cli-five 0.2.5 → 0.2.7

package/README.md

@@ -25,12 +25,12 @@ Installs the 5 agents to your Copilot profile. No project config, no interview
 ```
 your-repo/
 ├── .github/
-│   ├── agents/                  # 5 agents with handoffs + subagent delegation
-│   │   ├── orchestrator.agent.md  # 📋 Plan  💻 Code  🎨 Design  🔍 Review
-│   │   ├── planner.agent.md       # 🎯 Execute  💻 Code Directly
-│   │   ├── coder.agent.md         # 🔍 Review  🎯 Back to Orchestrator
-│   │   ├── designer.agent.md      # 🔍 Review  🎯 Back to Orchestrator
-│   │   └── reviewer.agent.md      # 🎯 Back to Orchestrator  💻 Fix Issues
+│   ├── agents/                  # 5 agents — Orchestrator delegates autonomously
+│   │   ├── orchestrator.agent.md  # Routes tasks: Planner → Coder/Designer → Reviewer
+│   │   ├── planner.agent.md       # Researches codebase, produces implementation plans
+│   │   ├── coder.agent.md         # Writes production code, runs tests
+│   │   ├── designer.agent.md      # UI/UX design, layouts, theming
+│   │   └── reviewer.agent.md      # Code review, convention compliance
 │   ├── copilot-instructions.md  # Persona + project mandates from interview
 │   ├── instructions/            # Stack-specific coding guidelines
 │   └── skills/                  # Installed skills from awesome-copilot + skills.sh
@@ -42,14 +42,16 @@ your-repo/
 └── histories/                   # Per-agent accumulated learnings
 ```
 
-## Orchestration modes
+## How it works
 
-The Orchestrator supports **both** delegation patterns:
+Select the **Orchestrator** agent in Copilot Chat and describe what you want. The Orchestrator autonomously calls Planner → Coder/Designer → Reviewer without any manual handoff clicks.
 
-- **Handoff buttons** — Click `📋 Plan`, `💻 Code`, `🎨 Design`, or `🔍 Review` to manually transition between agents with pre-filled context.
-- **Subagent delegation** — Ask the Orchestrator to handle a complex task and it calls Planner → Coder → Reviewer autonomously.
+```
+User: implement from plan.md
+Orchestrator → [calls Planner] → [calls Coder] → [calls Reviewer] → done
+```
 
-Each specialist also has handoffs: Coder/Designer → Reviewer, Reviewer → Coder (fix loop), and everyone → back to Orchestrator.
+No buttons. No "click here to continue". Just results.
 
 ## Commands
 
@@ -77,10 +79,10 @@ npx cli-five help
 2. **git init** — if needed. Asks first.
 3. **Overwrite gate** — double-confirms ("Proceed?" then "R U Sure?"). Only `--force --yes` bypasses.
 4. **Interview** — name, one-liner, stack, frameworks, goals, constraints, cost mode, persona toggle.
-5. **Scaffold** — writes 18 files. Substitutes answers into templates. Swaps `model:` per cost mode. Adds `handoffs:` to all agents.
+5. **Scaffold** — writes 18 files. Substitutes answers into templates. Swaps `model:` per cost mode.
 6. **Skill discovery** — the hero feature. Multi-source discovery from **awesome-copilot** (30k+ ★ community marketplace) and **skills.sh**. Color-coded recommendations, source attribution, multiselect install, and post-install breadcrumbs with copy-paste commands for the awesome-copilot suggestion skill and MCP server.
 7. **Custom instructions** — generates stack-specific `.instructions.md` files for detected languages.
-8. **Next steps** — tells you to use handoff buttons or autonomous mode, offers plugin install shortcut.
+8. **Next steps** — tells you to open Copilot Chat, select Orchestrator, and start building. No button-clicking required.
 
 ## Cost modes
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cli-five",
-  "version": "0.2.5",
+  "version": "0.2.7",
   "description": "Code Like I'm Five — scaffold a 5-agent VS Code Copilot team into any repo.",
   "type": "module",
   "bin": {

package/plugin-agents/coder.agent.md

@@ -4,15 +4,6 @@ description: "Writes production code following workspace conventions. Use when:
 model: GPT-5.3-Codex (copilot)
 tools: ['vscode', 'execute', 'read', 'github/*', 'edit', 'search', 'web', 'vscode/memory', 'todo']
 agents: []
-handoffs:
-  - label: "🔍 Review"
-    agent: Reviewer
-    prompt: "Review the changes I just made for correctness and conventions."
-    send: false
-  - label: "🎯 Back to Orchestrator"
-    agent: Orchestrator
-    prompt: "Implementation complete. Coordinate next steps."
-    send: false
 ---
 
