARGUMENTS
+
+@.claude/prompt-snippets/tasks.md

package/src/monorepo/.opencode/opencode.json

@@ -0,0 +1,9 @@
+{
+	"$schema": "https://opencode.ai/config.json",
+	"instructions": ["AGENTS.md", ".opencode/rules/*.md", ".agents/skills/orient-to-recent-work/SKILL.md"],
+	"skills": {
+		"paths": [".agents/skills/**/*.md", ".claude/skills/**/*.md"]
+	},
+	"plugin": [".opencode/plugins/ponytail.mjs"],
+	"lsp": true
+}

package/src/monorepo/.opencode/plugins/ponytail.mjs

@@ -0,0 +1,79 @@
+// ponytail — OpenCode plugin.
+//
+// Injects the ponytail ruleset into every chat's system prompt at the active
+// intensity, and persists /ponytail mode switches. Reuses the shared instruction
+// builder so Claude Code, Codex, pi, and OpenCode all read one source of truth.
+//
+// OpenCode loads this as a server plugin — add it to your opencode.json:
+//   { "plugin": ["./.opencode/plugins/ponytail.mjs"] }
+
+import { createRequire } from 'module';
+import fs from 'fs';
+import os from 'os';
+import path from 'path';
+import { fileURLToPath } from 'url';
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+
+// The shared instruction builder is CommonJS; bridge to it from this ES module.
+const require = createRequire(import.meta.url);
+const { getPonytailInstructions } = require('../../hooks/ponytail-instructions');
+const { getDefaultMode, normalizePersistedMode } = require('../../hooks/ponytail-config');
+
+// OpenCode has no flag-file convention of its own; keep mode beside its config.
+const statePath = path.join(
+  process.env.XDG_CONFIG_HOME || path.join(os.homedir(), '.config'),
+  'opencode',
+  '.ponytail-active',
+);
+
+function readMode() {
+  try {
+    return normalizePersistedMode(fs.readFileSync(statePath, 'utf8').trim()) || getDefaultMode();
+  } catch (e) {
+    return getDefaultMode();
+  }
+}
+
+function writeMode(mode) {
+  fs.mkdirSync(path.dirname(statePath), { recursive: true });
+  fs.writeFileSync(statePath, mode);
+}
+
+export default async ({ client } = {}) => {
+  const log = (level, message) => {
+    try { client && client.app && client.app.log({ body: { service: 'ponytail', level, message } }); } catch (e) {}
+  };
+
+  const ponytailSkillsDir = path.resolve(__dirname, '../../.agents/skills');
+
+  return {
+    // Register skills directory so opencode discovers ponytail skills.
+    config: async (config) => {
+      config.skills = config.skills || {};
+      config.skills.paths = config.skills.paths || [];
+      if (!config.skills.paths.includes(ponytailSkillsDir)) {
+        config.skills.paths.push(ponytailSkillsDir);
+      }
+    },
+
+    // Append the ruleset to the system prompt every turn.
+    'experimental.chat.system.transform': async (_input, output) => {
+      const mode = readMode();
+      if (mode === 'off') return;
+      output.system.push(getPonytailInstructions(mode));
+    },
+
+    // Persist `/ponytail <level>` so the next turn's injection follows it.
+    // ponytail: mode applies from the next message, not the current one — the
+    // transform reads the flag the command writes. Good enough; switch to a
+    // synchronous store if same-turn switching ever matters.
+    'command.execute.before': async (input) => {
+      if (!input || input.command !== 'ponytail') return;
+      // `off` is persisted like any mode; the transform reads it and stays silent.
+      const mode = normalizePersistedMode((input.arguments || '').trim()) || getDefaultMode();
+      writeMode(mode);
+      log('info', 'ponytail ' + mode);
+    },
+  };
+};

package/src/monorepo/.opencode/rules/agent-conduct.md

@@ -0,0 +1,12 @@
+# Agent Conduct
+
+Agent conduct and clarification rules for ambiguous requirements.
+
+@.claude/rules-snippets/agent-conduct.md
+
+## Key points
+
+- Use coordinator agents for non-trivial multi-step tasks (orchestration checkpoint).
+- Ask for clarification on ambiguous requirements before making assumptions.
+- Never silently change database schemas, API contracts, or authentication flows.
+- Never modify shared packages without considering downstream consumers in the monorepo.

package/src/monorepo/.opencode/rules/api-server.md

@@ -0,0 +1,11 @@
+# API & Server
+
+API and server-side development standards.
+
+@.claude/rules-snippets/api-server.md
+
+## Key points
+
+- Follow {{API_ROUTE_PATTERN}} for API route conventions.
+- Validate all input data before processing.
+- Return consistent response formats with proper HTTP status codes.

package/src/monorepo/.opencode/rules/coding-standards.md

@@ -0,0 +1,11 @@
+# Coding Standards
+
+Coding standards and language conventions.
+
+@.claude/rules-snippets/coding-standards.md
+
+## Key points
+
+- All code must follow {{LANGUAGE}} type safety rules and {{FRAMEWORK}} conventions.
+- Keep functions focused and manageable (under 50-75 lines).
+- Use try-catch for async operations; leverage {{FRAMEWORK}} error utilities.

package/src/monorepo/.opencode/rules/component-structure.md

@@ -0,0 +1,11 @@
+# Component Structure
+
+Component structure and composition patterns.
+
+@.claude/rules-snippets/component-structure.md
+
+## Key points
+
+- Follow the {{COMPONENT_PATTERN}} pattern for all components.
+- Use clear and descriptive naming for props, events, and methods.
+- Use bracketed identifiers for logs: `[ComponentName]: message`.

package/src/monorepo/.opencode/rules/core-libraries.md

@@ -0,0 +1,11 @@
+# Core Libraries
+
+Core library and framework usage conventions.
+
+@.claude/rules-snippets/core-libraries.md
+
+## Key points
+
+- Use {{UTILITY_LIBRARY}} for common utilities and {{STATE_MANAGEMENT}} for state.
+- Use {{STYLING}} for styling; prefer utility classes over custom CSS.
+- Use {{UI_LIBRARY}} for UI components; check existing components before creating new ones.

package/src/monorepo/.opencode/rules/environment-tooling.md

@@ -0,0 +1,11 @@
+# Environment & Tooling
+
+Environment and tooling configuration.
+
+@.claude/rules-snippets/environment-tooling.md
+
+## Key points
+
+- Tailor commands to the user's OS and shell.
+- Use `{{PACKAGE_MANAGER}}` for package management.
+- Follow project-specific tooling rules for linting and formatting.

package/src/monorepo/.opencode/rules/logging-comments.md

@@ -0,0 +1,11 @@
+# Logging & Comments
+
+Logging identifiers and code comment conventions.
+
+@.claude/rules-snippets/logging-comments.md
+
+## Key points
+
+- Comment complex logic and non-obvious implementations.
+- Use bracketed identifiers for logs: `[ModuleName]: message`.
+- Remove debug logs before committing to main branch.

package/src/monorepo/.opencode/rules/logging.md

@@ -0,0 +1,11 @@
+# Logging Standards
+
+Structured logging standards and best practices.
+
+@.claude/rules-snippets/logging.md
+
+## Key points
+
+- Include app or package context in all log messages: `[App:Name]` or `[Pkg:Name]`.
+- Use appropriate log levels: error, warn, info, debug.
+- Never log passwords, API keys, tokens, or PII — sanitize before logging.

package/src/monorepo/.opencode/rules/ponytail.md

@@ -0,0 +1,3 @@
+# Ponytail, lazy senior dev mode
+
+Full content: [.claude/rules-snippets/ponytail.md](../../.claude/rules-snippets/ponytail.md)