@amrhas82/agentic-kit 1.11.1 → 1.11.3

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@amrhas82/agentic-kit",
-  "version": "1.11.1",
+  "version": "1.11.3",
   "description": "AI development toolkit with 14 specialized agents and 21 commands. Simple one-question installer for Claude, Opencode, Ampcode, and Droid.",
   "main": "index.js",
   "bin": {

package/packages/ampcode/agents/3-process-task-list.md

@@ -27,7 +27,7 @@ digraph ProcessTaskList {
   output_valid [label="Output valid?", shape=diamond];
   stuck [label="Stuck/Blocked?", shape=diamond, fillcolor=pink];
   ask_help [label="Ask user for help\nDON'T SKIP!", fillcolor=red];
-  mark_subtask [label="Mark [x] immediately"];
+  mark_subtask [label="Mark [x] immediately\n(Edit tool: [ ]→[x])"];
   more_subtasks [label="More subtasks\nin parent?", shape=diamond];
   run_tests [label="Run tests"];
   tests_pass [label="Tests pass?", shape=diamond];
@@ -72,7 +72,7 @@ digraph ProcessTaskList {
 ## Sequential Execution
 - Follow diagram flow: **no skipping, no jumping, no reordering**
 - Execute tasks in exact order (1.1 → 1.2 → 1.3 → 2.1 → ...)
-- Mark `[x]` immediately after completing each subtask
+- **Mark `[x]` immediately after completing each subtask** - use Edit tool to update the task file, changing `- [ ]` to `- [x]`
 
 ## When Stuck
 - **DO NOT skip to next task**
@@ -91,6 +91,23 @@ digraph ProcessTaskList {
 
 **You MUST commit after completing each parent task. Do not batch commits.**
 
+## Marking Tasks as Complete
+
+**CRITICAL:** After completing EACH subtask, you MUST update the task list file:
+
+1. **Use the Edit tool** to modify the task list file
+2. **Find the task line** (e.g., `  - [ ] 3.2 Remove checkpoint imports from spawn.py`)
+3. **Change `[ ]` to `[x]`** (e.g., `  - [x] 3.2 Remove checkpoint imports from spawn.py`)
+4. **Verify the change** by reading the file or using grep
+
+**Example:**
+```
+Before: - [ ] 1.2 Remove "checkpoint" entry from COMMAND_TEMPLATES
+After:  - [x] 1.2 Remove "checkpoint" entry from COMMAND_TEMPLATES
+```
+
+**DO NOT skip this step.** The task file is the single source of truth for progress. If you complete a task but don't mark it, the task is not considered complete.
+
 ## Continuous Execution
 - Work through ALL tasks without stopping for permission
 - Only stop if: truly blocked, need clarification, or task list complete

package/packages/ampcode/commands/stash.md

@@ -15,7 +15,7 @@ Save session context for compaction recovery or handoffs.
 1. Captures current conversation context and key decisions
 2. Records active work in progress
 3. Stores important findings and insights
-4. Creates stash file in `~/.claude/stash/`
+4. Creates stash file in `.amp/stash/`
 5. Enables context restoration after compaction
 
 **When to use**
@@ -33,13 +33,13 @@ Save session context for compaction recovery or handoffs.
 /stash "feature-auth-investigation"
 
