Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Code Review Subagent Dispatcher

agent coding skill risk: low

Code Review Subagent Dispatcher

Instructs on mandatory and optional scenarios for requesting code reviews during development, and details steps to obtain git SHAs then dispatch a code reviewer subagent via the Ta…

SKILL 2 files

SKILL.md
---
name: requesting-code-review
description: "Use when completing tasks, implementing major features, or before merging to verify work meets requirements"
---
# Requesting Code Review

Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.

**Core principle:** Review early, review often.

## When to Request Review

**Mandatory:**
- After each task in subagent-driven development
- After completing major feature
- Before merge to main

**Optional but valuable:**
- When stuck (fresh perspective)
- Before refactoring (baseline check)
- After fixing complex bug

## How to Request

**1. Get git SHAs:**
```bash
BASE_SHA=$(git rev-parse HEAD~1)  # or origin/main
HEAD_SHA=$(git rev-parse HEAD)
```

**2. Dispatch code reviewer subagent:**

Use Task tool with `general-purpose` type, fill template at `code-reviewer.md`

**Placeholders:**
- `{DESCRIPTION}` - Brief summary of what you built
- `{PLAN_OR_REQUIREMENTS}` - What it should do
- `{BASE_SHA}` - Starting commit
- `{HEAD_SHA}` - Ending commit

**3. Act on feedback:**
- Fix Critical issues immediately
- Fix Important issues before proceeding
- Note Minor issues for later
- Push back if reviewer is wrong (with reasoning)

## Example

```
[Just completed Task 2: Add verification function]

You: Let me request code review before proceeding.

BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)

[Dispatch code reviewer subagent]
  DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
  PLAN_OR_REQUIREMENTS: Task 2 from docs/superpowers/plans/deployment-plan.md
  BASE_SHA: a7981ec
  HEAD_SHA: 3df7661

[Subagent returns]:
  Strengths: Clean architecture, real tests
  Issues:
    Important: Missing progress indicators
    Minor: Magic number (100) for reporting interval
  Assessment: Ready to proceed

You: [Fix progress indicators]
[Continue to Task 3]
```

## Integration with Workflows

**Subagent-Driven Development:**
- Review after EACH task
- Catch issues before they compound
- Fix before moving to next task

**Executing Plans:**
- Review after each task or at natural checkpoints
- Get feedback, apply, continue

**Ad-Hoc Development:**
- Review before merge
- Review when stuck

## Red Flags

**Never:**
- Skip review because "it's simple"
- Ignore Critical issues
- Proceed with unfixed Important issues
- Argue with valid technical feedback

**If reviewer wrong:**
- Push back with technical reasoning
- Show code/tests that prove it works
- Request clarification

See template at: requesting-code-review/code-reviewer.md

INPUTS

{DESCRIPTION} REQUIRED

Brief summary of what was built

e.g. Added verifyIndex() and repairIndex() with 4 issue types

{PLAN_OR_REQUIREMENTS} REQUIRED

Reference to what the code should do

e.g. Task 2 from docs/superpowers/plans/deployment-plan.md

{BASE_SHA} REQUIRED

Starting commit SHA

e.g. a7981ec

{HEAD_SHA} REQUIRED

Ending commit SHA

e.g. 3df7661

REQUIRED CONTEXT

  • git BASE_SHA and HEAD_SHA
  • DESCRIPTION of changes
  • PLAN_OR_REQUIREMENTS reference

TOOLS REQUIRED

  • Task tool

ROLES & RULES

  1. Dispatch a code reviewer subagent to catch issues before they cascade
  2. never your session's history
  3. Review early, review often
  4. Fix Critical issues immediately
  5. Fix Important issues before proceeding
  6. Note Minor issues for later
  7. Push back if reviewer is wrong (with reasoning)
  8. Never skip review because it is simple
  9. Never ignore Critical issues
  10. Never proceed with unfixed Important issues
  11. Never argue with valid technical feedback

EXPECTED OUTPUT

Format
markdown
Constraints
  • follow the described workflow steps
  • use placeholders for DESCRIPTION, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA

SUCCESS CRITERIA

  • Review after each task in subagent-driven development
  • Review after completing major feature
  • Review before merge to main
  • Act on feedback by fixing Critical and Important issues

FAILURE MODES

  • Skip review because it is simple
  • Ignore Critical issues
  • Proceed with unfixed Important issues
  • Argue with valid technical feedback

EXAMPLES

Includes one detailed example of requesting review after Task 2, showing git SHA commands, subagent dispatch, sample feedback, and follow-up actions.

CAVEATS

Dependencies
  • Requires git repository with commit history
  • Requires code-reviewer.md template
  • Requires Task tool with general-purpose type
  • Requires prior task completion or feature work
Missing context
  • The content or structure of the referenced code-reviewer.md template
  • Exact parameters and syntax of the Task tool
Ambiguities
  • 'general-purpose' type
  • fill template at `code-reviewer.md`
  • Use Task tool

QUALITY

OVERALL
0.78
CLARITY
0.88
SPECIFICITY
0.78
REUSABILITY
0.82
COMPLETENESS
0.65

IMPROVEMENT SUGGESTIONS

  • Embed or inline the code-reviewer.md template content so the prompt is self-contained.
  • Provide the exact Task tool call format including all required arguments.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT