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.
git clone --depth 1 https://github.com/cryndoc/polisade-orchestratorWrote 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/commands/cryndoc/polisade-orchestrator/polisade-review)<a href="https://agentmods.dev/commands/cryndoc/polisade-orchestrator/polisade-review"><img src="https://agentmods.dev/badge/commands/cryndoc/polisade-orchestrator/polisade-review/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.
<a href="https://agentmods.dev/commands/cryndoc/polisade-orchestrator/polisade-review"><img src="https://agentmods.dev/badge/commands/cryndoc/polisade-orchestrator/polisade-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00099 | $0.02756 |
| Opus 5 | $0.00049 | $0.01378 |
| Sonnet 5 | $0.00020 | $0.00551 |
| Haiku 4.5 | $0.00010 | $0.00276 |
Grade A, and why
polisade-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 yesterday.
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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
"Второе мнение" по качеству постановки задачи. Независимый opencode-субагент в чистом контексте проверяет TASK на полноту, корректность и пригодность для автономной реализации агентом.
Read-only — ничего не модифицируется. Это advisory review.
Флаг
self— принимается для совместимости с Claude Code / Codex. В opencode-сборке review всегда выполняется субагентом в чистом контексте (этот файл имеетsubtask: true, поэтому команда исполняется изолированным субагентом; поведение приselfидентично поведению по умолчанию).
Использование
/polisade-review TASK-001 # Review конкретной задачи
/polisade-review # Auto-select первый ready TASK
/polisade-review TASK-001 self # То же (self — default для opencode)
/polisade-review self # Auto-select + self-review
Аргументы передаются через $ARGUMENTS (как в Claude Code).
Архитектура
/polisade-review TASK-001
|
v
+-----------------------------------------+
| СУБАГЕНТ (изолированный контекст) |
| Чистый контекст. Сам: |
| - Определяет TASK-ID |
| ($ARGUMENTS или auto-select ready) |
| - Находит TASK файл |
| - Определяет parent из frontmatter |
| - Читает гайдлайны из корня проекта |
| - Читает код/тесты при необходимости |
| Возвращает текст ревью |
+-----------------+-----------------------+
v
+-----------------------------------------+
| Показать результат в формате box |
+-----------------------------------------+
Алгоритм
1. Определить TASK-ID и режим
⛔ Вызов скрипта отклонён или не запустился (
Command references protected path/Install directory is read-protected/Filesystem Guard/the tool's default permission is 'deny', отказ песочницы, ненулевой exit без вывода) — STOP. Процитируй отказ дословно. НЕ пересказывай по исходнику, что скрипт «сделал бы»; НЕ собирай dry-run вручную; НЕ переходи к apply/push/pr-create. НЕ транскрибируй скрипт (прочитать → записать копию в/tmpили в проект → запустить копию): копия не байт-идентична — уезжают классы символов в regex, форма возврата функций, пропадают целые функции — и молча меняется набор применённых изменений. Отказ инструмента — это отказ, а не результат. Доложи PM дословный текст отказа и сошлись на #127 (доставка скриптов в проект).
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.
- yesterday Changed · +48 lines c663c4416372
- 9d ago First seen · 150 lines · 99 tokens per session scan A e6b7ae0bd827
polisade-review is a command published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 2,756 once invoked, about $0.0005 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 2026-08-31.
Other commands, from other repositories
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
audit
Onboard an existing codebase: every domain's checks over the whole tree, then a triaged plan to bring it in line.
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
done
Finish a task - document, create PR or merge, close.