hydraia-reviewer

hydraia-reviewer is an agent for Claude Code from jdanigo/hydraia. It costs 42 tokens per session (211 once invoked), scanned A, original, MIT.

A whole-branch review agent for Hydraia Phase 5, checking whether a completed feature follows its specification and works correctly.

In plain words
What is it for?
Use it to review a feature branch for specification compliance, correctness, code quality, test coverage, and coupling with other parts of the project.
Why use it?
It provides an independent check for missed requirements, edge cases, hidden dependencies, weak tests, and unnecessary complexity.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

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

Good fit Use it to review a feature branch for specification compliance, correctness, code quality, test coverage, and coupling with other parts of the project.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jdanigo/hydraia/hydraia-reviewer
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/jdanigo/hydraia

Made for: Claude Code.

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 hydraia-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jdanigo/hydraia/hydraia-reviewer/github.svg)](https://agentmods.dev/agents/jdanigo/hydraia/hydraia-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jdanigo/hydraia/hydraia-reviewer"><img src="https://agentmods.dev/badge/agents/jdanigo/hydraia/hydraia-reviewer/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 hydraia-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jdanigo/hydraia/hydraia-reviewer"><img src="https://agentmods.dev/badge/agents/jdanigo/hydraia/hydraia-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 211 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00042 $0.00211
Opus 5 $0.00021 $0.00105
Sonnet 5 $0.00008 $0.00042
Haiku 4.5 $0.00004 $0.00021

Measured 10d ago against content hash ecba1e413c1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hydraia-reviewer 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 10d 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.

agents/hydraia-reviewer.md · 18 lines

What it actually says

You are a senior reviewer doing the first of two independent review passes on a completed feature branch. You receive the spec, the plan, and the diff — never the implementer's session history.

Review for:

  • Spec compliance: does it do what the Phase 2 spec required, no more, no less?
  • Correctness and edge cases; silent failures and swallowed errors.
  • Hidden coupling and blast radius — cross-check against the code graph.
  • Test adequacy: are the important paths actually covered?
  • Simplicity: flag over-engineering and unnecessary breadth.

Output findings ranked material → minor. For each: file, line, what's wrong, suggested fix. Be direct. Do not rubber-stamp.

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. 10d ago First seen · 18 lines · 42 tokens per session scan A ecba1e413c1b

Subscribe to this mod's changes

hydraia-reviewer is an agent published in the GitHub repository jdanigo/hydraia (8 stars, last pushed 20d ago), licensed MIT. It adds 42 tokens to every session and 211 once invoked, about $0.0002 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.