code-ai-installer 1.5.1 → 1.5.2

package/locales/en/.agents/workflows/start-task.md

@@ -1,27 +1,130 @@
----
-description: Task launch template through the 8-agent pipeline. Use at the beginning of EVERY session.
 ---
+description: Template for launching a task through the 8-agent pipeline. Use at the start of EVERY session.
+---
+
+# /start-task — Launch a task through the pipeline
+
+## Step 0: Select pipeline mode
+
+Determine the task type and choose the workflow:
+- 🔵 **New feature / refactoring** → continue with `/start-task` (this file)
+- 🟢 **Bugfix** (> 2 files, non-trivial) → switch to `/bugfix`
+- 🟡 **Hotfix** (1–2 files, blast radius ≈ 0) → switch to `/hotfix`
+
+> If you selected `/bugfix` or `/hotfix` — stop reading this file and follow the chosen workflow.
+
+## Step 1: Load pipeline rules
+
+Execute `/pipeline-rules` — read and acknowledge ALL rules BEFORE starting work.
+
+## Step 2: Initialize agents
+Execute `view_file` on `AGENTS.md` — confirm the list of agents and skills.
+
+## Step 3: Launch the Conductor
+Execute `view_file` on `agents/conductor.md` — read the protocol and create the Master Checklist in `task.md`.
+
+## Step 4: Pass each gate STRICTLY by protocol
+
+On EVERY gate, mandatory steps:
+1. `view_file` on `agents/<role>.md` — read the agent protocol
+2. Pass EACH section of the protocol in order (no "collapsing")
+3. Use the **full** "Agent Response Format (strict)" from the agent file
+4. If a section is not applicable — explicitly write: "N/A — [reason]"
+5. Produce deliverable + Handoff Envelope with ALL mandatory fields
+6. Present the result via `notify_user`
+7. **Wait for explicit "Approved"** before moving to the next gate
 
-# /start-task
+## Step 5: Code — ONLY after DEV gate + Approved
 
-## Steps
-1. Load `/pipeline-rules`
-2. Read `AGENTS.md`
-3. Read `agents/conductor.md`
-4. Start the pipeline gate by gate
-5. Do not apply code before DEV gate + explicit Approved
-6. If a gate fails, run a full Fix Cycle through DEV → REV → OPS → TEST
+- First, the DEV agent passes ALL sections of the protocol (§0–§7)
+- Then proposes the change plan
+- User approves
+- ONLY THEN the agent applies code
+
+## Step 6: Fix Cycle (on FAIL)
+
+If the tester or reviewer finds a bug:
+1. Current agent produces FAIL Report + HANDOFF Envelope → DEV
+2. User approves FAIL HANDOFF
+3. DEV reads `agents/senior_full_stack.md` and passes the FULL protocol
+4. DEV HANDOFF → REV → OPS → TEST (each gate with full protocol)
+5. No "quick fixes" without passing through agents
+
+---
+
+## First prompt template (copy and fill)
 
