@nolrm/contextkit 0.10.0 → 0.12.3

package/README.md

@@ -2,7 +2,7 @@
 
 > Context Engineering for AI Development
 
-Give your AI assistants (Cursor, Claude, Copilot, Codex, Gemini, Aider, Continue, Windsurf) structured context through markdown files. ContextKit creates a knowledge base that ensures AI generates code matching your exact patterns, style, and architecture—no more hallucinated code or mismatched conventions.
+Give your AI assistants (Cursor, Claude, Copilot, Codex, OpenCode, Gemini, Aider, Continue, Windsurf) structured context through markdown files. ContextKit creates a knowledge base that ensures AI generates code matching your exact patterns, style, and architecture—no more hallucinated code or mismatched conventions.
 
 ContextKit is a CLI tool that provides **context-engineering** capabilities by creating `.contextkit/` directories with project standards, guidelines, and patterns that AI assistants read automatically.
 
@@ -21,7 +21,7 @@ Update `.md` files as your project evolves; the AI follows.
 
 ## Multi-Platform Support
 
-Works with: **Cursor** • **Claude Code** • **GitHub Copilot** • **Codex CLI** • **Gemini CLI** • **Aider** • **Continue** • **Windsurf**
+Works with: **Cursor** • **Claude Code** • **GitHub Copilot** • **Codex CLI** • **OpenCode** • **Gemini CLI** • **Aider** • **Continue** • **Windsurf**
 
 Each platform gets auto-loaded bridge files (`CLAUDE.md`, `AGENTS.md`, `GEMINI.md`, `.windsurfrules`, etc.) so your AI tools read project standards automatically. Claude Code uses `@` imports in CLAUDE.md to load standards content directly into context — no extra token cost from manual file reads.
 
@@ -76,6 +76,7 @@ ck claude      # creates CLAUDE.md + .claude/rules/
 ck cursor      # creates .cursor/rules/ (scoped .mdc files)
 ck copilot     # creates .github/copilot-instructions.md
 ck codex       # creates AGENTS.md
+ck opencode    # creates AGENTS.md
 ck gemini      # creates GEMINI.md + .gemini/settings.json
 ck aider       # creates CONVENTIONS.md + .aider/rules.md
 ck continue    # creates .continue/rules/ + config.yaml
@@ -136,6 +137,11 @@ claude "create checkout flow for customer"
 codex "create checkout flow for customer"
 ```
 
+**OpenCode** — reads `AGENTS.md` automatically
+```bash
+opencode "create checkout flow for customer"
+```
+
 **CLI** (Chat with AI)
 ```bash
 ck ai "create a button"
@@ -161,7 +167,8 @@ ContextKit installs reusable slash commands for supported platforms:
 | `/squad-test` | Write and run tests against acceptance criteria |
 | `/squad-review` | Review the full pipeline and give a verdict |
 | `/squad-batch` | Kick off multiple tasks at once (batch PO specs) |
-| `/squad-run` | Auto-run the remaining pipeline for batch tasks |
+| `/squad-run` | Auto-run the remaining pipeline for batch tasks (sequential) |
+| `/squad-run-agents` | Auto-run the pipeline in parallel using Claude Code agents (Claude Code only) |
 | `/ck` | Health check — verify setup, standards, and integrations |
 
