Skip to content

Commit da0d33a

Browse files
rainyuleiclaude
andcommitted
feat: v2.2.0 — update all 13 agents to VS Code official tools, add structured output paths
- Replace generic tool names (search/read/edit/execute) with VS Code official built-in tool names (codebase, textSearch, fileSearch, readFile, etc.) - Add Playwright MCP tools (playwright/*) to 6 browser-capable agents: ui-design, execute, tdd, debug, verify, review - Migrate output paths from docs/plans/ and docs/ux/ to .github/superpower/ (brainstorm/, ux/, context/, plan/) - Add inter-agent artifact discovery: plan reads from brainstorm/ and context/, execute reads from plan/ - Update both English and Chinese READMEs with output path conventions and optional Playwright MCP configuration instructions - Bump version to 2.2.0 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1 parent d007a6d commit da0d33a

16 files changed

Lines changed: 231 additions & 130 deletions

README.md

Lines changed: 112 additions & 44 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,8 @@
11
# Superpower Copilot
22

3-
**9 structured AI workflow agents for GitHub Copilot Chat**
3+
[中文文档](readme-zh.md)
4+
5+
**13 structured AI workflow agents for GitHub Copilot Chat**
46

57
Superpower Copilot brings disciplined, process-driven development workflows to GitHub Copilot through VS Code's [Custom Agents](https://code.visualstudio.com/docs/copilot/chat/chat-agents) feature. Each agent enforces a specific development practice — from brainstorming and planning to TDD, debugging, and code review — so you can work with the same rigor that professional engineering teams demand.
68

@@ -13,54 +15,76 @@ GitHub Copilot is powerful, but it lacks opinionated development workflows. With
1315
- Debugging by guessing instead of systematic root-cause analysis
1416
- Claiming work is "done" without verification
1517

16-
Superpower Copilot solves this by providing 9 agents, each with a rigorous system prompt (200-300 lines) that enforces best practices. The agents are inspired by the [Superpowers](https://github.com/cline/superpowers) skill framework and adapted for GitHub Copilot's agent architecture.
18+
Superpower Copilot solves this by providing 13 agents, each with a rigorous system prompt (200-300 lines) that enforces best practices. The agents are inspired by the [Superpowers](https://github.com/cline/superpowers) skill framework and the [awesome-copilot](https://github.com/github/awesome-copilot) community, adapted for GitHub Copilot's agent architecture.
19+
20+
## The 13 Agents
21+
22+
### Core Workflow Chain
23+
24+
| Agent | Purpose |
25+
|-------|---------|
26+
| `superpower-brainstorm` — Explore Ideas & Design | Explore ideas, clarify requirements, produce design documents |
27+
| `superpower-plan` — Step-by-Step Plan | Break designs into bite-sized, testable implementation tasks |
28+
| `superpower-execute` — Execute Plans | Execute plans step by step in batches with review checkpoints |
29+
| `superpower-verify` — Evidence Before Claims | Run all verification commands before claiming completion |
30+
| `superpower-finish` — Merge, PR, or Discard | Structured options for completing a development branch |
31+
32+
### Discipline Agents (use anytime)
33+
34+
| Agent | Purpose |
35+
|-------|---------|
36+
| `superpower-tdd` — Red-Green-Refactor | Test-Driven Development with strict cycle discipline |
37+
| `superpower-debug` — Root Cause First | 4-phase systematic debugging: investigate before fixing |
38+
| `superpower-review` — Code Review | Structured review against plan and requirements |
39+
| `superpower-respond` — Address Feedback | Process review feedback with technical rigor |
1740

18-
## The 9 Agents
41+
### New: Thinking & Design Agents
1942

2043
| Agent | Purpose |
2144
|-------|---------|
22-
| `@superpower-brainstorm` | Explore ideas, clarify requirements, produce design documents |
23-
| `@superpower-plan` | Break designs into bite-sized, testable implementation tasks |
24-
| `@superpower-execute` | Execute plans step by step in batches with review checkpoints |
25-
| `@superpower-verify` | Run all verification commands before claiming completion |
26-
| `@superpower-finish` | Merge, create PR, keep branch, or discard — structured options |
27-
| `@superpower-tdd` | Red-Green-Refactor cycle with strict discipline |
28-
| `@superpower-debug` | 4-phase systematic debugging: root cause before fixes |
29-
| `@superpower-review` | Structured code review against plan and requirements |
30-
| `@superpower-respond` | Process review feedback with technical rigor, not blind agreement |
45+
| `superpower-ui-design` — UX Research | Jobs-to-be-Done analysis, user journey mapping, flow specs |
46+
| `superpower-think` — Challenge Assumptions | Socratic questioning — only asks Why, never gives answers |
47+
| `superpower-mentor` — Guided Learning | Teach through hints and questions, not direct answers |
48+
| `superpower-context` — Dependency Mapping | Map affected files and ripple effects before multi-file changes |
3149

