archguardian: Skill for Claude Code

.claude/skills/deps/SKILL.md

deps is a skill for Claude Code from ysfAskri/archguardian. It costs 9 tokens per session (389 once invoked), scanned A, original, MIT.

A dependency security scan that checks the external packages used by a project for publicly known vulnerabilities. Vulnerabilities are software weaknesses, often tracked with identifiers such as CVEs.

In plain words
What is it for?
Use it to list affected packages and versions, CVEs, severity, fixes, and upgrade paths for direct or indirect dependencies.
Why use it?
It shows which installed packages are risky, how serious each issue is, and whether an update fixes it.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is ysfAskri/archguardian's own configuration. It tells Claude Code how to work on archguardian itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything archguardian configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ysfAskri/archguardian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ysfAskri/archguardian/master/.claude/skills/deps/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ysfAskri/archguardian

Made for: Claude Code.

Wrote 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.

agentmods badge for deps

README.md
[![agentmods](https://agentmods.dev/badge/skills/ysfaskri/archguardian/deps.svg)](https://agentmods.dev/skills/ysfaskri/archguardian/deps)
Your own site
<a href="https://agentmods.dev/skills/ysfaskri/archguardian/deps"><img src="https://agentmods.dev/badge/skills/ysfaskri/archguardian/deps.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 389 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00009 $0.00389
Opus 5 $0.00005 $0.00195
Sonnet 5 $0.00002 $0.00078
Haiku 4.5 $0.00001 $0.00039

Measured 6d ago against content hash 4da596143746, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deps 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 6d 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.

.claude/skills/deps/SKILL.md · 46 lines

What it actually says

archguardian deps

Check project dependencies for known security vulnerabilities using the dependency scanner.

Instructions

  1. Run the scan with the dependency scanner enabled:

    npx archguardian scan --format json $ARGUMENTS
    
  2. Parse the JSON output and focus on dependency/known-vulnerability findings.

  3. For each vulnerability found, present:

    • Package: The affected dependency name and installed version
    • CVE: The CVE identifier (e.g., CVE-2024-12345)
    • Severity: Critical, High, Medium, or Low
    • Description: What the vulnerability allows (RCE, XSS, data leak, etc.)
    • Fixed in: The version that patches the vulnerability (if available)
  4. Prioritize findings by severity (Critical first, then High, Medium, Low).

  5. For each vulnerable package, suggest the upgrade path:

    • Direct dependency: npm install <package>@<fixed-version>
    • Transitive dependency: Identify which direct dependency pulls it in and suggest upgrading that instead
    • If no fix is available, suggest alternatives or mitigations
  6. After presenting all findings, summarize:

    • Total vulnerabilities by severity
    • How many have available fixes
    • Recommended upgrade commands

Tips

  • Run this regularly and before releases to catch newly disclosed vulnerabilities.
  • Pair with /gate to enforce zero critical vulnerabilities as a quality gate threshold.
  • For transitive dependencies, use npm ls <package> to trace the dependency chain.
  • If a vulnerability is a false positive or not applicable, use /dismiss to exclude it from future scans.
Changes

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.

  1. 6d ago First seen · 46 lines · 9 tokens per session scan A 4da596143746

Subscribe to this mod's changes

deps is a skill published in the GitHub repository ysfAskri/archguardian (4 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 389 once invoked, about $0.0000 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 2026-08-31.

Related

Other skills, from other repositories

repo-onboarding

Systematically map an unfamiliar codebase before changing it — entry points, build/test loop, conventions, data flow. Use when starting work in a repo you haven't seen, or asked "how does this codebase work?".

jnMetaCode/skillet · 48 tokens

code-to-diagram

Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a…

zebbern/claude-code-guide · 74 tokens

remindb-setup

Config-first setup wizard for a remindb MCP server — run it as /remindb-setup (interactive), /remindb-setup automode (hands-off), or /remindb-setup only-config (bridge hosts: author .remindb/ only, no env wiring). Two passes. First-time (no server attached yet): detect the host, author the .remindb/ config…

radimsem/remindb · 202 tokens

pre-edit-safety-gate

Prepare a safe, current, and maintainable code change before editing. Use before a cohesive code or workflow change to assess the request and existing structure, then choose a local change, reuse, extension, or necessary refactor with clear ownership. Do not use to block ordinary TDD or authorized refactors.

rexleimo/aios · 68 tokens

audit-architecture

Audit module coupling, cohesion, hidden dependencies, and design smells. Use when conducting architecture reviews, evaluating design decisions, or identifying structural tech debt.

panbanda/omen · 33 tokens

remember

Front door for long-term memory backed by a remindb MCP server. Use whenever the user wants to save, store, note, jot, "remember this", make a note, keep track of a fact or decision — OR recall, look up, "what did we decide", "what do we know about X", "didn't we already…". Fires on the generic remember/recall intent…

radimsem/remindb · 113 tokens