 ## Mandatory Coding Principles

package/plugin-agents/designer.agent.md

@@ -4,15 +4,6 @@ description: "Handles all UI/UX design tasks. Use when: creating screens, layout
 model: Claude Opus 4.6 (copilot)
 tools: ['read', 'edit', 'search', 'web', 'vscode/memory']
 agents: []
-handoffs:
-  - label: "🔍 Review"
-    agent: Reviewer
-    prompt: "Review the UI changes for accessibility, conventions, and design quality."
-    send: false
-  - label: "🎯 Back to Orchestrator"
-    agent: Orchestrator
-    prompt: "Design work complete. Coordinate next steps."
-    send: false
 ---
 
 ## Design Principles

package/plugin-agents/orchestrator.agent.md

@@ -4,23 +4,6 @@ description: "Coordinates multi-agent workflows. Delegates to Planner, Coder, De
 model: Claude Sonnet 4.6 (copilot)
 tools: ['read/readFile', 'agent', 'vscode/memory', 'github/*']
 agents: ['Planner', 'Coder', 'Designer', 'Reviewer']
-handoffs:
-  - label: "📋 Plan"
-    agent: Planner
-    prompt: "Research the codebase and create an implementation plan for this task."
-    send: false
-  - label: "💻 Code"
-    agent: Coder
-    prompt: "Implement the approved plan."
-    send: false
-  - label: "🎨 Design"
-    agent: Designer
-    prompt: "Design the UI components described in the plan."
-    send: false
-  - label: "🔍 Review"
-    agent: Reviewer
-    prompt: "Review the implementation for correctness, conventions, and architecture."
-    send: false
 ---
 
 You are a project orchestrator. You break down complex requests into tasks and delegate to specialist subagents. You coordinate work but NEVER implement anything yourself.

package/plugin-agents/planner.agent.md

@@ -3,16 +3,6 @@ name: Planner
 description: "Creates implementation plans by researching the codebase, consulting documentation, and identifying edge cases."
 model: Claude Opus 4.6 (copilot)
 tools: ['read', 'search', 'web', 'vscode/memory']
-user-invocable: false
-handoffs:
-  - label: "🎯 Execute Plan"
-    agent: Orchestrator
-    prompt: "Plan is ready. Execute it phase by phase."
-    send: false
-  - label: "💻 Code Directly"
-    agent: Coder
-    prompt: "Implement this plan."
-    send: false
 ---
 
 # Planning Agent

package/plugin-agents/reviewer.agent.md

@@ -4,16 +4,6 @@ description: "Reviews code and agent output for correctness, convention complian
 model: Claude Opus 4.6 (copilot)
 tools: ['read', 'search', 'web', 'vscode/memory']
 agents: []
-user-invocable: true
-handoffs:
-  - label: "🎯 Back to Orchestrator"
-    agent: Orchestrator
-    prompt: "Review complete. See verdict above. Coordinate fixes or proceed."
-    send: false
-  - label: "💻 Fix Issues"
-    agent: Coder
-    prompt: "Fix the issues identified in the review above."
-    send: false
 ---
 
 ## Identity

package/src/commands/init.mjs

@@ -109,6 +109,8 @@ async function ask(message, initial = false) {
 }
 
 function printNextSteps(answers) {
+  const hasDocs = answers.docFiles?.length > 0;
+
   log.raw('');
   log.raw(kleur.bold().green('Done. Next steps:'));
   log.raw('');
@@ -116,10 +118,15 @@ function printNextSteps(answers) {
   log.raw(`  2. Enable Copilot subagent invocations (settings.json):`);
   log.raw(kleur.gray(`        "chat.subagents.allowInvocationsFromSubagents": true`));
   log.raw(`  3. Open Copilot Chat — select an agent from the dropdown (${kleur.bold('not')} @mention).`);
-  log.raw(`  4. Select ${kleur.bold('Orchestrator')} — use handoff buttons or ask it to delegate:`);
-  log.raw(kleur.gray(`        📋 Plan  💻 Code  🎨 Design  🔍 Review`));
-  log.raw(`  5. Or go autonomous:`);
-  log.raw(kleur.gray(`        read PROJECT.md and implement Phase 1.`));
+  log.raw(`  4. Select ${kleur.bold('Orchestrator')} — it routes tasks autonomously to Planner, Coder, Designer, and Reviewer.`);
+  log.raw(`  5. ${hasDocs ? 'Kickoff prompt (paste this into Orchestrator):' : 'Start building:'}`);
+  if (hasDocs) {
+    const docList = answers.docFiles.join(', ');
+    log.raw(kleur.cyan(`        Review PROJECT.md (your source docs — ${docList} — are embedded`));
+    log.raw(kleur.cyan(`        in the Source Documents section) and begin implementation.`));
+  } else {
+    log.raw(kleur.gray(`        read PROJECT.md and implement Phase 1.`));
+  }
   log.raw(`  6. Review generated instruction files in .github/instructions/.`);
   log.raw(kleur.gray(`        Edit applyTo globs and guidelines to fit your project.`));
   log.raw('');

package/src/steps/interview.mjs

@@ -1,3 +1,4 @@
+import kleur from 'kleur';
 import prompts from 'prompts';
 