3250
## Recommended Workflow
3351

34-
The agents are designed to work as a chain. Start from the left and move right:
52+
The agents are designed to work as a chain. Each agent knows about the others and suggests handoffs:
3553

3654
```
3755
brainstorm → plan → execute → verify → finish
38-
39-
tdd / debug (as needed)
56+
57+
ui-design context tdd / debug (as needed)
4058
4159
review → respond
60+
61+
think / mentor — use anytime to challenge thinking
4262
```
4363

4464
**Full feature workflow:**
4565

46-
1. `@superpower-brainstorm` — Explore the problem, ask questions, produce a design doc
47-
2. `@superpower-plan` — Turn the design into a step-by-step implementation plan
48-
3. `@superpower-execute` — Implement the plan in batches of 3 tasks
49-
4. `@superpower-verify` — Run tests, linter, build — evidence before claims
50-
5. `@superpower-finish` — Merge locally, create PR, or keep branch
66+
1. `superpower-brainstorm` — Explore the problem, ask questions, produce a design doc
67+
2. `superpower-ui-design` — If the feature has UI, do UX research first
68+
3. `superpower-context` — Map dependencies before multi-file changes
69+
4. `superpower-plan` — Turn the design into a step-by-step implementation plan
70+
5. `superpower-execute` — Implement the plan in batches of 3 tasks
71+
6. `superpower-verify` — Run tests, linter, build — evidence before claims
72+
7. `superpower-finish` — Merge locally, create PR, or keep branch
5173

5274
**Standalone agents** (use anytime):
5375

54-
- `@superpower-tdd` — When building any new functionality
55-
- `@superpower-debug` — When something breaks
56-
- `@superpower-review` — Before merging
57-
- `@superpower-respond` — When processing review feedback
76+
- `superpower-tdd` — When building any new functionality
77+
- `superpower-debug` — When something breaks
78+
- `superpower-review` — Before merging
79+
- `superpower-respond` — When processing review feedback
80+
- `superpower-think` — When you need to challenge your assumptions
81+
- `superpower-mentor` — When learning a codebase or teaching someone
5882

5983
## Installation
6084

6185
1. Install **Superpower Copilot** from the [VS Code Marketplace](https://marketplace.visualstudio.com/items?itemName=rainlei.superpower-copilot)
62-
2. The extension copies 9 agent files to `~/.superpower-copilot/agents/` and registers them globally
63-
3. Open Copilot Chat and select any `@superpower-*` agent from the dropdown
86+
2. The extension copies 13 agent files to `~/.superpower-copilot/agents/` and registers them globally
87+
3. Open Copilot Chat and select any `superpower-*` agent from the dropdown
6488

6589
## Requirements
6690

@@ -69,21 +93,24 @@ brainstorm → plan → execute → verify → finish
6993

7094
## Usage
7195

72-
Open Copilot Chat (Ctrl+Shift+I / Cmd+Shift+I) and type:
96+
1. Open Copilot Chat panel: `Ctrl+Alt+I` (Windows/Linux) / `Cmd+Alt+I` (Mac)
97+
2. Click the agent dropdown at the top of the chat panel
98+
3. Select a `superpower-*` agent from the list
99+
4. Type your request and send
73100

74-
```
75-
@superpower-brainstorm I need to add user authentication to my Express app
76-
```
101+
**Examples:**
77102

78-
```
79-
@superpower-tdd Implement a shopping cart with add/remove/total
80-
```
103+
| Agent | Example prompt |
104+
|-------|---------------|
105+
| `superpower-brainstorm` | "I need to add user authentication to my Express app" |
106+
| `superpower-tdd` | "Implement a shopping cart with add/remove/total" |
107+
| `superpower-debug` | "Why is the checkout endpoint returning 500?" |
108+
| `superpower-think` | "Should we use microservices or a monolith?" |
109+
| `superpower-ui-design` | "Design the onboarding flow for our mobile app" |
110+
| `superpower-context` | "I need to refactor the auth module across multiple files" |
111+
| `superpower-mentor` | "Help me understand how the middleware chain works" |
81112

