Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/transparent-pegasus/herdrpowers/requesting-code-reviewnpx skills add transparent-pegasus/herdrpowers --skill requesting-code-reviewgit clone --depth 1 https://github.com/transparent-pegasus/herdrpowersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/transparent-pegasus/herdrpowers/requesting-code-review)<a href="https://agentmods.dev/skills/transparent-pegasus/herdrpowers/requesting-code-review"><img src="https://agentmods.dev/badge/skills/transparent-pegasus/herdrpowers/requesting-code-review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00022 | $0.01343 |
| Opus 5 | $0.00011 | $0.00672 |
| Sonnet 5 | $0.00004 | $0.00269 |
| Haiku 4.5 | $0.00002 | $0.00134 |
Grade A, and why
requesting-code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
BASE_SHA=$(git merge-base <BASE_BRANCH> HEAD) # or the commit recorded before the task
HEAD_SHA=$(git rev-parse HEAD)
../pane-driven-development/scripts/review-package "$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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 107 lines · 22 tokens per session scan A ca3a18c99fd4
requesting-code-review is a skill published in the GitHub repository transparent-pegasus/herdrpowers (11 stars, last pushed 8d ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,343 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
plannotator-tui
Open a Markdown plan or document for the human to review and annotate in a Herdr pane; their feedback arrives as your next message. Use when you have written a plan, spec, or design document that needs human review before you act on it.
compound-v
Use when superpowers:brainstorming is about to begin (pre-brainstorm recon), OR has produced a spec, OR when superpowers:writing-plans has produced a plan, OR when about to invoke superpowers:subagent-driven-development or superpowers:executing-plans. Sidekick that intercepts these four Superpowers transitions — runs…
backend-launcher
Use when Compound V's dispatcher needs to run one file-scoped job on a chosen backend (Claude subagent, headless Codex worker, headless Antigravity worker, headless Cursor worker, headless Devin worker, or headless opencode worker) and get back a canonical jobresult. The single jobspec → jobresult contract every…
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session.
write-documentation
Use when writing or substantially rewriting human-facing prose: documentation, README, guides, blog posts, emails, Slack messages, PR descriptions, release notes, or any text a human will read. Not for code comments, commit messages, or agent-to-agent communication.
research-driven-development
Use when the user asks a question about a topic, requests research, or when understanding something is needed before planning. Triggers on "research this", "what is X", "how does Y work", "compare A vs B", "investigate", "deep dive", "look into".