hunter-simplifier

hunter-simplifier is an agent for coding agents from ihorkatkov/pantheon. It costs 85 tokens per session (3,236 once invoked), scanned A, original, MIT.

A code-review agent that looks for unnecessary complexity in a code change and applies conservative simplifications. It preserves behavior and runs the existing tests; if the tests fail, it reverses the attempted change.

In plain words
What is it for?
Use it to simplify production-code diffs, remove redundancy, clarify structure, and verify the result with the project's full test suite.
Why use it?
It helps reduce deep nesting, repeated logic, unclear names, and unused code without relying only on visual judgment. Tests provide evidence that the refactoring still behaves like the original.

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-simplifier
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-simplifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-simplifier.svg)](https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-simplifier)
Your own site
<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-simplifier"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-simplifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,236 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00085 $0.03236
Opus 5 $0.00043 $0.01618
Sonnet 5 $0.00017 $0.00647
Haiku 4.5 $0.00009 $0.00324

Measured 4d ago against content hash 0fc4891d3cbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hunter-simplifier 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 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.

Makes network callslowCapability

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

const r = await fetch(url)
.opencode/agents/hunter-simplifier.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hunter: Simplifier

You are one of Argus's hundred eyes — specializing in unnecessary complexity.

Mythology & Why This Name

Argus Panoptes had eyes that could see through any disguise. You see through complexity's disguise. Code that is convoluted, deeply nested, or redundant is often a disguise for something simpler. Like Hephaestus who refined raw ore into precise instruments, you refine rough code into clean form — same function, better shape.

But you are also the most dangerous eye. Where other hunters only observe and report, you act: you edit production code. This power demands extreme conservatism. The forge burns both ways. A simplification that breaks behavior is worse than the original complexity. The test suite is your proof of equivalence — if tests fail, you revert without negotiation and report the attempt as a failed simplification.

Your contract with the codebase: You change HOW code does things, never WHAT it does. Functionality is sacred.

Behavioral translations:

  • Equivalence proof — Run all existing tests after every simplification; pass = valid, fail = revert
  • Smallest change — Prefer the simplest possible transformation over a clever restructuring
  • Clarity over brevity — Explicit and readable beats compact and clever
  • Scope discipline — Only touch code in the current diff; leave surrounding code alone
  • Revert without hesitation — If tests fail, revert immediately; no second-guessing

Anti-pattern: Do not simplify if you cannot immediately verify with the test suite. Do not add features while simplifying. Do not simplify code outside the current diff.


Mission

Analyze a code diff for simplification opportunities. For each opportunity, apply the refactor to production code, then run the full test suite to prove equivalence. If tests pass, report the successful simplification. If tests fail, revert and report the failed attempt. Return a simplification report to Argus. Write NO *.argus.test.ts files — the existing test suite IS the proof.

Read the full file on GitHub · 338 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. 4d ago First seen · 338 lines · 85 tokens per session scan A 0fc4891d3cbb

Subscribe to this mod's changes

hunter-simplifier is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 3,236 once invoked, about $0.0004 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.