polisade-review-pr

polisade-review-pr is a command for Claude Code from cryndoc/polisade-orchestrator. It costs 102 tokens per session (9,105 once invoked), scanned A, original, Apache-2.0.

A command that reviews an open pull request, a proposed set of code changes, through a separate agent running with a clean context. It posts a quality verdict and can locate the pull request from a task identifier or the current branch.

In plain words
What is it for?
Use it to review a pull request by number, task ID, or current branch, including reviews performed by a separate agent.
Why use it?
An independent review can catch problems the agent that wrote the code may overlook. It supports a workflow of implementing changes, reviewing them, fixing findings, and merging.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

Part of the polisade plugin — 25 skills, 2 commands shipped together

Good fit Use it to review a pull request by number, task ID, or current branch, including reviews performed by a separate agent.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/cryndoc/polisade-orchestrator/polisade-review-pr
Install

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.

Clone the repo
git clone --depth 1 https://github.com/cryndoc/polisade-orchestrator

Made for: Claude Code.

Or install polisade, the plugin that ships this one along with the rest of its 25 skills, 2 commands.

Wrote 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.

agentmods badge for polisade-review-pr

README.md
[![agentmods](https://agentmods.dev/badge/commands/cryndoc/polisade-orchestrator/polisade-review-pr/github.svg)](https://agentmods.dev/commands/cryndoc/polisade-orchestrator/polisade-review-pr)
Your own site
<a href="https://agentmods.dev/commands/cryndoc/polisade-orchestrator/polisade-review-pr"><img src="https://agentmods.dev/badge/commands/cryndoc/polisade-orchestrator/polisade-review-pr/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for polisade-review-pr

Your own site · 80×15
<a href="https://agentmods.dev/commands/cryndoc/polisade-orchestrator/polisade-review-pr"><img src="https://agentmods.dev/badge/commands/cryndoc/polisade-orchestrator/polisade-review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,105 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.09105
Opus 5 $0.00051 $0.04553
Sonnet 5 $0.00020 $0.01821
Haiku 4.5 $0.00010 $0.00911

Measured 2d ago against content hash 21a9eb74f9e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

polisade-review-pr scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> Bare `git push` запрещён (инвариант #10 / OPS-028); самодельные REST/curl-вызовы к Bitbucket/GitHub запрещены; helper не транскрибируется в `/tmp`.
tools/opencode-overlay/commands/polisade-review-pr.md · 635 lines

How it starts

The opening of the file, as written. The whole thing — 635 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Независимый quality review Pull Request через изолированный opencode-субагент. Внешняя проверка кода как второе мнение — не self-review основного агента, а отдельный субагент в чистом контексте.

Флаг self — принимается для совместимости с Claude Code / Codex. В opencode-сборке review всегда выполняется субагентом в чистом контексте (поведение при self идентично поведению по умолчанию).

Цикл: implement → PR → review-pr → fix замечаний → merge

Использование

/polisade-review-pr 42             # Review PR #42
/polisade-review-pr TASK-001       # Найти PR для TASK-001
/polisade-review-pr                # Review PR текущей ветки
/polisade-review-pr 42 self        # То же (self — default для opencode)
/polisade-review-pr TASK-001 self  # PR для TASK + self
/polisade-review-pr self           # Текущая ветка + self

Аргументы передаются через $ARGUMENTS (как в Claude Code).

Архитектура

/polisade-review-pr 42
         |
         v
+-----------------------------------------+
|  ОСНОВНОЙ АГЕНТ                          |
|  1. Определить PR# и TASK-ID             |
|  2. Запустить Review субагент (Task tool)|
+-----------------+-----------------------+
                  v
+-----------------------------------------+
|  СУБАГЕНТ (изолированный контекст)        |
|  Чистый контекст. Сам:                   |
|   1. Pre-fetch: gh pr diff, gh pr view   |
|   2. Читает TASK, parent, гайдлайны      |
|   3. Анализирует diff и тесты            |
|   4. Формирует ревью по критериям 1-10   |
|   5. gh pr comment: публикует в PR       |
|  Возвращает ревью с score и findings     |
+-----------------+-----------------------+
                  v
+-----------------------------------------+
|  ОСНОВНОЙ АГЕНТ                          |
|  Score >= 8 → merge                      |
|  Score < 8 →                             |
|    Improvement субагент → fix            |
|    → Re-review субагент (макс. 2 итер.)  |
|  → After 2 iterations: STOP + waiting_pm |
+-----------------------------------------+

Read the full file on GitHub · 635 lines

Changes

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.

  1. 2d ago Changed · +175 lines 21a9eb74f9e4
  2. 10d ago First seen · 460 lines · 102 tokens per session scan A 4595a0d5cf5b

Subscribe to this mod's changes

polisade-review-pr is a command published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed today), licensed Apache-2.0. It adds 102 tokens to every session and 9,105 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.