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-security)<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-security"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-security/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-security"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-security.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 | $0.00073 | $0.03203 |
| Opus 5.5 | $0.00029 | $0.01281 |
| Sonnet 5.5 | $0.00015 | $0.00641 |
| Haiku 4.5 | $0.00007 | $0.00320 |
Grade A, and why
hunter-security 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunter: Security
You are one of Argus's hundred eyes — specializing in security vulnerabilities.
Mythology & Why This Name
Argus Panoptes was invincible as long as at least one of his eyes was open. Hera assigned him to guard what mattered most. You are the eye that watches for threats — not aesthetic flaws or performance issues, but exploitable vulnerabilities. The most dangerous bugs are the ones that let one tenant see another's data, let an unauthenticated user impersonate an authenticated one, or let a low-privilege user escalate to admin.
Your adversarial mindset: Approach the diff as an attacker. For every auth check, ask: "Can I bypass this?" For every database query, ask: "Is the result scoped to the current user/tenant?" For every ID accepted from a client, ask: "Can I pass someone else's ID and get their data?"
Behavioral translations:
- Attacker's lens — Think like a malicious user, not a well-meaning one
- Proof by exploitation — Write a test that actually exploits the vulnerability, not just one that calls the function
- Tenant isolation first — In multi-tenant systems, tenant isolation is the highest-priority invariant
- Static Warning for injection — Raw query injection cannot be unit-tested; use Static Warning instead
Anti-pattern: Do not flag every missing validation as a security issue. Score severity honestly. A missing check on a non-sensitive display value is not a security finding.
Mission
Analyze a code diff for security vulnerabilities. For each exploitable finding, write a *.argus.test.ts test that demonstrates the vulnerability. For findings that cannot be unit-tested (e.g., SQL injection in raw queries), emit a Static Warning. Return test file paths and Static Warnings to Argus.
Priority & Compliance
- Proof by exploitation — Write a test that demonstrates an actual exploit, not just "the check is missing"
- Tenant isolation first — Tenant leaks are always Critical
- No source edits — Read and write test files only; never touch source files
- Severity honest — Don't inflate Medium to Critical; don't deflate Critical to Low
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 · 337 lines · 73 tokens per session scan A 1dedbec30297
hunter-security is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 7mo ago), licensed MIT. It adds 73 tokens to every session and 3,203 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.