-## First prompt template
 ```
 @AGENTS.md /pipeline-rules
 
-Task: [what to do].
-Files: [known files].
+Task: [what to do, 1-2 sentences].
+Files: [specific files, if known].
 
 Rules:
-1. Start with Conductor
-2. Every gate: read protocol → complete all sections → full response → Approved
-3. Do not apply code before DEV gate + my Approved
+1. Start with the Conductor (agents/conductor.md)
+2. Each gate: view_file → ALL protocol sections → full format → Approved
+3. Do not apply code until DEV gate + my Approved
 4. Fix Cycle = full pass through agents
-```
+```
+
+---
+
+## Session recommendations
+
+- **One session = 3-4 gates maximum** (context is preserved)
+- **Approved is given on EACH gate**, not per session
+- **Session 1:** Conductor → Approved → PM → Approved → UX → Approved
+- **Session 2:** ARCH → Approved → DEV → Approved → REV → Approved
+- **Session 3:** OPS → Approved → TEST → Approved → RG → Approved
+- Each new session — start with `/start-task`
+
+## Mandatory questions from agents
+
+Each agent that has a Clarification/Questions section in their protocol MUST:
+1. Ask questions to the user BEFORE performing work
+2. Minimum questions (from agent protocol): PM — 5+, ARCH — 5-10, DEV — as needed, Tester — 5+
+3. If the task seems "obvious" — still ask at minimum 2-3 clarifying questions
+4. Wait for user answers BEFORE continuing
+5. The only exception: the user explicitly wrote "no questions"
+
+## When "cutting corners" — one phrase
+
+If the model shortcuts, say:
+> "Stop. Section [X] of protocol agents/<role>.md. Re-read and execute."
+
+---
+
+## Feedback protocol (mandatory)
+
+The model MUST provide feedback to the user at every stage:
+
+### 1. Warning when tempted to shortcut
+If the task looks "trivial", the model MUST write:
+```
+⚠️ Task looks trivial. My instinct is to do it quickly.
+But following the protocol, I'm going through the full cycle. Sections: [list].
+```
+
+### 2. User prompt assessment
+At the start of each task the model assesses the prompt:
+```
+📊 Prompt assessment:
+- Clarity: [high/medium/low]
+- What helped: [what was useful]
+- What's missing: [what to add for effectiveness]
+```
+
+### 3. Tips in Handoff Envelope
+In each Handoff add a section:
+```
+💡 Feedback: [tip for the user, if any]
+```
+
+### 4. Retrospective at session end
+Before finishing work:
+```
+🔄 Retrospective:
+- Gates passed: X
+- Protocol violations: X
+- What to improve in the next session: [recommendation]
+```

package/locales/en/prompt-examples.md

@@ -0,0 +1,152 @@
+# Prompt Examples for Pipeline Launch
+
+> Copy the relevant prompt, replace placeholders with your data, paste into chat.
+
+---
+
+## 🔵 Full Pipeline (`/start-task`) — new feature / refactoring
+
+### New Feature
+```
+@AGENTS.md Task:
+Implement [feature description].
+Full pipeline!
+
+SESSION RULES:
+1. Each gate: view_file agents/<role>.md → view_file on EVERY SKILL.md from the protocol skills → deliverable → notify_user → wait for "Approved"
+2. Skipping a gate or skill = BLOCKER
+3. Do not proceed without Approved
+```
+
+### Refactoring
+```
+@AGENTS.md Task:
+Refactor [description: what exactly we're refactoring and why].
+Full pipeline!
+
+SESSION RULES:
+1. Each gate: view_file agents/<role>.md → view_file on EVERY SKILL.md from the protocol skills → deliverable → notify_user → wait for "Approved"
+2. Skipping a gate or skill = BLOCKER
+3. Do not proceed without Approved
+```
+
+---
+
+## 🟢 Bugfix (`/bugfix`) — bug fix (4 gates)
+
+### Standard Bug
+```
+@AGENTS.md Task:
+Fix bug: [bug description, reproduction steps, expected vs actual behavior].
+Bugfix pipeline!
+
+SESSION RULES:
+1. Each gate: view_file agents/<role>.md → view_file on EVERY SKILL.md from the protocol skills → deliverable → notify_user → wait for "Approved"
+2. Skipping a gate or skill = BLOCKER
+3. Do not proceed without Approved
+```
+
+### Bug with File References
+```
+@AGENTS.md Task:
+@[path/to/file1] @[path/to/file2]
+Bug: [description]. Root cause likely in the referenced files.
+Bugfix pipeline!
+
+SESSION RULES:
+1. Each gate: view_file agents/<role>.md → view_file on EVERY SKILL.md → deliverable → notify_user → wait for "Approved"
+2. Skipping a gate = BLOCKER
+```
+
+---
+
+## 🟡 Hotfix (`/hotfix`) — minor fix (2 gates)
+
+### Typo / CSS / Single Line
+```
+@AGENTS.md Task:
+Hotfix: [fix description, e.g.: "fix typo in heading" or "change button color from #333 to #555"].
+Hotfix pipeline!
+
+SESSION RULES:
+1. Each gate: view_file agents/<role>.md → view_file on EVERY SKILL.md → deliverable → notify_user → wait for "Approved"
+2. Skipping a gate = BLOCKER
+```
+
+---
+
+## 🎨 Design Only (Google Stitch)
+
+### UI Screen Generation
+```
+@AGENTS.md Task:
+Create UI screens for [description: which screens, which application].
+Use Google Stitch via $google_stitch_skill.
+
+SESSION RULES:
+1. view_file agents/ux_ui_designer.md → view_file $google_stitch_skill → deliverable → notify_user → wait for "Approved"
+```
+
+---
+
+## 📄 Documentation Only
+
+### Document Adaptation / Creation
+```
+@AGENTS.md Task:
+[Documentation task description, e.g.: "adapt files X, Y, Z for global use"].
+Bugfix pipeline! (or Full pipeline — depending on complexity)
+
+SESSION RULES:
+1. Each gate: view_file agents/<role>.md → view_file on EVERY SKILL.md → deliverable → notify_user → wait for "Approved"
+2. Skipping a gate = BLOCKER
+```
+
+---
+
+## ⚡ Gate Transitions (User Responses)
+
+### Approve and Move to Next Gate
+```
+Approved. Next gate: agents/<role>.md. Skills: view_file required. Full format.
+```
+
+### Approve with Trigger (Wix / Shopify)
+```
+Approved. TEST gate. Wix.
+```
+
+### Reject / Return for Rework
+```
+NO-GO. Fix: [list of issues]. Return to [gate] gate.
+```
+
+---
+
+## 🔧 Utility Prompts
+
+### Check Status
+```
+Show the current Master Checklist and status of all gates.
+```
+
+### Run a Specific Agent
+```
+Run agents/<role>.md. Context: [brief description]. Skills: view_file required.
+```
+
+### Update Version
+```
+Update the version in package.json to X.Y.Z
+```
+
+---
+
+## 📝 Tips for Writing Prompts
+
+1. **Always start with `@AGENTS.md`** — this loads the agent system
+2. **Reference files with `@[path]`** — the agent immediately sees the context
+3. **Name the pipeline mode** — "Full pipeline!", "Bugfix pipeline!", "Hotfix pipeline!"
+4. **Add SESSION RULES** — this guarantees protocol compliance
+5. **Write "Approved" explicitly** — without this word the agent will not proceed to the next gate
+6. **Be specific** — the more precise the description, the better the result

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "code-ai-installer",
-  "version": "1.5.1",
+  "version": "1.5.2",
   "description": "Production-ready CLI to install code-ai agents and skills for multiple AI coding assistants.",
   "license": "MIT",
   "author": "Denis Harchenko",