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.
npx skills add rampstackco/claude-skills --skill vendor-evaluationgit clone --depth 1 https://github.com/rampstackco/claude-skillsWrote 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.
[](https://agentmods.dev/skills/rampstackco/claude-skills/vendor-evaluation)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/vendor-evaluation"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/vendor-evaluation/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.
<a href="https://agentmods.dev/skills/rampstackco/claude-skills/vendor-evaluation"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/vendor-evaluation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.02497 |
| Opus 5.5 | $0.00040 | $0.00999 |
| Sonnet 5.5 | $0.00020 | $0.00499 |
| Haiku 4.5 | $0.00010 | $0.00250 |
Grade A, and why
vendor-evaluation 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- vendor-evaluation — 92% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vendor Evaluation
Pick the right tool or service, negotiate fair terms, and avoid the lock-in traps. Stack-agnostic. Applies to SaaS, infrastructure providers, agencies, and any external dependency.
When to use
- Selecting a tool or vendor for a new need
- Evaluating alternatives to a current vendor
- Build vs buy analysis
- Renewal coming up: should we stay or switch?
- Running a formal RFP or RFI
- Comparing finalists in a vendor selection
- Negotiating a contract
- Assessing vendor risk (financial, security, dependency)
When NOT to use
- General cost reduction (use
cost-optimization) - Specific contract legal terms (those go to legal)
- Performance issues with an existing vendor (try fixing before switching)
- Hiring an agency for a one-off project (lighter framework needed)
Required inputs
- The need (what problem are you solving, what would success look like)
- Constraints (budget, timeline, integration requirements)
- Stakeholders (users, IT, security, finance, legal)
- Existing context (what's already used, what's been tried)
- Compliance requirements
The framework: 5 phases
A structured vendor evaluation. Skip phases at your peril.
Phase 1: Define the need
Before looking at vendors, define what you actually need.
- What problem are you solving?
- What's the user / use case?
- What does "success" look like in 6 months? In 2 years?
- What's the budget (range, not just ceiling)?
- What's the timeline?
- Are there must-have integrations or constraints?
The temptation: skip this and start demoing. Vendors are happy to show off; you end up choosing what looks shiny rather than what fits.
Phase 2: Build vs buy
Before evaluating vendors, decide whether you should build instead.
Build when:
- It's core to the business (differentiating)
- The need is so specific no vendor matches
- The economics work at your scale
- You have the team to maintain it
- Vendor lock-in would be unacceptable
Buy when:
- It's table stakes (not differentiating)
- The need is well-served by existing products
- The economics favor it
- The team should focus elsewhere
- The vendor's specialization beats your generalism
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 287 lines · 99 tokens per session scan A 44b1e50b7f52
vendor-evaluation is a skill published in the GitHub repository rampstackco/claude-skills (995 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 2,497 once invoked, about $0.0004 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.
Other skills, from other repositories
sow-generator
Generates professional Statements of Work from a project brief. Use when a user needs to create an SOW, scope a project, define deliverables and milestones, or produce a consulting engagement document.
legal-contract-lifecycle
Método do ciclo de vida de contratos e conflitos depois do PASS — registro único com #id, vigência, renovação e alertas, assinatura com versão travada, envio à contraparte só com PASS e confirmação, arquivamento, aditivo e distrato, notificação extrajudicial e dossiê para o advogado. Use ao registrar contrato…
massenschaden-datenmodell-rechtsabteilung
Für Massenschaden Datenmodell: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: massenschaden-datenmodell-rechtsabteilung.
resume-screener
Screen resumes efficiently against job requirements with structured scoring, red flag identification, and interview recommendations.
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…
aenderungsvorbehalt-308
Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.