requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Skill by transparent-pegasus
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/transparent-pegasus-requesting-code-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/requesting-code-review
What's inside
- Skill name
requesting-code-review- Description
- Use when completing tasks, implementing major features, or before merging to verify work meets requirements
- License
- MIT
- Instructions
- 104 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- review-brief.md
SKILL.md (first lines)
# Requesting Code Review
**Placeholder resolution:** `<KEY>` placeholders in this file (such as `<BASE_BRANCH>`) resolve from the `Herdrpowers Configuration` section of the repository's `CLAUDE.md` / `AGENTS.md`. If that section is missing, initialize it with the pack's init workflow (`/herdrpowers:init` on Claude Code plugin installs; `commands/init.md` otherwise).
Delegate the review to a **herdr sibling pane via a reset-backed submit** to catch issues before they cascade. The reviewing pane starts from a reset session, so it sees the work product and never the implementer's thought process — that is where review independence comes from in this pack, not from a separate named agent or a different pane ID.
**Core principle:** Review early, review often. Do not review your own work inside an unreset session. A reset-backed delegation may reuse any idle pane of the resolved role's agent type(s), including the pane that wrote the code.
**Gate:** the whole-branch review this skill requests is the `assignments.final-branch-review` gate; per-task reviews are `assignments.task-review`. Both resolve from `.herdrpowers/config.yaml` over the pack's `orchestration/roles.yaml` defaults — see "Delegation tasks and their assignments" in `orchestration`. When the resolved role binds to a list of agent types, the review runs once per entry, in separate panes, and their findings merge into one list. A disabled gate means the review does not run and the final report says so. It never means an unreset implementing session reviews itself.
## When to Request Review
**Mandatory:**
- After each task in pane-driven development
- After completing a major feature
- Before merge to the base branch
**Optional but valuable:**
- When stuck (fresh perspective)
- Before refactoring (baseline check)
- After fixing a complex bug
## How to Request
**1. Record the range and build the diff package:**
```bash
BASE_SHA=$(git merge-base <BASE_BRANCH> HEAD) # or the commit recorded before the task
HEAD_SHA=$(git rev-parse HEAD)
bash ../pane-driven-development/scripts/review-package "$PLAN_FILE" "$BASE_SHA" "$HEAD_SHA" # prints the path
```
`PLAN_FILE` scopes the package to that plan's workspace. In plan-less flows (`/quick`, ad-hoc reviews) pass `-`.
The package never enters your own context — you pass the path, the pane reads the file.
**2. Pick the pane:**
Resolve the gate's `role` from the merged configuration. Pick any idle pane of that role's agent type(s). The pane that implemented is fine when the submit resets the session. If no pane of the needed type is idle but one exists and is busy, wait; do not interrupt. If none exists, fall back per `orchestration`, or state in the final report that the review could not be delegated.
**3. Delegate:**
Write the review contract from [review-brief.md](review-brief.md) to a file, then submit the one-line instruction through `using-herdr-sibling-panes` (`composer-submit.sh`) and wait for the completion marker. Never submit an agent-pane prompt with `pane run`.
**Placeholders:**
- `[DESCRIPTION]` - Brief summary of what you built
- `[PLAN_OR_REQUIREMENTS]` - What it should do
- `[BASE_SHA]` / `[HEAD_SHA]` - The range under review
- `[DIFF_FILE]` - The path `review-package` printed
**4. Act on feedback:**
- Read the review from its output file, not from pane scrollback
- Fix Critical issues immediately
- Fix Important issues before proceeding
- Note Minor issues for later
- Rule on every line of the reviewer's "Declined to judge" list: each set-aside behavior either stands, with your reason, or becomes a finding. None is dropped silently
- Push back if the reviewer is wrong (with reasoning) — see `receiving-code-review`
## Example
```
[Just completed Task 2: Add verification function]
You: Delegating the review before proceeding.
