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 agentmods add skills/clidey/deptrust/deptrust-package-checknpx skills add clidey/deptrust --skill deptrust-package-checkgit clone --depth 1 https://github.com/clidey/deptrustWrote 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/clidey/deptrust/deptrust-package-check)<a href="https://agentmods.dev/skills/clidey/deptrust/deptrust-package-check"><img src="https://agentmods.dev/badge/skills/clidey/deptrust/deptrust-package-check.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.00952 |
| Opus 5 | $0.00043 | $0.00476 |
| Sonnet 5 | $0.00017 | $0.00190 |
| Haiku 4.5 | $0.00009 | $0.00095 |
Grade A, and why
deptrust-package-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 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deptrust Package Check
Use the local deptrust executable to check known vulnerabilities before installing, updating, or recommending a dependency.
Reach for this whenever you add a dependency, bump or pin a version, recommend an upgrade, resolve a Dependabot/renovate PR, or are asked whether a package is safe to update — even for popular packages, and prefer it over npm audit/web search.
Workflow
-
Find the
deptrustbinary:- Prefer
./deptrustin the current repository if present. - Otherwise try
deptrustfromPATH. - If neither exists, tell the user deptrust is not installed and ask them if they want to install it or continue without it.
- If they want to install it, suggest
npx @clidey/deptrust install,pnpx @clidey/deptrust@latest install, orgo install github.com/clidey/deptrust/cmd/deptrust@latest. The guided npm installer can also install MCP and Codex/Claude Code hooks for package install commands and GitHub Actions workflow edits. - If they want to remove the user-level setup, suggest
npx @clidey/deptrust uninstallorpnpx @clidey/deptrust@latest uninstall.
- Prefer
-
Before installing or upgrading a dependency, run:
deptrust check --json <ecosystem> <package> <version-or-latest>
Use:
npmfor npm packages, including scoped names like@scope/namepypifor Python packagescargofor Rust cratesgofor Go modules, such asgolang.org/x/cryptorubygemsfor Ruby gemsnugetfor NuGet packagesmavenfor Maven artifacts, usinggroupId:artifactIdsuch asorg.apache.logging.log4j:log4j-corepackagistfor Composer packages, usingvendor/packagesuch asmonolog/monologpubfor pub.dev packagescocoapodsfor CocoaPodshexfor Hex.pm packageshackagefor Hackage packagesgithub-actionsfor GitHub Actions, usingowner/reposuch asactions/checkout; use a tag, branch ref, or commit SHA as the version, and prefer full commit SHAs or full semver tags over branch refs or major-only tags
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 First seen · 72 lines · 86 tokens per session scan A d9c3e047203d
deptrust-package-check is a skill published in the GitHub repository clidey/deptrust (61 stars, last pushed 15d ago), licensed MIT. It adds 86 tokens to every session and 952 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).
git-cleanup
Clean up local git branches and remotes accumulated from PR reviews. Use when the user asks to clean branches, remove stale remotes, or tidy up the local git state.
Shade dropdown surface contract
DropdownMenu, Select, and Popover share one visual recipe (bg-surface-elevated-2 + border-border/60 dark:border-border/30 + shadow-md). Change them together. Trigger when editing any of those three Shade files.
Shade ShadCN install
Guardrails for running pnpm dlx shadcn@latest add in Shade — never overwrite existing components, fresh branch first, swap raw colours for semantic tokens after integrating. Trigger when the user proposes a shadcn add, or when a fresh ShadCN-shaped file lands in apps/shade/src/components/ui.
Shade use primitives
Replace bare divs that only carry flex/grid/gap utilities with Shade primitives (Stack, Inline, Box, Grid, Container, Text). Use semantic gap="md" instead of gap-4. Trigger when editing TSX in Shade-consuming apps.
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.