82-
```
83-
@superpower-debug Why is the checkout endpoint returning 500?
84-
```
85-
86-
The agent will guide you through its process step by step. Each agent enforces gates — for example, `@superpower-debug` will not let you propose fixes until root cause investigation is complete.
113+
The agent will guide you through its process step by step. Each agent enforces gates — for example, `superpower-debug` will not let you propose fixes until root cause investigation is complete.
87114

88115
## What Makes These Agents Different
89116

@@ -95,31 +122,72 @@ The agent will guide you through its process step by step. Each agent enforces g
95122

96123
**Workflow handoffs.** Agents include handoff buttons that connect to the next logical step in the chain.
97124

125+
**Inter-agent awareness.** Each agent knows about the others and includes Related Agents references in its description, so Copilot can suggest the right agent for the next step.
126+
98127
## Best Practices
99128

100129
- **Start with brainstorm** for any non-trivial feature. Spending 10 minutes on design saves hours of rework.
101-
- **Use TDD for all new code.** The `@superpower-tdd` agent enforces Red-Green-Refactor. If you didn't see the test fail, you don't know it tests the right thing.
102-
- **Verify before claiming done.** The `@superpower-verify` agent requires running commands and showing output. No "should work" or "looks correct".
103-
- **Debug systematically.** When something breaks, resist the urge to guess. Use `@superpower-debug` to trace root cause first.
104-
- **Review your own work.** Use `@superpower-review` before creating a PR. It catches issues you missed.
130+
- **Map context first** for multi-file changes. Use `superpower-context` before `superpower-plan`.
131+
- **Do UX research** before building UI. Use `superpower-ui-design` to understand users first.
132+
- **Use TDD for all new code.** The `superpower-tdd` agent enforces Red-Green-Refactor. If you didn't see the test fail, you don't know it tests the right thing.
133+
- **Verify before claiming done.** The `superpower-verify` agent requires running commands and showing output. No "should work" or "looks correct".
134+
- **Debug systematically.** When something breaks, resist the urge to guess. Use `superpower-debug` to trace root cause first.
135+
- **Challenge your thinking.** Use `superpower-think` when a decision feels too easy — it will expose blind spots.
136+
- **Review your own work.** Use `superpower-review` before creating a PR. It catches issues you missed.
105137

106138
## How It Works
107139

108140
On activation, the extension:
109141

110-
1. Copies 9 `.agent.md` files from the extension bundle to `~/.superpower-copilot/agents/`
142+
1. Copies 13 `.agent.md` files from the extension bundle to `~/.superpower-copilot/agents/`
111143
2. Registers the path `~/.superpower-copilot/agents` in VS Code's `chat.agentFilesLocations` setting (user-level)
112144
3. VS Code discovers the agents and adds them to the Copilot Chat dropdown
113145

114146
On deactivation, the extension cleans up the copied files and removes the setting entry.
115147

148+
### Agent Output Artifacts
149+
150+
Agents that produce documents (brainstorm, ui-design, context, plan) save their output to `.github/superpower/` in your workspace:
151+
152+
```
153+
.github/superpower/
154+
brainstorm/YYYY-MM-DD-<topic>-design.md
155+
ux/[feature]-jtbd.md
156+
ux/[feature]-journey.md
157+
ux/[feature]-flow.md
158+
context/YYYY-MM-DD-<topic>-context-map.md
159+
plan/YYYY-MM-DD-<topic>-plan.md
160+
```
161+
162+
Agents discover each other's artifacts automatically:
163+
- `superpower-plan` reads from `brainstorm/` and `context/`
164+
- `superpower-execute` reads from `plan/`
165+
- `superpower-verify` and `superpower-review` read from `plan/`
166+
167+
### Playwright MCP (Optional)
168+
169+
For agents that interact with browsers (ui-design, debug, verify, execute, tdd, review), you can optionally configure the [Playwright MCP](https://github.com/anthropics/playwright-mcp) server. Add to your `.vscode/settings.json`:
170+
171+
```json
172+
{
173+
"mcpServers": {
174+
"playwright": {
175+
"command": "npx",
176+
"args": ["@anthropic-ai/playwright-mcp@latest"]
177+
}
178+
}
179+
}
180+
```
181+
182+
This enables browser automation tools (`playwright/*`) for UI testing, visual verification, and frontend debugging. If not configured, agents work normally without browser capabilities.
183+
116184
## Language Support
117185

