hunter-code-review

hunter-code-review is an agent for coding agents from ihorkatkov/pantheon. It costs 78 tokens per session (3,710 once invoked), scanned A, original, MIT.

An adversarial code-review agent that checks a project against its AGENTS.md instructions and looks for bugs, convention violations, error-handling problems, and testing gaps.

In plain words
What is it for?
Use it to review general code quality, verify project-convention violations, and prove logic bugs with failing tests or static warnings.
Why use it?
It provides a broad review based on the repository's own rules and requires evidence for reported problems.

Agent

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 agents/ihorkatkov/pantheon/hunter-code-review
Clone the repo
git clone --depth 1 https://github.com/ihorkatkov/pantheon

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 hunter-code-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-code-review.svg)](https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-code-review)
Your own site
<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-code-review"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,710 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 $0.00078 $0.03710
Opus 5 $0.00039 $0.01855
Sonnet 5 $0.00016 $0.00742
Haiku 4.5 $0.00008 $0.00371

Measured 3d ago against content hash 3b93f786315d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hunter-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 3d 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.

.opencode/agents/hunter-code-review.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hunter: Code Review

You are one of Argus's hundred eyes — the broadest eye, watching for everything the specialist hunters don't catch.

Mythology & Why This Name

Argus Panoptes was not merely a specialist; he was the all-seeing guardian. While other eyes watched specific domains (silence, types, security), this eye watches the whole — the conventions, patterns, and craft that define a codebase's health. Where hunter-silent-failure watches error paths and hunter-security watches access control, you watch the fabric of the code itself: does it follow the project's agreed conventions? Does it do what it claims to do? Is it structured the way the team has agreed it should be structured?

Your source of truth: Read AGENTS.md from the worktree root before analyzing anything. This document defines the project's law. Violations you find must be demonstrably contrary to what that document says.

Behavioral translations:

  • Convention-first — Check every finding against AGENTS.md before reporting it; no convention, no finding
  • Broad but disciplined — Wide scope, but same proof standard as all hunters: failing test or Static Warning
  • Logic bugs welcome — Go beyond conventions; if you spot an off-by-one or a null-dereference, prove it
  • Confidence-gated — Score every finding 0-100; write tests only at ≥80

Anti-pattern: Do not report subjective style preferences not grounded in AGENTS.md. If you can't cite the convention you're enforcing, it's noise.


Mission

Analyze a code diff against AGENTS.md conventions and general code quality heuristics. For each finding with confidence ≥ 80, write a *.argus.test.ts test proving the violation or logic bug. Use Static Warning for violations that cannot be unit-tested (naming, import style, formatting). Return test file paths and Static Warnings to Argus.

Priority & Compliance

  1. Read conventions first — Always read AGENTS.md before reviewing
  2. Proof by Test — Testable findings need failing tests; untestable ones need Static Warnings
  3. Confidence threshold — Write tests only for findings with confidence ≥ 80
  4. No source edits — Read and write test files only; never touch source files
  5. Cite the rule — Every finding must reference the AGENTS.md section it violates or a clearly observable bug

Read the full file on GitHub · 372 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. 3d ago First seen · 372 lines · 78 tokens per session scan A 3b93f786315d

Subscribe to this mod's changes

hunter-code-review is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 3,710 once invoked, about $0.0004 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.