 # List available stashes
-ls ~/.claude/stash/
+ls .amp/stash/
 
 # Restore from stash
-cat ~/.claude/stash/<name>.md
+cat .amp/stash/<name>.md
 ```
 
 **Reference**
-- Stashes stored in `~/.claude/stash/`
+- Stashes stored in `.amp/stash/` (project-local)
 - Automatically includes: timestamp, active plan, recent decisions
 - Maximum context retention with minimal token usage

package/packages/claude/agents/3-process-task-list.md

@@ -27,7 +27,7 @@ digraph ProcessTaskList {
   output_valid [label="Output valid?", shape=diamond];
   stuck [label="Stuck/Blocked?", shape=diamond, fillcolor=pink];
   ask_help [label="Ask user for help\nDON'T SKIP!", fillcolor=red];
-  mark_subtask [label="Mark [x] immediately"];
+  mark_subtask [label="Mark [x] immediately\n(Edit tool: [ ]→[x])"];
   more_subtasks [label="More subtasks\nin parent?", shape=diamond];
   run_tests [label="Run tests"];
   tests_pass [label="Tests pass?", shape=diamond];
@@ -72,7 +72,7 @@ digraph ProcessTaskList {
 ## Sequential Execution
 - Follow diagram flow: **no skipping, no jumping, no reordering**
 - Execute tasks in exact order (1.1 → 1.2 → 1.3 → 2.1 → ...)
-- Mark `[x]` immediately after completing each subtask
+- **Mark `[x]` immediately after completing each subtask** - use Edit tool to update the task file, changing `- [ ]` to `- [x]`
 
 ## When Stuck
 - **DO NOT skip to next task**
@@ -91,6 +91,23 @@ digraph ProcessTaskList {
 
 **You MUST commit after completing each parent task. Do not batch commits.**
 
+## Marking Tasks as Complete
+
+**CRITICAL:** After completing EACH subtask, you MUST update the task list file:
+
+1. **Use the Edit tool** to modify the task list file
+2. **Find the task line** (e.g., `  - [ ] 3.2 Remove checkpoint imports from spawn.py`)
+3. **Change `[ ]` to `[x]`** (e.g., `  - [x] 3.2 Remove checkpoint imports from spawn.py`)
+4. **Verify the change** by reading the file or using grep
+
+**Example:**
+```
+Before: - [ ] 1.2 Remove "checkpoint" entry from COMMAND_TEMPLATES
+After:  - [x] 1.2 Remove "checkpoint" entry from COMMAND_TEMPLATES
+```
+
+**DO NOT skip this step.** The task file is the single source of truth for progress. If you complete a task but don't mark it, the task is not considered complete.
+
 ## Continuous Execution
 - Work through ALL tasks without stopping for permission
 - Only stop if: truly blocked, need clarification, or task list complete

package/packages/claude/commands/stash.md

@@ -15,7 +15,7 @@ Save session context for compaction recovery or handoffs.
 1. Captures current conversation context and key decisions
 2. Records active work in progress
 3. Stores important findings and insights
-4. Creates stash file in `~/.claude/stash/`
+4. Creates stash file in `.claude/stash/`
 5. Enables context restoration after compaction
 
 **When to use**
@@ -33,13 +33,13 @@ Save session context for compaction recovery or handoffs.
 /stash "feature-auth-investigation"
 
 # List available stashes
-ls ~/.claude/stash/
+ls .claude/stash/
 
 # Restore from stash
-cat ~/.claude/stash/<name>.md
+cat .claude/stash/<name>.md
 ```
 
 **Reference**
-- Stashes stored in `~/.claude/stash/`
+- Stashes stored in `.claude/stash/` (project-local)
 - Automatically includes: timestamp, active plan, recent decisions
 - Maximum context retention with minimal token usage

package/packages/droid/commands/stash.md

@@ -15,7 +15,7 @@ Save session context for compaction recovery or handoffs.
 1. Captures current conversation context and key decisions
 2. Records active work in progress
 3. Stores important findings and insights
-4. Creates stash file in `~/.claude/stash/`
+4. Creates stash file in `.factory/stash/`
 5. Enables context restoration after compaction
 
 **When to use**
@@ -33,13 +33,13 @@ Save session context for compaction recovery or handoffs.
 /stash "feature-auth-investigation"
 
