scan-full

scan-full is a skill for Claude Code from DevInder1/supply-chain-scanner-public. It costs 84 tokens per session (597 once invoked), scanned A, original, MIT.

A workflow for checking project dependencies, operating-system packages, and installed coding-tool extensions for security flaws.

In plain words
What is it for?
It scans npm and PyPI dependencies, Homebrew or Linux packages, and VS Code or JetBrains extensions, grouping the results by source.
Why use it?
It covers software on the developer’s machine that project-only scanners may miss.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the tridentchain-security plugin — 7 skills shipped together

Good fit It scans npm and PyPI dependencies, Homebrew or Linux packages, and VS Code or JetBrains extensions, grouping the results by source.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/devinder1/supply-chain-scanner-public/scan-full
Install

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.

Any agent
npx skills add DevInder1/supply-chain-scanner-public --skill scan-full
Clone the repo
git clone --depth 1 https://github.com/DevInder1/supply-chain-scanner-public

Made for: Claude Code.

Or install tridentchain-security, the plugin that ships this one along with the rest of its 7 skills.

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 scan-full

README.md
[![agentmods](https://agentmods.dev/badge/skills/devinder1/supply-chain-scanner-public/scan-full.svg)](https://agentmods.dev/skills/devinder1/supply-chain-scanner-public/scan-full)
Your own site
<a href="https://agentmods.dev/skills/devinder1/supply-chain-scanner-public/scan-full"><img src="https://agentmods.dev/badge/skills/devinder1/supply-chain-scanner-public/scan-full.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 597 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 $0.00084 $0.00597
Opus 5 $0.00042 $0.00298
Sonnet 5 $0.00017 $0.00119
Haiku 4.5 $0.00008 $0.00060

Measured 7d ago against content hash 5a6f910fe164, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

scan-full 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 7d 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.

plugins/tridentchain-security/skills/scan-full/SKILL.md · 37 lines

What it actually says

Full workspace scan

When the user wants comprehensive coverage — project + system + IDE — or mentions any of: "my whole machine", "my system", "Homebrew", "apt packages", "VS Code extensions", "JetBrains plugins", "IDE security", "audit everything":

  1. Call the tridentchain MCP tool scan_full with:
    • project_path = workspace root (absolute path)
    • output_dir = .tridentchain-out-full
    • run_profile = "full"
    • max_findings = 30
  2. Report findings grouped by source — this is the key value of scan_full:
    • Project (npm/PyPI) — raw_summary.vulnerability_breakdown_by_type.project
    • System packages (brew, apt) — raw_summary.vulnerability_breakdown_by_type.system
    • IDE extensions (VS Code, JetBrains) — raw_summary.vulnerability_breakdown_by_type.extension
  3. Highlight critical system findings first. A critical CVE in git, openssl, or ffmpeg on the user's machine outranks any project finding. Always surface these at the top with the exact upgrade command (brew upgrade git, etc.).
  4. If any KEV-listed package is on the user's machine (system or project), call it out as URGENT.
  5. Report runtime — scan_full is slower than scan_project (5–60 seconds depending on how many system components are installed).

Why this matters

Project-only scanners miss the most impactful CVEs. A recent example: many systems shipped with git 2.35.x which has 3 critical CVEs (CVE-2024-32002 and family). A project scanner won't find that — scan_full does. Same logic applies to freetype, giflib, ffmpeg, and the entire VS Code marketplace extension catalog.

CLI fallback

tridentchain-security --scan all --project-path . --output-dir .tridentchain-out-full

When NOT to use scan-full

  • User explicitly says "project only" → use scan
  • User wants the fastest possible answer → use quick-scan
  • User wants to verify a fix → use validate-fixes
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. 7d ago First seen · 37 lines · 84 tokens per session scan A 5a6f910fe164

Subscribe to this mod's changes

scan-full is a skill published in the GitHub repository DevInder1/supply-chain-scanner-public (0 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 597 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 2026-08-31.