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 w95/awesome-claude-corporate-skills --skill vendor-evaluationgit clone --depth 1 https://github.com/w95/awesome-claude-corporate-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/w95/awesome-claude-corporate-skills/vendor-evaluation)<a href="https://agentmods.dev/skills/w95/awesome-claude-corporate-skills/vendor-evaluation"><img src="https://agentmods.dev/badge/skills/w95/awesome-claude-corporate-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/w95/awesome-claude-corporate-skills/vendor-evaluation"><img src="https://agentmods.dev/badge/skills/w95/awesome-claude-corporate-skills/vendor-evaluation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00024 | $0.02828 |
| Opus 5 | $0.00012 | $0.01414 |
| Sonnet 5 | $0.00005 | $0.00566 |
| Haiku 4.5 | $0.00002 | $0.00283 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vendor Evaluation
Overview
Systematically evaluate vendor options using quantitative and qualitative criteria. Comprehensive vendor evaluation combines total cost of ownership (TCO) analysis, risk assessment, reference verification, and strategic fit to select the best long-term partner.
Vendor Comparison Matrix
Basic Comparison (3 vendors):
| Capability | Requirements | Vendor A | Vendor B | Vendor C |
|---|---|---|---|---|
| Functionality | ||||
| Real-time integrations | Mandatory | Yes | Yes | Yes |
| API rate limits | 1000 req/sec | 1000 | 2000 | 500 |
| Customization support | Available | Limited | Extensive | Standard |
| Performance | ||||
| Response time (p95) | <200ms | 150ms | 180ms | 250ms |
| Uptime SLA | 99.9% | 99.95% | 99.9% | 99.5% |
| Data latency | <15 min | 5 min | 10 min | 30 min |
| Security | ||||
| SOC 2 Type II | Mandatory | Yes | Yes | No |
| Data encryption | AES-256 | Yes | Yes | Yes |
| GDPR certified | Required | Yes | Yes | In progress |
| Support | ||||
| 24/7 phone support | Desired | Yes | Yes | No |
| Avg response time (P1) | <30 min | 15 min | 30 min | 2 hours |
| Customer success manager | Yes | Included | Included | Extra cost |
| Pricing | ||||
| Year 1 total cost | Benchmark | $115K | $95K | $80K |
| Implementation cost | Fixed | $30K | $25K | $40K |
| Hidden costs | Identify | Minimal | Minimal | Training extra |
| 3-year TCO | Compare | $285K | $270K | $290K |
Total Cost of Ownership (TCO) Analysis
Calculate True Cost Beyond License:
VENDOR A - 3 YEAR TCO
ACQUISITION COSTS:
Software License (Year 1) | $50,000
Implementation Services | $30,000
Data Migration | $10,000
Initial Training (3 days) | $15,000
Subtotal | $105,000
ONGOING COSTS (Years 1-3):
Support & Maintenance (Y1) | $25,000
Support & Maintenance (Y2) | $26,250
Support & Maintenance (Y3) | $27,563
Annual Training Refresher (Y1) | $5,000
Annual Training Refresher (Y2) | $5,000
Annual Training Refresher (Y3) | $5,000
Infrastructure/Licenses (Y1) | $5,000
Infrastructure/Licenses (Y2) | $5,250
Infrastructure/Licenses (Y3) | $5,513
Software License Renewal (Y2) | $52,500
Software License Renewal (Y3) | $55,125
Subtotal | $217,388
HIDDEN COSTS:
Internal Project Management (500 hrs @ $100/hr) | $50,000
Vendor Management (100 hrs/year @ $100/hr) | $30,000
Process redesign (800 hrs @ $125/hr) | $100,000
Knowledge transfer (200 hrs @ $100/hr) | $20,000
System integration/customization (300 hrs @ $150/hr) | $45,000
Subtotal | $245,000
TOTAL 3-YEAR TCO | $567,388
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.
- 9d ago First seen · 302 lines · 24 tokens per session scan A e653757dd185
vendor-evaluation is a skill published in the GitHub repository w95/awesome-claude-corporate-skills (198 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 2,828 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
workflow
Starts and manages autonomous agent workflows. Triggers: workflow, start workflow, autonomous agents, agent pipeline.
autonomous-dev
Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR. Persists ownership, progress and commit-bound evidence for safe resumption. Use for autonomous software delivery or finishing an interrupted development run.
onboard
Sets up ai-toolkit in a project: symlinks, CLAUDE.md, intent interview. Triggers: onboard, setup project, install ai-toolkit, migrate project.
plan
Breaks features/goals into phased plans with task lists, agent assignments, dependencies. Triggers: plan feature, implementation roadmap, break down task, project phases.
prd-to-issues
Splits a PRD into vertical-slice GitHub issues with HITL/AFK tagging and dependencies. Triggers: PRD to issues, create tickets, break down PRD, work items.
prd-to-plan
Converts PRD into phased plan via tracer-bullet vertical slices. Triggers: PRD to plan, break down PRD, implementation plan, tracer bullets, phased plan.