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 sergeyklay/.agents --skill vet-dependencygit clone --depth 1 https://github.com/sergeyklay/.agentsWrote 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/sergeyklay/.agents/vet-dependency)<a href="https://agentmods.dev/skills/sergeyklay/.agents/vet-dependency"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/vet-dependency/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/sergeyklay/.agents/vet-dependency"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/vet-dependency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00209 | $0.03761 |
| Opus 5 | $0.00105 | $0.01880 |
| Sonnet 5 | $0.00042 | $0.00752 |
| Haiku 4.5 | $0.00021 | $0.00376 |
Grade A, and why
vet-dependency 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 4d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vetting a candidate dependency
A package's landing page reports the wrong variables. Stars measure attention at some point in the past, release count measures how often a version was published, and the repository's last-push timestamp moves whenever anything touches it. None of the three answers the question that decides adoption: can this package reach the version this project has already committed to, and does it behave correctly when it gets there.
The two facts that settle it are both invisible from the README. The first is the queue of pull requests nobody has merged, which measures whether the package can still move. The second is what the library does at runtime with the exact input class this project will feed it, which measures whether moving would help.
The subject is a package that is not yet a dependency, characterized empirically before it becomes one rather than described from its documentation. This skill sits beneath research-it, which owns source priority, triangulation, and the discipline around absence claims. It owns only how a candidate's health and fitness are measured, and what verdict that measurement supports.
Nothing here is language-specific. Three operations differ per ecosystem (resolving a package to its repository, obtaining the published artifact, running an isolated probe) and are catalogued in references/ecosystems.md; the forge API calls differ per host and are catalogued in references/forges.md. Read the relevant rows of each before step 0. Everything else in this file applies unchanged.
When this fires
- An architecture decision turns on adopting, replacing, or dropping a library, and the project's rule is to ask before adding a dependency.
- Two or more packages implement the same protocol, SDK, or wire schema, and one must be chosen.
- A package is already a candidate in a draft decision record and the open question is whether it is alive enough to depend on.
- A package the project uses looks stalled and the question is whether to fork, vendor, pin, or leave.
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.
- 4d ago Changed · -3 lines 45b9113358b3
- 7d ago First seen · 167 lines · 209 tokens per session scan A 35994a816d05
vet-dependency is a skill published in the GitHub repository sergeyklay/.agents (5 stars, last pushed today), licensed Apache-2.0. It adds 209 tokens to every session and 3,761 once invoked, about $0.0010 per session on Opus 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
glab-gitlab-issue
Read and manage GitLab issues through the glab CLI. Use when a user provides an issue ID and repository and asks to view issue details, comments, or uploaded images, publish comments, update assignees or labels, or manage issue time tracking (estimate/spent time) without using the web UI.
agentrq
Lead multiple agents to accomplish big tasks with specialized workspaces/agents by assigning tasks to specialized agents.
work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).