BASE_SHA=a7981ec # recorded before Task 2's implementer was delegated
HEAD_SHA=3df7661
[review-package docs/plans/feature.md a7981ec 3df7661 → /repo/.herdrpowers/pdd/feature/review-a7981ec..3df7661.diff]
[Write the review contract to /repo/.herdrpowers/pdd/feature/task-2-review-brief.md]
[composer-submit.sh w2:p19 "<one-line instruction>"; pane wait-output REVIEW_OK_9C4A]
[Read /repo/.herdrpowers/pdd/feature/task-2-review.md]:
Strengths: Clean architecture, tests assert the requirement
Issues:
Important: Missing progress indicators
Minor: Magic number (100) for reporting interval
Assessment: Ready to proceed
You: [Delegate one fix with both findings]
[Continue to Task 3]
```
## Common Rationalizations
| Excuse | Reality |
|--------|---------|
| "I'll just review the diff myself instead of delegating" | You're the orchestrator — reviewing the diff inline burns the context window you need to keep driving the work, and it is not an independent review. Delegate via a reset-backed submit: the diff and the evaluation live in that session, and only the findings come back to you. |
| "The reviewing pane needs my whole session history to understand the change" | Hand it precisely crafted context, never your session's history. That keeps the review on the work product, not your thought process. |
| "The only idle pane is the one that wrote the code" | Reuse it after a reset-backed submit. Independence is the fresh session, not a different pane ID. |
## Red Flags
**Never:**
- Skip review because "it's simple"
- Review the change inside an unreset implementing session
- Submit the review prompt with `pane run`, or without a completion marker
- Accept "looks good" without a written report file
- Ignore Critical issues
- Proceed with unfixed Important issues
- Argue with valid technical feedback
**If the reviewer is wrong:**
- Push back with technical reasoning
- Show code/tests that prove it works
- Request clarification
See the template at: [review-brief.md](review-brief.md)From transparent-pegasus/herdrpowers, MIT.
More from transparent-pegasus/herdrpowers
- 0.639score
executing-plans
transparent-pegasus
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no herdr sibling…
SkillAFreshness: A★ 12Claude Code +9 - 0.639score
using-herdr-sibling-panes
transparent-pegasus
Use when inside herdr (HERDR_ENV=1), the current pane is acting as the orchestrator for the task, and idle sibling agent panes can take delegated work —…
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
herdr
transparent-pegasus
Use when the user explicitly requests Herdr pane, tab, workspace, or agent operations from an existing Herdr session.
SkillAFreshness: A★ 12Claude Code +9 - 0.630score
orchestration
transparent-pegasus
Route every task received directly from the user through the pane that received it (the orchestrator) in herdr unless the user explicitly denies orchestration.
SkillAFreshness: A★ 12Claude Code +9 - 0.611score
brainstorming
transparent-pegasus
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
SkillAFreshness: A★ 12Claude Code +9 - 0.608score
systematic-debugging
transparent-pegasus
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
SkillAFreshness: A★ 12Claude Code +9 - 0.608score
writing-plans
transparent-pegasus
Use when you have a spec or requirements for a multi-step task, before touching code
SkillAFreshness: A★ 12Claude Code +9 - 0.604score
pane-driven-development
transparent-pegasus
Use when executing implementation plans with independent tasks by delegating each task to a fresh herdr sibling pane
SkillAFreshness: A★ 12Claude Code +9 - 0.569score
finishing-a-development-branch
transparent-pegasus
Use when implementation is complete, all tests pass, and the user needs to decide how to integrate the work - presents the integration candidates (merge…
SkillBFreshness: B★ 12Claude Code +9 - 0.544score
update-docs
transparent-pegasus
Use when code, config, prompt, schema, or task changes require updating Markdown files directly under docs/, such as architecture, structure, config-sync…
SkillCFreshness: C★ 12Claude Code +9 - 0.519score
receiving-code-review
transparent-pegasus
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires…
SkillCFreshness: C★ 12Claude Code +9
Signals
- Stars
- 12
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Oct 9, 2026 (19 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from transparent-pegasus
- 0.639score
executing-plans
transparent-pegasus
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no herdr sibling…
SkillAFreshness: A★ 12Claude Code +9 - 0.639score
using-herdr-sibling-panes
transparent-pegasus
Use when inside herdr (HERDR_ENV=1), the current pane is acting as the orchestrator for the task, and idle sibling agent panes can take delegated work —…
SkillAFreshness: A★ 12Claude Code +9 - 0.633score
herdr
transparent-pegasus
Use when the user explicitly requests Herdr pane, tab, workspace, or agent operations from an existing Herdr session.
SkillAFreshness: A★ 12Claude Code +9 - 0.630score
orchestration
transparent-pegasus
Route every task received directly from the user through the pane that received it (the orchestrator) in herdr unless the user explicitly denies orchestration.
SkillAFreshness: A★ 12Claude Code +9 - 0.611score
brainstorming
transparent-pegasus
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
SkillAFreshness: A★ 12Claude Code +9 - 0.608score
systematic-debugging
transparent-pegasus
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
SkillAFreshness: A★ 12Claude Code +9
Cite this page
requesting-code-review skill. Agent Mart. https://agentmart.dev/skills/transparent-pegasus-requesting-code-review (last updated 2026-10-24)