 **Claude Code** — available as `/analyze`, `/review`, etc. in `.claude/commands/`
@@ -207,6 +214,16 @@ For multiple tasks, use batch mode to spec them all up front, then run the full
 # Runs Architect → Dev → Test → Review for each task sequentially
 ```
 
+**Agent mode (Claude Code only):** Use `/squad-run-agents` instead of `/squad-run` to spawn parallel subagents — one per task per phase — so all tasks progress simultaneously rather than one at a time.
+
+```bash
+/squad-batch "add dark mode" "fix login bug" "refactor checkout"
+
+/squad-run-agents
+# Phase 1: architect agents for all 3 tasks run in parallel
+# Phase 2: dev→test→review pipeline runs in parallel per task
+```
+
 ### Feedback Loop
 
 Any downstream role can raise questions for an upstream role. When this happens, the pipeline pauses and directs you to the right command:
@@ -273,7 +290,7 @@ Hooks are optional and can be skipped with `ck install --no-hooks`.
 - 🧠 **Context Engineering** - Structured MD files your AI reads automatically
 - 🔍 **Smart Analysis** - AI generates standards content based on your codebase
 - 🌍 **Project Agnostic** - Works with React, Vue, Node.js, PHP, Python, Rust, monorepos—any project type
-- 🤖 **Multi-Platform** - Works with Cursor, Claude Code, Copilot, Codex, Gemini, Aider, Continue, Windsurf
+- 🤖 **Multi-Platform** - Works with Cursor, Claude Code, Copilot, Codex, OpenCode, Gemini, Aider, Continue, Windsurf
 - 🛡️ **Safe Install** - Backs up existing files with rollback support
 - ⚡ **Zero Config** - Auto-detects project type and package manager
 - ✅ **Policy Enforcement** - Configurable validation with `ck check`
@@ -292,6 +309,7 @@ ck claude      # add Claude Code integration (CLAUDE.md + rules)
 ck cursor      # add Cursor integration (scoped .mdc rules)
 ck copilot     # add GitHub Copilot integration
 ck codex       # add Codex CLI integration (AGENTS.md)
+ck opencode    # add OpenCode integration (AGENTS.md)
 ck gemini      # add Gemini CLI integration (GEMINI.md)
 ck aider       # add Aider integration (CONVENTIONS.md)
 ck continue    # add Continue integration

package/bin/contextkit.js

@@ -275,6 +275,19 @@ program
     }
   });
 
+program
+  .command('opencode')
+  .description('Install OpenCode integration only')
+  .option('--non-interactive', 'Skip interactive prompts')
+  .action(async (options) => {
+    try {
+      await install({ platform: 'opencode', ...options });
+    } catch (error) {
+      console.error(chalk.red('Installation failed:'), error.message);
+      process.exit(1);
+    }
+  });
+
 program
   .command('copilot')
   .description('Install GitHub Copilot integration only')

package/lib/commands/install.js

@@ -127,7 +127,7 @@ class InstallCommand {
 
       if (!integration) {
         console.log(chalk.red(`❌ Unknown platform: ${platform}`));
-        console.log(chalk.yellow('💡 Available: claude, cursor, copilot, codex, gemini, aider, continue, windsurf'));
+        console.log(chalk.yellow('💡 Available: claude, cursor, copilot, codex, opencode, gemini, aider, continue, windsurf'));
         return;
       }
 
@@ -178,6 +178,7 @@ class InstallCommand {
         { name: 'Cursor', value: 'cursor' },
         { name: 'Copilot (GitHub)', value: 'copilot' },
         { name: 'Codex (OpenAI)', value: 'codex' },
+        { name: 'OpenCode', value: 'opencode' },
         { name: 'Gemini', value: 'gemini' },
         { name: 'Windsurf', value: 'windsurf' },
         { name: 'Aider', value: 'aider' },
@@ -597,6 +598,10 @@ Run \`ck analyze\` to generate this content, or manually add your API pattern be
         `${this.repoUrl}/commands/squad-run.md`,
         '.contextkit/commands/squad-run.md'
       );
+      await this.downloadManager.downloadFile(
+        `${this.repoUrl}/commands/squad-run-agents.md`,
+        '.contextkit/commands/squad-run-agents.md'
+      );
 
       // Download hooks (pre-push and commit-msg only, no pre-commit)
       await this.downloadManager.downloadFile(
@@ -1511,7 +1516,7 @@ If standards are still skeletons, warn that @imports in CLAUDE.md are loading em
     console.log(''.padEnd(48, '─'));
     console.log(`ck status    → Check installation & integrations`);
     console.log(`ck ai <cmd>  → Use AI with project context`);
-    console.log(`ck <platform> → Add platform (claude, cursor, copilot, codex, gemini, aider, continue, windsurf)`);
+    console.log(`ck <platform> → Add platform (claude, cursor, copilot, codex, opencode, gemini, aider, continue, windsurf)`);
     console.log('');
     console.log(`Docs → ${chalk.blue('https://contextkit-docs.vercel.app')}`);
     console.log(`Issues → ${chalk.blue('https://github.com/nolrm/contextkit/issues')}`);

package/lib/commands/update.js

@@ -278,6 +278,10 @@ class UpdateCommand {
         `${this.repoUrl}/commands/squad-run.md`,
         '.contextkit/commands/squad-run.md'
       );
+      await this.downloadManager.downloadFile(
+        `${this.repoUrl}/commands/squad-run-agents.md`,
+        '.contextkit/commands/squad-run-agents.md'
+      );
 
       // Download hooks (pre-push and commit-msg only, no pre-commit)
       await this.downloadManager.downloadFile(

package/lib/integrations/claude-integration.js