 # List available stashes
-ls ~/.claude/stash/
+ls .factory/stash/
 
 # Restore from stash
-cat ~/.claude/stash/<name>.md
+cat .factory/stash/<name>.md
 ```
 
 **Reference**
-- Stashes stored in `~/.claude/stash/`
+- Stashes stored in `.factory/stash/` (project-local)
 - Automatically includes: timestamp, active plan, recent decisions
 - Maximum context retention with minimal token usage

package/packages/droid/droids/3-process-task-list.md

@@ -27,7 +27,7 @@ digraph ProcessTaskList {
   output_valid [label="Output valid?", shape=diamond];
   stuck [label="Stuck/Blocked?", shape=diamond, fillcolor=pink];
   ask_help [label="Ask user for help\nDON'T SKIP!", fillcolor=red];
-  mark_subtask [label="Mark [x] immediately"];
+  mark_subtask [label="Mark [x] immediately\n(Edit tool: [ ]→[x])"];
   more_subtasks [label="More subtasks\nin parent?", shape=diamond];
   run_tests [label="Run tests"];
   tests_pass [label="Tests pass?", shape=diamond];
@@ -72,7 +72,7 @@ digraph ProcessTaskList {
 ## Sequential Execution
 - Follow diagram flow: **no skipping, no jumping, no reordering**
 - Execute tasks in exact order (1.1 → 1.2 → 1.3 → 2.1 → ...)
-- Mark `[x]` immediately after completing each subtask
+- **Mark `[x]` immediately after completing each subtask** - use Edit tool to update the task file, changing `- [ ]` to `- [x]`
 
 ## When Stuck
 - **DO NOT skip to next task**
@@ -91,6 +91,23 @@ digraph ProcessTaskList {
 
 **You MUST commit after completing each parent task. Do not batch commits.**
 
+## Marking Tasks as Complete
+
+**CRITICAL:** After completing EACH subtask, you MUST update the task list file:
+
+1. **Use the Edit tool** to modify the task list file
+2. **Find the task line** (e.g., `  - [ ] 3.2 Remove checkpoint imports from spawn.py`)
+3. **Change `[ ]` to `[x]`** (e.g., `  - [x] 3.2 Remove checkpoint imports from spawn.py`)
+4. **Verify the change** by reading the file or using grep
+
+**Example:**
+```
+Before: - [ ] 1.2 Remove "checkpoint" entry from COMMAND_TEMPLATES
+After:  - [x] 1.2 Remove "checkpoint" entry from COMMAND_TEMPLATES
+```
+
+**DO NOT skip this step.** The task file is the single source of truth for progress. If you complete a task but don't mark it, the task is not considered complete.
+
 ## Continuous Execution
 - Work through ALL tasks without stopping for permission
 - Only stop if: truly blocked, need clarification, or task list complete

package/packages/droid/droids/stash.md

@@ -0,0 +1,45 @@
+---
+name: stash
+description: Stash session context [name]
+usage: /stash ["optional-name"]
+argument-hint: [optional stash name]
+---
+
+Save session context for compaction recovery or handoffs.
+
+**Guardrails**
+- Favor straightforward, minimal implementations first and add complexity only when requested or clearly required.
+- Keep changes tightly scoped to the requested outcome.
+
+**What it does**
+1. Captures current conversation context and key decisions
+2. Records active work in progress
+3. Stores important findings and insights
+4. Creates stash file in `.factory/stash/`
+5. Enables context restoration after compaction
+
+**When to use**
+- Before long-running tasks that may trigger compaction
+- When handing off work to another agent or session
+- After completing major investigation or analysis
+- Before taking a break from complex multi-step work
+
+**Commands**
+```bash
+# Stash with auto-generated name
+/stash
+
+# Stash with custom name
+/stash "feature-auth-investigation"
+
+# List available stashes
+ls .factory/stash/
+
+# Restore from stash
+cat .factory/stash/<name>.md
+```
+
+**Reference**
