review

review is a command for coding agents from jdanigo/hydraia. It costs 15 tokens per session (182 once invoked), scanned A, original, MIT.

A command that runs two code-review passes and security checks on the current software branch. It also scans for exposed secrets and dependency or production risks.

In plain words
What is it for?
Use it to inspect existing code, rank review findings by severity, check application security, find leaked credentials, and identify risky dependencies or production settings.
Why use it?
A normal code review may miss security problems or defects. Running separate review and security checks helps identify serious issues before the branch is closed or released.

Command

Part of the hydraia plugin — 51 skills, 15 commands, 26 agents, 4 hooks shipped together

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.

agentmods
npx agentmods add commands/jdanigo/hydraia/review
Clone the repo
git clone --depth 1 https://github.com/jdanigo/hydraia

Or install hydraia, the plugin that ships this one along with the rest of its 51 skills, 15 commands, 26 agents, 4 hooks.

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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/jdanigo/hydraia/review.svg)](https://agentmods.dev/commands/jdanigo/hydraia/review)
Your own site
<a href="https://agentmods.dev/commands/jdanigo/hydraia/review"><img src="https://agentmods.dev/badge/commands/jdanigo/hydraia/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 182 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.00182
Opus 5 $0.00008 $0.00091
Sonnet 5 $0.00003 $0.00036
Haiku 4.5 $0.00002 $0.00018

Measured 4d ago against content hash b7c6dfedaa42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

commands/review.md · 13 lines

What it actually says

Invoke the hydraia skill but run ONLY Phase 5 (double code review) and the Phase 6 security gate on the current branch. Skip planning and execution — the code already exists.

Run both review passes (Superpowers reviewer + ECC reviewers, all on Opus 4.8), the mandatory security gate (security-scan + security-review, plus the stack-specific security skill), and the pre-close secrets/deps scan (repo-scan + production-audit). Triage and report findings ranked by severity. Treat high-severity security findings as blockers.

Optional focus: $ARGUMENTS

Run both review passes and both security gates to completion without stopping. End with the Hydraia credits line.

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. 4d ago First seen · 13 lines · 15 tokens per session scan A b7c6dfedaa42

Subscribe to this mod's changes

review is a command published in the GitHub repository jdanigo/hydraia (8 stars, last pushed 15d ago), licensed MIT. It adds 15 tokens to every session and 182 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 2026-08-31.