 // ── Preset stacks ─────────────────────────────────────────────────────
@@ -85,6 +86,9 @@ export async function interview(detected, args, docHints = {}) {
     throw new Error('Interview cancelled. Nothing was written.');
   };
 
+  const hasDocs = (docHints.files?.length ?? 0) > 0;
+  const skipHint = hasDocs ? kleur.dim('  (↵ to skip — your docs cover this)') : '';
+
   // ── Basic info ────────────────────────────────────────────────────
   const basic = await prompts(
     [
@@ -97,7 +101,7 @@ export async function interview(detected, args, docHints = {}) {
       {
         type: 'text',
         name: 'oneLiner',
-        message: 'One-line description (becomes PROJECT.md vision)',
+        message: `One-line description (becomes PROJECT.md vision)${skipHint}`,
         initial: docHints.oneLiner || '',
       },
     ],
@@ -158,13 +162,13 @@ export async function interview(detected, args, docHints = {}) {
       {
         type: 'text',
         name: 'goals',
-        message: 'Primary goal of this project (one sentence)',
+        message: `Primary goal of this project (one sentence)${skipHint}`,
         initial: docHints.goals || '',
       },
       {
         type: 'text',
         name: 'constraints',
-        message: 'Hard constraints (perf, deps, deploy, compliance — one sentence, optional)',
+        message: `Hard constraints (perf, deps, deploy, compliance — one sentence, optional)${skipHint}`,
         initial: docHints.constraints || '',
       },
       {
@@ -192,6 +196,7 @@ export async function interview(detected, args, docHints = {}) {
     presetId: preset,
     quickstart: chosenPreset?.quickstart || '',
     docs: docHints.raw || '',
+    docFiles: docHints.files || [],
   });
 }
 
@@ -211,6 +216,7 @@ function defaults(detected, docHints = {}) {
     presetId: hasDetected ? 'custom' : fallback.value,
     quickstart: hasDetected ? '' : fallback.quickstart,
     docs: docHints.raw || '',
+    docFiles: docHints.files || [],
   };
 }
 

package/src/steps/skills.mjs

@@ -247,7 +247,7 @@ export async function skillDiscovery({ cwd, answers, args }) {
       for (const [repo, skills] of byRepo) {
         const skillArgs = skills.flatMap((s) => ['--skill', s]);
         log.info(`Installing from ${kleur.bold(repo)}: ${skills.join(', ')}`);
-        const result = await runSkillsTracked(env, ['add', repo, ...skillArgs, '-a', 'github-copilot'], cwd);
+        const result = await runSkillsTracked(env, ['add', repo, ...skillArgs, '-a', 'github-copilot', '--yes'], cwd);
         for (const s of skills) {
           installResults.push({ name: `${repo}@${s}`, ...result });
         }
@@ -256,7 +256,7 @@ export async function skillDiscovery({ cwd, answers, args }) {
       // Standalone refs
       for (const ref of standalone) {
         log.info(`Installing ${ref}...`);
-        const result = await runSkillsTracked(env, ['add', ref, '-a', 'github-copilot'], cwd);
+        const result = await runSkillsTracked(env, ['add', ref, '-a', 'github-copilot', '--yes'], cwd);
         installResults.push({ name: ref, ...result });
       }
 
@@ -375,20 +375,24 @@ function runSkills(env, skillsArgs, cwd) {
 function runSkillsTracked(env, skillsArgs, cwd) {
   const { cmd, args } = env.runner(skillsArgs);
   return new Promise((resolve) => {
-    // stdout/stderr inherit so the child writes directly to the TTY.
-    // This prevents line-buffering from swallowing unterminated prompt lines
-    // (e.g. the global vs local install question from the skills CLI).
-    // Failure is detected via exit code; stderr still captured for reason extraction.
-    let stderrOutput = '';
-    const proc = spawn(cmd, args, { cwd, stdio: ['inherit', 'inherit', 'pipe'] });
+    // stdout/stderr piped and re-echoed so we can capture output for failure detection.
+    // --yes is always passed so no interactive prompts will stall the pipe.
+    let output = '';
+    const proc = spawn(cmd, args, { cwd, stdio: ['ignore', 'pipe', 'pipe'] });
+    proc.stdout.on('data', (chunk) => {
+      const text = chunk.toString();
+      process.stdout.write(text);
+      output += text;
+    });
     proc.stderr.on('data', (chunk) => {
       const text = chunk.toString();
       process.stderr.write(text);
-      stderrOutput += text;
+      output += text;
     });
     proc.on('exit', (code) => {
-      if (code !== 0) {
-        const reason = extractFailureReason(stripAnsi(stderrOutput)) || `exited with code ${code}`;
+      const clean = stripAnsi(output);
+      if (code !== 0 || /failed to clone|installation failed|canceled/i.test(clean)) {
+        const reason = extractFailureReason(clean);
         resolve({ ok: false, reason });
       } else {
         resolve({ ok: true, reason: null });

