vendor-audit

vendor-audit is a command for coding agents from sergei-aronsen/claude-code-toolkit. It costs 37 tokens per session (1,383 once invoked), scanned A, original, MIT.

A quarterly review of external tools and services used by an AI-assisted development toolkit. It checks whether their maintainers, versions, licenses, and priorities are changing.

In plain words
What is it for?
Use it to review listed plugins, MCP servers, npm tools, API providers, and framework versions every three months or before a major project milestone.
Why use it?
It helps you spot abandoned projects, frequent breaking changes, license changes, or service changes before they disrupt your work.

Command

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.

agentmods
npx agentmods add commands/sergei-aronsen/claude-code-toolkit/vendor-audit
Clone the repo
git clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkit

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 vendor-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/vendor-audit.svg)](https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/vendor-audit)
Your own site
<a href="https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/vendor-audit"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/vendor-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.01383
Opus 5 $0.00018 $0.00691
Sonnet 5 $0.00007 $0.00277
Haiku 4.5 $0.00004 $0.00138

Measured 5d ago against content hash d6cc156c0df6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

vendor-audit 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 5d 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.

commands/vendor-audit.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/vendor-audit — Quarterly External Dependency Risk Review

Purpose

Solo developers building real products on AI-assisted toolchains depend on external maintainers staying engaged and predictable. This command runs a structured quarterly check on every external dependency the toolkit recommends. Goal: catch maintainer drift, breaking-change cadence, license shifts, or marketing-driven priority changes BEFORE they break your workflow.

When to Use

  • Quarterly (every 3 months) — set calendar reminder
  • After hearing news about any tool (acquisition, fork, security incident)
  • Before committing to a new milestone that depends heavily on a specific tool

Not for ad-hoc one-off lookups — for those, just gh api repos/<owner>/<repo> directly.

What It Audits

Five categories of external dependencies:

  1. Plugins — GSD (gsd-build/get-shit-done), Superpowers (obra/superpowers)
  2. MCP servers — Morph (morphllm), claude-context (zilliztech)
  3. npm tools — better-model (talkstream/better-model)
  4. Supreme Council backends — Gemini API, OpenAI API (model availability + pricing)
  5. Frameworks behind cheatsheets — Laravel, Rails, Next.js, etc. (major version drift)

For each dependency:

  • Activity: last commit date, recent commit cadence (per week)
  • Risk signals: marketing pivot, memecoin/token launch, ownership change, license change
  • Breaking changes: how many shipped in last 90 days?
  • Issues backlog: open issues vs closed in last 90 days (healthy ratio = closed > opened)
  • CI health: main branch CI green or red?

Output

.planning/audits/vendor-audit-YYYY-MM-DD.md — structured report with:

  • Status per dependency (GREEN / YELLOW / RED)
  • Recommended actions (continue / pin version / prepare exit / abandon)
  • Diff vs last quarter's audit (cadence trends)

Usage

/vendor-audit

Optional flags:

  • --dependency <name> — audit only one (e.g., /vendor-audit --dependency gsd)
  • --since <date> — compare against snapshot from a specific date
  • --dry-run — show what would be checked, don't write report

Read the full file on GitHub · 136 lines

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. 5d ago First seen · 136 lines · 37 tokens per session scan A d6cc156c0df6

Subscribe to this mod's changes

vendor-audit is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 19d ago), licensed MIT. It adds 37 tokens to every session and 1,383 once invoked, about $0.0002 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.