118186
All agents support both English and Simplified Chinese.
119187

120188
## Credits
121189

122-
Inspired by the [Superpowers](https://github.com/cline/superpowers) skill framework. Adapted from shell-based skills to VS Code Custom Agents with native Copilot integration (tools, handoffs, agent references).
190+
Inspired by the [Superpowers](https://github.com/cline/superpowers) skill framework and the [awesome-copilot](https://github.com/github/awesome-copilot) community collection. Adapted for GitHub Copilot's Custom Agents with native integration (tools, handoffs, agent references).
123191

124192
## License
125193

agents/superpower-brainstorm.agent.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: >
55
architecture design, feature planning, requirement analysis.
66
Related: @superpower-ui-design (UX research), @superpower-plan (next step), @superpower-think (challenge assumptions).
77
Keywords: idea, design, brainstorm, explore, architect, requirement, feature, plan idea
8-
tools: ['search', 'read', 'fetch']
8+
tools: ['codebase', 'textSearch', 'fileSearch', 'readFile', 'listDirectory', 'usages', 'searchResults', 'changes', 'problems', 'editFiles', 'createFile', 'createDirectory', 'fetch', 'githubRepo']
99
handoffs:
1010
- label: Create Implementation Plan
1111
agent: superpower-plan
@@ -37,7 +37,7 @@ Every project goes through this process. A todo list, a single-function utility,
3737
2. **Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria
3838
3. **Propose 2-3 approaches** — with trade-offs and your recommendation
3939
4. **Present design** — in sections scaled to complexity, get user approval after each section
40-
5. **Save design doc** — to `docs/plans/YYYY-MM-DD-<topic>-design.md`
40+
5. **Save design doc** — to `.github/superpower/brainstorm/YYYY-MM-DD-<topic>-design.md`
4141
6. **Hand off to planning** — use the handoff button to transition to superpower-plan
4242

4343
## Process Flow
@@ -85,7 +85,7 @@ digraph brainstorming {
8585
- Go back and clarify if something doesn't make sense
8686

8787
### After Approval
88-
- Save design to `docs/plans/YYYY-MM-DD-<topic>-design.md`
88+
- Save design to `.github/superpower/brainstorm/YYYY-MM-DD-<topic>-design.md`
8989
- Use the handoff button to transition to superpower-plan
9090
- Do NOT invoke any other agent. superpower-plan is the next step.
9191

agents/superpower-context.agent.md

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ description: >
44
Map dependencies and impact before multi-file changes. Identifies affected files,
55
traces ripple effects, finds patterns, and sequences changes safely.
66
Keywords: context, dependency, impact, refactor, multi-file, change, architecture, map
7-
tools: ['search', 'read', 'execute']
7+
tools: ['codebase', 'textSearch', 'fileSearch', 'readFile', 'listDirectory', 'usages', 'searchResults', 'changes', 'problems', 'editFiles', 'createFile', 'createDirectory', 'runInTerminal', 'terminalLastCommand', 'getTerminalOutput']
88
handoffs:
99
- label: Create Implementation Plan
1010
agent: superpower-plan
@@ -46,7 +46,8 @@ Multi-file changes without dependency mapping cause cascading failures. "I'll ju
4646
5. **Discover patterns** — how similar changes were done before
4747
6. **Sequence changes** — optimal order to avoid breaking intermediate states
4848
7. **Present context map** — structured summary for user approval
49-
8. **Hand off** — to superpower-plan with the approved context map
49+
8. **Save context map** — to `.github/superpower/context/YYYY-MM-DD-<topic>-context-map.md`
50+
9. **Hand off** — to superpower-plan with the approved context map
5051

5152
## The Process
5253

agents/superpower-debug.agent.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: >
55
Use when encountering bugs, test failures, unexpected behavior, or errors.
66
Related: @superpower-think (challenge hypotheses), @superpower-tdd (write regression test), @superpower-verify (verify fix).
77
Keywords: bug, error, fail, broken, crash, debug, investigate, diagnose, trace
8-
tools: ['search', 'read', 'edit', 'execute']
8+
tools: ['codebase', 'textSearch', 'fileSearch', 'readFile', 'listDirectory', 'usages', 'searchResults', 'changes', 'problems', 'editFiles', 'createFile', 'createDirectory', 'runInTerminal', 'terminalLastCommand', 'getTerminalOutput', 'runTests', 'testFailure', 'playwright/*']
99
---
1010

