supply-chain-scan

supply-chain-scan is a skill for Claude Code from DevInder1/supply-chain-scanner-public. It costs 74 tokens per session (491 once invoked), scanned A, original, MIT.

A workflow for finding supply-chain CVEs, which are publicly recorded security flaws, in project dependencies, system packages, and IDE extensions.

In plain words
What is it for?
It scans npm and PyPI projects, Homebrew and apt packages, and VS Code or JetBrains extensions, then prioritises fixes using exploit data.
Why use it?
It helps identify which security problems are most likely to be exploited instead of sorting them only by general severity.

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 projects, Homebrew and apt packages, and VS Code or JetBrains extensions, then prioritises fixes using exploit data.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/devinder1/supply-chain-scanner-public/supply-chain-scan/github.svg)](https://agentmods.dev/skills/devinder1/supply-chain-scanner-public/supply-chain-scan)
Your own site
<a href="https://agentmods.dev/skills/devinder1/supply-chain-scanner-public/supply-chain-scan"><img src="https://agentmods.dev/badge/skills/devinder1/supply-chain-scanner-public/supply-chain-scan/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.

agentmods 80×15 button for supply-chain-scan

Your own site · 80×15
<a href="https://agentmods.dev/skills/devinder1/supply-chain-scanner-public/supply-chain-scan"><img src="https://agentmods.dev/badge/skills/devinder1/supply-chain-scanner-public/supply-chain-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 491 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 $0.00074 $0.00491
Opus 5 $0.00037 $0.00246
Sonnet 5 $0.00015 $0.00098
Haiku 4.5 $0.00007 $0.00049

Measured 9d ago against content hash c78d91204bac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

supply-chain-scan 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 9d 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/supply-chain-scan/SKILL.md · 32 lines

What it actually says

Supply chain scan

When the user asks about dependency vulnerabilities, CVEs, supply-chain risk, IDE extension security, or wants to audit package.json / lockfiles / requirements.txt:

  1. Use the tridentchain MCP tools — pick the right scope:
    • scan_project — fast scan of project deps only (npm, PyPI). Best when the user explicitly says "project only" or wants a fast pre-commit check.
    • scan_full — comprehensive: project deps + Homebrew/apt packages + VS Code + JetBrains extensions. Use when the user says "everything", "system", "machine", "IDE", or asks about extension security.
  2. Pass project_path as the workspace root (absolute path).
  3. Use output_dir .tridentchain-out under the project unless the user specifies another path.
  4. Lead the summary with EPSS-prioritised findings — the top 3 by EPSS score are the actual fix-first list. Then summarise by severity. Mention output_paths.epss_remediation_html for the prioritised view.
  5. If KEV findings are present (raw_summary.intelligence_sources.sources_used.kev), call them out separately — these are actively exploited in the wild.
  6. No API keys are required for the default profile.

CLI fallback (if MCP unavailable)

tridentchain-security --scan project --project-path <workspace> --output-dir .tridentchain-out
# Or for full system coverage:
tridentchain-security --scan all --project-path <workspace> --output-dir .tridentchain-out

Read .tridentchain-out/scan-report.json for the full data; scan-remediation-epss.html for the prioritised remediation queue.

Do not

  • Put API keys in chat; use environment variables only.
  • Scan paths outside the user's project without permission.
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. 9d ago First seen · 32 lines · 74 tokens per session scan A c78d91204bac

Subscribe to this mod's changes

supply-chain-scan is a skill published in the GitHub repository DevInder1/supply-chain-scanner-public (0 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 491 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.