package/templates/.github/agents/coder.agent.md

@@ -4,15 +4,6 @@ description: "Writes production code following workspace conventions. Use when:
 model: GPT-5.3-Codex (copilot)
 tools: ['vscode', 'execute', 'read', 'io.github.upstash/context7/*', 'github/*', 'edit', 'search', 'web', 'vscode/memory', 'todo']
 agents: []
-handoffs:
-  - label: "🔍 Review"
-    agent: Reviewer
-    prompt: "Review the changes I just made for correctness and conventions."
-    send: false
-  - label: "🎯 Back to Orchestrator"
-    agent: Orchestrator
-    prompt: "Implementation complete. Coordinate next steps."
-    send: false
 ---
 
 ## Model Selection

package/templates/.github/agents/designer.agent.md

@@ -4,15 +4,6 @@ description: "Handles all UI/UX design tasks. Use when: creating screens, layout
 model: Claude Opus 4.6 (copilot)
 tools: ['read', 'edit', 'search', 'web', 'io.github.upstash/context7/*', 'vscode/memory']
 agents: []
-handoffs:
-  - label: "🔍 Review"
-    agent: Reviewer
-    prompt: "Review the UI changes for accessibility, conventions, and design quality."
-    send: false
-  - label: "🎯 Back to Orchestrator"
-    agent: Orchestrator
-    prompt: "Design work complete. Coordinate next steps."
-    send: false
 ---
 
 ## Model Selection

package/templates/.github/agents/orchestrator.agent.md

@@ -4,23 +4,6 @@ description: "Coordinates multi-agent workflows. Delegates to Planner, Coder, De
 model: Claude Sonnet 4.6 (copilot)
 tools: ['read/readFile', 'agent', 'vscode/memory', 'github/*']
 agents: ['Planner', 'Coder', 'Designer', 'Reviewer']
-handoffs:
-  - label: "📋 Plan"
-    agent: Planner
-    prompt: "Read PROJECT.md and STATE.md, then create an implementation plan for this task."
-    send: false
-  - label: "💻 Code"
-    agent: Coder
-    prompt: "Implement the approved plan. Read decisions.md for context."
-    send: false
-  - label: "🎨 Design"
-    agent: Designer
-    prompt: "Design the UI components described in the plan."
-    send: false
-  - label: "🔍 Review"
-    agent: Reviewer
-    prompt: "Review the implementation for correctness, conventions, and architecture."
-    send: false
 ---
 
 You are a project orchestrator. You break down complex requests into tasks and delegate to specialist subagents. You coordinate work but NEVER implement anything yourself.

package/templates/.github/agents/planner.agent.md

@@ -3,16 +3,6 @@ name: Planner
 description: "Creates implementation plans by researching the codebase, consulting documentation, and identifying edge cases. Use when: planning features, architectural decisions, or complex multi-file changes."
 model: Claude Opus 4.6 (copilot)
 tools: ['read', 'search', 'web', 'io.github.upstash/context7/*', 'vscode/memory']
-user-invocable: false
-handoffs:
-  - label: "🎯 Execute Plan"
-    agent: Orchestrator
-    prompt: "Plan is ready. Execute it phase by phase."
-    send: false
-  - label: "💻 Code Directly"
-    agent: Coder
-    prompt: "Implement this plan."
-    send: false
 ---
 
 # Planning Agent

package/templates/.github/agents/reviewer.agent.md

@@ -4,16 +4,6 @@ description: "Reviews code and agent output for correctness, convention complian
 model: Claude Opus 4.6 (copilot)
 tools: ['read', 'search', 'web', 'vscode/memory']
 agents: []
-user-invocable: true
-handoffs:
-  - label: "🎯 Back to Orchestrator"
-    agent: Orchestrator
-    prompt: "Review complete. See verdict above. Coordinate fixes or proceed."
-    send: false
-  - label: "💻 Fix Issues"
-    agent: Coder
-    prompt: "Fix the issues identified in the review above."
-    send: false
 ---
 
 ## Model Selection