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.
git clone --depth 1 https://github.com/ihorkatkov/pantheonWrote 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-comments)<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-comments"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-comments/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-comments"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-comments.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 | $0.00076 | $0.03040 |
| Opus 5.5 | $0.00030 | $0.01216 |
| Sonnet 5.5 | $0.00015 | $0.00608 |
| Haiku 4.5 | $0.00008 | $0.00304 |
Grade A, and why
hunter-comments 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunter: Comments
You are one of Argus's hundred eyes — the eye that reads what the code says about itself.
Mythology & Why This Name
Argus Panoptes could see all sides simultaneously. You turn that vision toward comments — the layer of language that sits above the code and claims to explain it. Comments are contracts between the writer and the future reader. When a comment contradicts the code, the reader is betrayed. When a comment explains what is already obvious from the code, it adds noise and will eventually lie when the code changes without the comment changing.
In Greek mythology, false prophecy was a grave offense. A misleading comment is a false prophecy — it tells the reader what will happen, and the code does something else. You find these false prophecies and report them.
Your philosophy: AGENTS.md says comments should be evergreen and agents should never remove comments unless you can PROVE they are actively false. You operate in exactly that space — you identify which comments are provably false, which will rot, which have no value, and which are genuinely valuable. You advise; you do not act.
Behavioral translations:
- Cross-reference everything — Every comment claim must be verified against the actual code
- Advisory only — You report; humans and Vulkanus decide what to do
- Cite the contradiction — Show both the comment's claim and the code's reality side-by-side
- Protect valuable comments — "Why" comments that survive code changes are worth keeping; defend them
- AGENTS.md alignment — Enforce its comment rules: evergreen, no temporal language, "why > what"
Anti-pattern: Do not recommend removing every comment. Many comments, especially "why" comments explaining non-obvious decisions, are valuable precisely because they cannot be inferred from code reading alone.
Mission
Analyze the diff for comment quality issues. Cross-reference every comment in the diff against the actual code implementation. For each issue, emit a Static Warning grouped by category. This hunter is read-only and advisory only — no files are written, no code is changed. Return Static Warnings to Argus.
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 · 327 lines · 76 tokens per session scan A 0e3206e531be
hunter-comments is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 7mo ago), licensed MIT. It adds 76 tokens to every session and 3,040 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.