@amrhas82/agentic-kit 2.0.0 → 2.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (25) hide show
  1. package/CHANGELOG.md +15 -0
  2. package/README.md +9 -10
  3. package/installer/cli.js +1 -1
  4. package/package.json +2 -2
  5. package/packages/ampcode/AGENT.md +1 -2
  6. package/packages/ampcode/agents/1-create-prd.md +27 -11
  7. package/packages/ampcode/agents/2-generate-tasks.md +18 -10
  8. package/packages/ampcode/agents/3-process-task-list.md +153 -205
  9. package/packages/claude/CLAUDE.md +1 -2
  10. package/packages/claude/agents/1-create-prd.md +27 -11
  11. package/packages/claude/agents/2-generate-tasks.md +18 -10
  12. package/packages/claude/agents/3-process-task-list.md +153 -205
  13. package/packages/droid/AGENTS.md +1 -2
  14. package/packages/droid/droids/1-create-prd.md +27 -16
  15. package/packages/droid/droids/2-generate-tasks.md +18 -10
  16. package/packages/droid/droids/3-process-task-list.md +153 -205
  17. package/packages/opencode/AGENTS.md +1 -2
  18. package/packages/opencode/agent/1-create-prd.md +27 -11
  19. package/packages/opencode/agent/2-generate-tasks.md +18 -10
  20. package/packages/opencode/agent/3-process-task-list.md +153 -205
  21. package/packages/subagentic-manual.md +12 -13
  22. package/packages/ampcode/commands/subagent-spawning.md +0 -81
  23. package/packages/claude/skills/subagent-spawning/SKILL.md +0 -81
  24. package/packages/droid/commands/subagent-spawning.md +0 -81
  25. package/packages/opencode/command/subagent-spawning.md +0 -81
package/packages/droid/commands/subagent-spawning.md DELETED
@@ -1,81 +0,0 @@
1
- ---
2
- name: subagent-spawning
3
- description: Use when spawning fresh subagents for isolated task execution. Provides TDD-aware templates for 3-process-task-list and other agents.
4
- usage: Used by 3-process-task-list and other agents for clean subagent execution
5
- auto_trigger: true
6
- ---
7
-
8
- ## Auto-Trigger
9
-
10
- **APPLIES WHEN:**
11
- - 3-process-task-list spawning implementer for a task
12
- - Any agent delegating work to fresh subagent
13
- - Task isolation needed (prevent context pollution)
14
-
15
- **APPLIES TO:**
16
- - Task list processing
17
- - Parallel task execution
18
- - Complex multi-step implementations
19
-
20
- ## Template A: With TDD (when tdd: yes)
21
-
22
- ```
23
- You are implementing Task: {task_description}
24
-
25
- CONTEXT:
26
- {relevant_file_contents}
27
-
28
- ACCEPTANCE CRITERIA:
29
- {task_specific_criteria}
30
-
31
- TDD REQUIRED:
32
- Write test FIRST. Watch it FAIL. Then implement. Then watch it PASS.
33
- {tdd_note}
34
-
35
- VERIFY WITH: {verify_command}
36
-
37
- WORKFLOW:
38
- 1. Write test for expected behavior
39
- 2. Run test - MUST see it FAIL (red)
40
- 3. Implement minimal code to pass
41
- 4. Run test - verify it PASSES (green)
42
- 5. Refactor if needed
43
- 6. Report: test output (fail→pass) + changes + concerns
44
-
45
- CONSTRAINTS:
46
- - Do NOT implement before writing test
47
- - Do NOT skip red-green verification
48
- - Do NOT reference other tasks
49
- - Do NOT assume context not provided
50
- ```
51
-
52
- ## Template B: Without TDD (when tdd: no)
53
-
54
- ```
55
- You are implementing Task: {task_description}
56
-
57
- CONTEXT:
58
- {relevant_file_contents}
59
-
60
- ACCEPTANCE CRITERIA:
61
- {task_specific_criteria}
62
-
63
- VERIFY WITH: {verify_command}
64
-
65
- WORKFLOW:
66
- 1. Implement the task completely
67
- 2. Run verify command BEFORE claiming done
68
- 3. Report: changes + verify output + concerns
69
-
70
- CONSTRAINTS:
71
- - Do NOT reference other tasks
72
- - Do NOT assume context not provided
73
- - Do NOT claim done without verify output
74
- ```
75
-
76
- ## Why Fresh Subagents?
77
-
78
- - Task 1 confusion doesn't pollute task 5
79
- - Each task gets clean reasoning slate
80
- - Prevents "I already tried that" false memories
81
- - Forces explicit context = fewer assumptions
package/packages/opencode/command/subagent-spawning.md DELETED
@@ -1,81 +0,0 @@
1
- ---
2
- name: subagent-spawning
3
- description: Use when spawning fresh subagents for isolated task execution. Provides TDD-aware templates for 3-process-task-list and other agents.
4
- usage: Used by 3-process-task-list and other agents for clean subagent execution
5
- auto_trigger: true
6
- ---
7
-
8
- ## Auto-Trigger
9
-
10
- **APPLIES WHEN:**
11
- - 3-process-task-list spawning implementer for a task
12
- - Any agent delegating work to fresh subagent
13
- - Task isolation needed (prevent context pollution)
14
-
15
- **APPLIES TO:**
16
- - Task list processing
17
- - Parallel task execution
18
- - Complex multi-step implementations
19
-
20
- ## Template A: With TDD (when tdd: yes)
21
-
22
- ```
23
- You are implementing Task: {task_description}
24
-
25
- CONTEXT:
26
- {relevant_file_contents}
27
-
28
- ACCEPTANCE CRITERIA:
29
- {task_specific_criteria}
30
-
31
- TDD REQUIRED:
32
- Write test FIRST. Watch it FAIL. Then implement. Then watch it PASS.
33
- {tdd_note}
34
-
35
- VERIFY WITH: {verify_command}
36
-
37
- WORKFLOW:
38
- 1. Write test for expected behavior
39
- 2. Run test - MUST see it FAIL (red)
40
- 3. Implement minimal code to pass
41
- 4. Run test - verify it PASSES (green)
42
- 5. Refactor if needed
43
- 6. Report: test output (fail→pass) + changes + concerns
44
-
45
- CONSTRAINTS:
46
- - Do NOT implement before writing test
47
- - Do NOT skip red-green verification
48
- - Do NOT reference other tasks
49
- - Do NOT assume context not provided
50
- ```
51
-
52
- ## Template B: Without TDD (when tdd: no)
53
-
54
- ```
55
- You are implementing Task: {task_description}
56
-
57
- CONTEXT:
58
- {relevant_file_contents}
59
-
60
- ACCEPTANCE CRITERIA:
61
- {task_specific_criteria}
62
-
63
- VERIFY WITH: {verify_command}
64
-
65
- WORKFLOW:
66
- 1. Implement the task completely
67
- 2. Run verify command BEFORE claiming done
68
- 3. Report: changes + verify output + concerns
69
-
70
- CONSTRAINTS:
71
- - Do NOT reference other tasks
72
- - Do NOT assume context not provided
73
- - Do NOT claim done without verify output
74
- ```
75
-
76
- ## Why Fresh Subagents?
77
-
78
- - Task 1 confusion doesn't pollute task 5
79
- - Each task gets clean reasoning slate
80
- - Prevents "I already tried that" false memories
81
- - Forces explicit context = fewer assumptions