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 OneWave-AI/claude-skills --skill cowork-vendor-comparisongit clone --depth 1 https://github.com/OneWave-AI/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/onewave-ai/claude-skills/cowork-vendor-comparison)<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/cowork-vendor-comparison"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/cowork-vendor-comparison/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/onewave-ai/claude-skills/cowork-vendor-comparison"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/cowork-vendor-comparison.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 22 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00058 | $0.00703 |
| Opus 5 | $0.00029 | $0.00351 |
| Sonnet 5 | $0.00012 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
cowork-vendor-comparison 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 13d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cowork Vendor Comparison
Compare vendor proposals the way a procurement lead does: normalize everything to the same units before judging anything, price the full term not the first invoice, and read the terms the sales deck skipped. Input: a folder of quotes/proposals/SOWs (PDF, .docx, .xlsx) and, ideally, one sentence on what the purchase needs to accomplish.
Workflow
- Extract per vendor: pricing structure (license, usage, implementation, support tiers), contract term and renewal terms, SLAs and remedies, implementation timeline and dependencies, what is in scope vs. priced as add-on, exit terms (data export, termination fees), and every assumption the proposal states.
- Normalize. Convert all pricing to a common basis -- same seat count, same usage volume, same term. Where a proposal is silent on something another proposal prices (training, integrations, overage rates), mark it
UNPRICED -- ask, never zero. Unpriced is not free. - Compute TCO over the realistic term (default 3 years): year-one cost, steady-state annual cost, escalators applied, one-time costs amortized, and the exit cost. Show the math per vendor.
- Matrix. Output
vendor-comparison.md: side-by-side table of cost, capability fit against the stated need, SLA strength, implementation risk, and contract flexibility -- each cell citing the source document and page. Follow with a plain-English paragraph per vendor: the honest case for and against. - Negotiation prep. For the top 2 vendors: leverage points (their weaknesses vs. the rival's strengths, end-of-quarter timing, multi-year vs. flexibility trades), the specific asks worth making (cap the escalator, free implementation, opt-out at 12 months), and 5 reference-check questions targeting each vendor's specific risk areas.
Rules
- Never judge from unnormalized numbers. A lower sticker with usage pricing can be the expensive option.
- Every cell in the matrix traces to a document and page. "Vendor B has better support" without a citation is vibes.
- Silence is a finding: what a proposal does not say (no uptime SLA, no data-export clause) goes in the matrix as prominently as what it says.
- Do not manufacture a winner. If the vendors genuinely split on cost vs. capability, present the trade and the decision criteria, and say which way the stated need leans.
- Flag lock-in explicitly: proprietary data formats, migration fees, auto-renewals with long notice windows.
- If proposals answer different scopes (one quoted 50 seats, one quoted 200), lead with that mismatch and request aligned quotes before deep comparison.
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.
- 13d ago First seen · 35 lines · 58 tokens per session scan A a497aefaf17f
cowork-vendor-comparison is a skill published in the GitHub repository OneWave-AI/claude-skills (291 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 703 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
pdf-text-replace
Replace text in fillable PDF forms by updating form field values. This skill should be used when users need to update names, addresses, dates, or other text in PDF form fields.
suede-product-marketing
Suede-owned product-marketing context discipline. Use when a project needs a shared record of product, audience, ICP, positioning, objections, customer language, proof, and goals, or when that record needs updating. NOT FOR: writing a campaign (use suede-campaign-in-a-box), conducting new customer interviews (use…
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
atelier-setup
Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, preview the proposed configuration, and write only after approval. It does not install Atelier or initialize external tooling.
text-stats
Compute word count, character count, or reading time for a piece of text using the in-bundle text-stats engine. Invoke whenever the user asks how long a passage is, how many words or characters it has, or how long it takes to read.
food-ppt
Turn a food & nutrition review report, evidence brief, or manuscript into a fully EDITABLE PowerPoint (.pptx) that opens in PowerPoint / Keynote / Google Slides with every title, bullet, table, and figure as a native editable object — nothing flattened to an image. Converts the outputs of food-research…