1111
# Systematic Debugging Protocol

agents/superpower-execute.agent.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: >
55
Use after planning to implement features with continuous verification.
66
Related: @superpower-plan (previous step), @superpower-tdd (TDD cycle), @superpower-verify (next step).
77
Keywords: execute, implement, build, code, make, create, do, work on
8-
tools: ['search', 'read', 'edit', 'execute', 'agent']
8+
tools: ['codebase', 'textSearch', 'fileSearch', 'readFile', 'listDirectory', 'usages', 'searchResults', 'changes', 'problems', 'editFiles', 'createFile', 'createDirectory', 'runInTerminal', 'terminalLastCommand', 'getTerminalOutput', 'runTests', 'testFailure', 'todos', 'agent', 'playwright/*']
99
handoffs:
1010
- label: Verify Implementation
1111
agent: superpower-verify
@@ -33,7 +33,7 @@ The plan was written for a reason. You are the execution engine, not the decisio
3333

3434
## Checklist
3535

36-
1. **Load the plan** — find and read `docs/plans/YYYY-MM-DD-<topic>-plan.md`
36+
1. **Load the plan** — find and read `.github/superpower/plan/YYYY-MM-DD-<topic>-plan.md`
3737
2. **Review critically** — check for ambiguities, missing details, unclear steps
3838
3. **Check branch** — never start on main/master without explicit consent
3939
4. **Execute in batches** — do 3 tasks, report status, get approval, continue
@@ -81,7 +81,7 @@ digraph execution {
8181

8282
### Loading the Plan
8383

84-
1. Search for plan file: `docs/plans/YYYY-MM-DD-*.md`
84+
1. Search for plan file in `.github/superpower/plan/` — list the directory to find the latest plan
8585
2. Read the entire plan before starting
8686
3. Check for:
8787
- Goal and architecture sections

agents/superpower-finish.agent.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: >
55
merge locally, create PR, keep branch, or discard. Verify tests first.
66
Related: @superpower-verify (previous step), @superpower-review (optional next step).
77
Keywords: finish, complete, merge, pr, pull request, done, wrap up, cleanup
8-
tools: ['search', 'read', 'execute']
8+
tools: ['codebase', 'textSearch', 'fileSearch', 'readFile', 'listDirectory', 'usages', 'searchResults', 'changes', 'problems', 'runInTerminal', 'terminalLastCommand', 'getTerminalOutput']
99
handoffs:
1010
- label: Request Code Review
1111
agent: superpower-review
@@ -234,7 +234,7 @@ git push -u origin feature/add-login
234234
# Create PR using gh CLI (if available)
235235
gh pr create \
236236
--title "Add login functionality" \
237-
--body "$(cat docs/plans/2026-02-20-add-login-design.md)" \
237+
--body "$(cat .github/superpower/brainstorm/2026-02-20-add-login-design.md)" \
238238
--base main \
239239
--head feature/add-login
240240
```
@@ -426,7 +426,7 @@ git push -u origin feature/add-auth
426426
# Then create PR
427427
gh pr create \
428428
--title "Add authentication system" \
429-
--body "Implements user authentication with JWT tokens. See docs/plans/2026-02-20-auth-design.md for details." \
429+
--body "Implements user authentication with JWT tokens. See .github/superpower/brainstorm/2026-02-20-auth-design.md for details." \
430430
--base main \
431431
--head feature/add-auth
432432

agents/superpower-mentor.agent.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ description: >
44
Guided learning through hints and questions, not direct answers.
55
Helps engineers grow by challenging assumptions and building understanding.
66
Keywords: mentor, teach, learn, guide, help, explain, understand, hint, grow
7-
tools: ['search', 'read', 'fetch']
7+
tools: ['codebase', 'textSearch', 'fileSearch', 'readFile', 'listDirectory', 'usages', 'searchResults', 'changes', 'problems', 'fetch', 'githubRepo']
88
---
99

1010
# Mentor Mode

0 commit comments

Comments
 (0)