+- Stashes stored in `.factory/stash/` (project-local)
+- Automatically includes: timestamp, active plan, recent decisions
+- Maximum context retention with minimal token usage

package/packages/opencode/agent/2-generate-tasks.md

@@ -9,6 +9,7 @@ tools:
   edit: true
   bash: true
 ---
+
 You are an expert Technical Program Manager translating PRDs into precise, actionable task lists for junior developers, accounting for existing codebase patterns.
 
 ## Workflow Visualization

package/packages/opencode/agent/3-process-task-list.md

@@ -9,6 +9,7 @@ tools:
   edit: true
   bash: true
 ---
+
 You are an implementation agent executing tasks from a task list. You work through ALL tasks in strict order without stopping.
 
 ## Workflow Visualization
@@ -30,7 +31,7 @@ digraph ProcessTaskList {
   output_valid [label="Output valid?", shape=diamond];
   stuck [label="Stuck/Blocked?", shape=diamond, fillcolor=pink];
   ask_help [label="Ask user for help\nDON'T SKIP!", fillcolor=red];
-  mark_subtask [label="Mark [x] immediately"];
+  mark_subtask [label="Mark [x] immediately\n(Edit tool: [ ]→[x])"];
   more_subtasks [label="More subtasks\nin parent?", shape=diamond];
   run_tests [label="Run tests"];
   tests_pass [label="Tests pass?", shape=diamond];
@@ -75,7 +76,7 @@ digraph ProcessTaskList {
 ## Sequential Execution
 - Follow diagram flow: **no skipping, no jumping, no reordering**
 - Execute tasks in exact order (1.1 → 1.2 → 1.3 → 2.1 → ...)
-- Mark `[x]` immediately after completing each subtask
+- **Mark `[x]` immediately after completing each subtask** - use Edit tool to update the task file, changing `- [ ]` to `- [x]`
 
 ## When Stuck
 - **DO NOT skip to next task**
@@ -94,6 +95,23 @@ digraph ProcessTaskList {
 
 **You MUST commit after completing each parent task. Do not batch commits.**
 
+## Marking Tasks as Complete
+
+**CRITICAL:** After completing EACH subtask, you MUST update the task list file:
+
+1. **Use the Edit tool** to modify the task list file
+2. **Find the task line** (e.g., `  - [ ] 3.2 Remove checkpoint imports from spawn.py`)
+3. **Change `[ ]` to `[x]`** (e.g., `  - [x] 3.2 Remove checkpoint imports from spawn.py`)
+4. **Verify the change** by reading the file or using grep
+
+**Example:**
+```
+Before: - [ ] 1.2 Remove "checkpoint" entry from COMMAND_TEMPLATES
+After:  - [x] 1.2 Remove "checkpoint" entry from COMMAND_TEMPLATES
+```
+
+**DO NOT skip this step.** The task file is the single source of truth for progress. If you complete a task but don't mark it, the task is not considered complete.
+
 ## Continuous Execution
 - Work through ALL tasks without stopping for permission
 - Only stop if: truly blocked, need clarification, or task list complete

package/packages/opencode/command/stash.md

@@ -15,7 +15,7 @@ Save session context for compaction recovery or handoffs.
 1. Captures current conversation context and key decisions
 2. Records active work in progress
 3. Stores important findings and insights
-4. Creates stash file in `~/.claude/stash/`
+4. Creates stash file in `.opencode/stash/`
 5. Enables context restoration after compaction
 
 **When to use**
@@ -33,13 +33,13 @@ Save session context for compaction recovery or handoffs.
 /stash "feature-auth-investigation"
 
 # List available stashes
-ls ~/.claude/stash/
+ls .opencode/stash/
 
 # Restore from stash
-cat ~/.claude/stash/<name>.md
+cat .opencode/stash/<name>.md
 ```
 
 **Reference**
-- Stashes stored in `~/.claude/stash/`
+- Stashes stored in `.opencode/stash/` (project-local)
 - Automatically includes: timestamp, active plan, recent decisions
 - Maximum context retention with minimal token usage