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.
npx skills add atretyak1985/swarmery --skill deps-checkgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/skills/atretyak1985/swarmery/deps-check)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/deps-check"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/deps-check/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/skills/atretyak1985/swarmery/deps-check"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/deps-check.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 | $0.00050 | $0.00760 |
| Opus 5.5 | $0.00020 | $0.00304 |
| Sonnet 5.5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
deps-check 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Audit dependency versions across the project's repositories (.claude/project.json → repos), producing a structured report of outdated packages, vulnerabilities, and cross-repo version mismatches. Scan-and-report only; acting on findings goes to the implementation agent. Placeholders <mainApp>, <device>, <infrastructure-repo> come from project.json.
Rules (never violate)
- Read-only: never run
npm audit fix,npm update, orpip install --upgrade. - Every repo in scope is scanned or its failure reported in the header; capture stderr — silent failures produce incomplete reports.
- Note the
helm repo updateside effect explicitly (it mutates the local chart cache and needs network). - Outdated is not vulnerable — report severities using the registry's scale, never a custom one.
- Report stays within 200 lines; the cross-repo mismatch section always appears, even as "None found".
- Stop and ask on: a critical CVE with no patched version, missing scan tooling, no network, or a missing dependency file.
Resources
- Read
resources/scan-procedure.mdwhen running an audit — the procedure with scan commands, self-check, mistakes, escalation, failure modes. - Read
resources/output-template.mdwhen compiling results — the report template and a complete worked-example audit.
How to use
What it does
Audits the dependency health of every repository in your project into one report: outdated packages, known vulnerabilities, and repos pinning different versions of the same shared package. It reads and reports only — never upgrading a package or touching a lockfile.
When to use it
- A periodic security review needs a current picture of dependency risk.
- You are cutting a release and want proof no known vulnerability ships.
- A CVE advisory landed, or a shared package may have drifted between repos.
Not for performing upgrades (separate task), deployment config or chart lint issues (the project's infra pack skills), single-file package.json review, or offline environments.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 67 lines · 50 tokens per session scan A f2f13e532848
deps-check is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 760 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
dependency-versions
MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, planning or writing CI/CD workflows (GitHub Actions, CircleCI…
finish
Ship phase — merge, PR, keep, or discard with pre-merge verification.
gws-quick-ref
Quick reference for gws CLI syntax — core patterns, key flags, pagination, field masks, and output formats.
excalidraw
Create or extend editable Excalidraw diagrams from descriptions or repository evidence using a local skeleton-to-scene converter.
style-ops
Maintain, validate or report on the Fakoli principles ledger, checking evidence pointers and keeping its Markdown projection synchronized.
gws-events-subscribe
Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.