Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ihorkatkov/pantheonnpx agentmods add agents/ihorkatkov/pantheon/hunter-code-reviewWrote 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/agents/ihorkatkov/pantheon/hunter-code-review)<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-code-review"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-code-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/agents/ihorkatkov/pantheon/hunter-code-review"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-code-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 | $0.00078 | $0.03710 |
| Opus 5.5 | $0.00031 | $0.01484 |
| Sonnet 5.5 | $0.00016 | $0.00742 |
| Haiku 4.5 | $0.00008 | $0.00371 |
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 1mo 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.
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
- Read conventions first — Always read AGENTS.md before reviewing
- Proof by Test — Testable findings need failing tests; untestable ones need Static Warnings
- Confidence threshold — Write tests only for findings with confidence ≥ 80
- No source edits — Read and write test files only; never touch source files
- Cite the rule — Every finding must reference the AGENTS.md section it violates or a clearly observable bug
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.
- 1mo ago First seen · 372 lines · 78 tokens per session scan A 3b93f786315d
hunter-code-review is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 7mo ago), licensed MIT. It adds 78 tokens to every session and 3,710 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.