@@ -24,6 +24,7 @@ class ClaudeIntegration extends BaseIntegration {
       '.claude/commands/squad-review.md',
       '.claude/commands/squad-batch.md',
       '.claude/commands/squad-run.md',
+      '.claude/commands/squad-run-agents.md',
       '.claude/commands/ck.md',
     ];
     this.platformDir = '.claude/rules';
@@ -241,6 +242,13 @@ Create handoff files for multiple tasks and write PO specs for each one. Pass al
 Read \`.contextkit/commands/squad-run.md\` and execute the pipeline runner workflow.
 
 Process all batch tasks through the remaining pipeline steps (Architect, Dev, Test, Review) sequentially.
+`);
+
+    await this.writeGeneratedFile('.claude/commands/squad-run-agents.md', `# Squad Run — Agent Mode (Parallel)
+
+Read \`.contextkit/commands/squad-run-agents.md\` and execute the parallel pipeline workflow.
+
+Spawn one subagent per task per phase using the Task tool, so all tasks progress simultaneously instead of sequentially. Use this after \`/squad-batch\` for faster execution on multi-task batches.
 `);
 
     await this.writeGeneratedFile('.claude/commands/ck.md', `# ContextKit Health Check
@@ -271,8 +279,9 @@ Check project setup, standards status, and integrations. Report what needs atten
     console.log(chalk.dim('    /squad-dev         — Implement the code'));
     console.log(chalk.dim('    /squad-test        — Write and run tests'));
     console.log(chalk.dim('    /squad-review      — Review and write verdict'));
-    console.log(chalk.dim('    /squad-batch       — Batch kickoff: PO specs for multiple tasks'));
-    console.log(chalk.dim('    /squad-run         — Auto-run pipeline for batch tasks'));
+    console.log(chalk.dim('    /squad-batch            — Batch kickoff: PO specs for multiple tasks'));
+    console.log(chalk.dim('    /squad-run              — Auto-run pipeline sequentially'));
+    console.log(chalk.dim('    /squad-run-agents       — Auto-run pipeline in parallel (agent mode)'));
     console.log(chalk.dim(''));
     console.log(chalk.dim('  Health check:'));
     console.log(chalk.dim('    /ck           — Check project setup and standards status'));

package/lib/integrations/index.js

@@ -2,6 +2,7 @@ const ClaudeIntegration = require('./claude-integration');
 const CursorIntegration = require('./cursor-integration');
 const CopilotIntegration = require('./copilot-integration');
 const CodexIntegration = require('./codex-integration');
+const OpencodeIntegration = require('./opencode-integration');
 const GeminiIntegration = require('./gemini-integration');
 const AiderIntegration = require('./aider-integration');
 const ContinueIntegration = require('./continue-integration');
@@ -13,6 +14,7 @@ const INTEGRATIONS = {
   copilot: CopilotIntegration,
   vscode: CopilotIntegration, // backward compat alias
   codex: CodexIntegration,
+  opencode: OpencodeIntegration,
   gemini: GeminiIntegration,
   aider: AiderIntegration,
   continue: ContinueIntegration,
@@ -27,7 +29,7 @@ function getIntegration(name) {
 
 function getAllIntegrationNames() {
   // Return unique names (exclude aliases like vscode)
-  return ['claude', 'cursor', 'copilot', 'codex', 'gemini', 'aider', 'continue', 'windsurf'];
+  return ['claude', 'cursor', 'copilot', 'codex', 'opencode', 'gemini', 'aider', 'continue', 'windsurf'];
 }
 
 module.exports = { getIntegration, getAllIntegrationNames, INTEGRATIONS };

package/lib/integrations/opencode-integration.js

@@ -0,0 +1,45 @@
+const chalk = require('chalk');
+const BaseIntegration = require('./base-integration');
+
+class OpencodeIntegration extends BaseIntegration {
+  constructor() {
+    super();
+    this.name = 'opencode';
+    this.displayName = 'OpenCode';
+    this.bridgeFiles = ['AGENTS.md'];
+    this.generatedFiles = [];
+    this.platformDir = '';
+  }
+
+  async generateFiles() {
+    // Bridge file: AGENTS.md (auto-loaded by OpenCode)
+    const bridgeContent = `# Project Standards (ContextKit)
+
+This project uses [ContextKit](https://github.com/nolrm/contextkit) for AI development standards.
+
+${this.getStandardsBlock()}
+
+## Corrections Log
+
+- \`.contextkit/corrections.md\` — Track AI performance improvements
+
+## Quick Reference
+
+Before writing code, check the relevant standards files above. Always follow the project's established patterns and conventions.`;
+
+    await this.writeBridgeFile('AGENTS.md', bridgeContent);
+  }
+
+  showUsage() {
+    console.log('');
+    console.log(chalk.bold('  OpenCode Usage:'));
+    console.log('    AGENTS.md is auto-loaded by OpenCode');
+    console.log('    Just run: opencode "create a button component"');
+    console.log('    Standards are automatically included via AGENTS.md');
+    console.log('');
+    console.log(chalk.dim('  Files created:'));
+    console.log(chalk.dim('    AGENTS.md (bridge - auto-loaded)'));
+  }
+}
+
+module.exports = OpencodeIntegration;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nolrm/contextkit",
-  "version": "0.10.0",
+  "version": "0.12.3",
   "description": "ContextKit - Context Engineering for AI Development. Provide rich context to AI through structured MD files with standards, code guides, and documentation. Works with Cursor, Claude, Aider, VS Code Copilot, and more.",
   "main": "lib/index.js",
   "bin": {