design-vendor-risk-assessment

design-vendor-risk-assessment is a skill for Claude Code from jeffreytse/grimoire-core. It costs 67 tokens per session (1,501 once invoked), scanned A, original, MIT.

An ongoing process for checking the operational, security, financial, and compliance risks of important third-party vendors. It continues after the contract is signed as the relationship changes.

In plain words
What is it for?
Use it to assess vendors, track their risks, set review schedules, and monitor changes in their security, finances, operations, and compliance.
Why use it?
A vendor's condition and your dependence on it can change over time. Regular checks help identify new weaknesses before they disrupt your work or expose data.

Skill for Claude Code

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

Part of the grimoire-business plugin — 156 skills shipped together

Good fit Use it to assess vendors, track their risks, set review schedules, and monitor changes in their security, finances, operations, and compliance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/design-vendor-risk-assessment
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 jeffreytse/grimoire-core --skill design-vendor-risk-assessment
Clone the repo
git clone --depth 1 https://github.com/jeffreytse/grimoire-core

Made for: Claude Code.

Or install grimoire-business, the plugin that ships this one along with the rest of its 156 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 design-vendor-risk-assessment

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-vendor-risk-assessment/github.svg)](https://agentmods.dev/skills/jeffreytse/grimoire-core/design-vendor-risk-assessment)
Your own site
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-vendor-risk-assessment"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-vendor-risk-assessment/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 design-vendor-risk-assessment

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-vendor-risk-assessment"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-vendor-risk-assessment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,501 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 $0.00067 $0.01501
Opus 5.5 $0.00027 $0.00600
Sonnet 5.5 $0.00013 $0.00300
Haiku 4.5 $0.00007 $0.00150

Measured 1mo ago against content hash 5c8ad4fd9fba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-vendor-risk-assessment 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 1mo 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.

skills/business/operations/skills/design-vendor-risk-assessment/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Vendor Risk Assessment

Establish an ongoing program to assess and monitor a critical third-party vendor's operational, security, financial, and compliance risk — rather than evaluating the vendor once at contract signing and never revisiting the assessment, even as the vendor relationship, the vendor's own condition, and the organization's dependence on it all evolve over time.

Why This Is Best Practice

Adopted by: NIST Special Publication 800-161, "Cybersecurity Supply Chain Risk Management Practices," documents structured vendor and supply-chain risk assessment as a required discipline for organizations managing third-party dependencies, and ongoing vendor risk management (VRM) programs — as distinct from one-time vendor due diligence — are standard practice across procurement, security, and operational risk functions in organizations that depend on critical third-party vendors. Impact: A vendor assessed as low-risk at the point of contract signing can become significantly riskier over time — its financial condition can deteriorate, its security practices can weaken, its compliance posture can lapse, or the organization's own dependence on it can deepen — and an organization that only assessed the vendor once, at signing, has no mechanism to detect this drift before it results in an actual disruption or failure. Why best: A one-time vendor evaluation captures only a snapshot of the vendor's risk profile at a single point in time, while the actual risk the organization bears from the relationship accumulates and changes continuously over the life of the engagement — an ongoing monitoring program is specifically designed to detect this drift, providing warning and time to react before a vendor's deteriorating condition results in an actual failure affecting the organization.

Sources: NIST Special Publication 800-161, "Cybersecurity Supply Chain Risk Management Practices"; standard vendor/third-party risk management (VRM) industry practice

Read the full file on GitHub · 68 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. 1mo ago First seen · 68 lines · 67 tokens per session scan A 5c8ad4fd9fba

Subscribe to this mod's changes

design-vendor-risk-assessment is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 1,501 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.