Vellum Assistant is a personal AI assistant that remembers information about users, learns their preferences, and takes actions across connected apps. It is intended for people who want an assistant that can manage conversations, unfinished work, and proactive notifications over time. The catalogue skills, hooks, instruction, and setting configure or extend how the assistant works.
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 vellum-ai/vellum-assistant --skill amazongit clone --depth 1 https://github.com/vellum-ai/vellum-assistantWrote 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/vellum-ai/vellum-assistant/amazon)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/amazon"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/amazon/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/vellum-ai/vellum-assistant/amazon"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/amazon.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 | $0.00011 | $0.01103 |
| Opus 5 | $0.00005 | $0.00551 |
| Sonnet 5 | $0.00002 | $0.00221 |
| Haiku 4.5 | $0.00001 | $0.00110 |
Grade A, and why
amazon 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use browser automation for all Amazon actions. All browser operations are executed through the assistant browser CLI, invoked via host_bash. Use helper scripts with host_bash to normalize extraction results and decide the next step.
Required tools
host_bashforassistant browserCLI commands and deterministic helper scripts underscripts/.
Hard constraints
- Do not call
assistant browser chrome relay. - Do not use legacy relay-backed scripts.
- Always require explicit user confirmation before final order submission.
Step graph (state machine)
Step 1: Classify workflow state
Run this early in each turn when intent is unclear:
bun {baseDir}/scripts/amazon-intent.ts --request "<latest user request>" --checkout-reviewed <true|false> --has-cart-items <true|false>
Use the returned step to route to one of: search, variant_select, cart_review, checkout_review, fresh_slot, place_order.
Step 2: Product discovery (search)
- Navigate to search results page:
assistant browser --session amazon navigate --url "https://www.amazon.com/s?k=<urlencoded query>"
- Capture current state:
assistant browser --session amazon --json snapshot
assistant browser --session amazon --json extract --include-links
- Parse candidates deterministically:
bun {baseDir}/scripts/amazon-parse-search.ts --query "<query>" --input-json '<json payload with extracted text/links>'
- Present top options with title, price, ASIN (if present), Prime/Fresh hints.
Step 3: Product detail + variant resolution (variant_select)
- Open product result.
- Re-snapshot + re-extract.
- Parse product details:
bun {baseDir}/scripts/amazon-parse-product.ts --input-json '<json payload with extracted text/links>'
- If variation hints are present, resolve user choice before add-to-cart.
Step 4: Add to cart + verify (cart_review)
- Click Add to Cart on product page.
- Navigate to cart page and extract:
What ships with it
16 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.
- assets/icon.svg 5.4 KB
- README.md 1.6 KB
- scripts/__fixtures__/cart-sample.txt 164 B
- scripts/__fixtures__/product-sample.txt 94 B
- scripts/__fixtures__/search-sample.txt 120 B
- scripts/__tests__/amazon-checkout-sanity.test.ts 991 B runs code
- scripts/__tests__/amazon-intent.test.ts 1.2 KB runs code
- scripts/__tests__/amazon-parse-cart.test.ts 843 B runs code
- scripts/__tests__/amazon-parse-product.test.ts 1003 B runs code
- scripts/__tests__/amazon-parse-search.test.ts 1.1 KB runs code
- scripts/amazon-checkout-sanity.ts 3.0 KB runs code
- scripts/amazon-intent.ts 4.8 KB runs code
- scripts/amazon-parse-cart.ts 4.8 KB runs code
- scripts/amazon-parse-product.ts 4.7 KB runs code
- scripts/amazon-parse-search.ts 5.7 KB runs code
- scripts/lib/common.ts 3.3 KB runs code
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 · 154 lines · 11 tokens per session scan A 4296bf5c0a98
amazon is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,204 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,103 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 2026-08-30.
Other skills, from other repositories
deal-finder
Scan configured sources (Craigslist now; eBay + Facebook Marketplace planned) for used-item listings matching the owner's criteria. Currently configured for a Mac mini search (M2+, 16GB+, 512GB+, ≤$500, near 94566). Notify owner via SMS + Telegram on a match.
lictor-security-check
Pre-release security audit for ANY project — AI-built or hand-written, web or mobile. Scans the codebase for the full range of real-world risks that get apps breached: leaked API & AI-provider keys, exposed configs/secrets, broken auth & access control (IDOR), injection (SQL/XSS/command), SSRF, open databases & cloud…
lictor-rotate
Walks the user through rotating a leaked API key — step by step, provider-specific. Knows the exact URL to visit, the exact button to click, and how to verify the rotation worked. Supports Stripe, OpenAI, Anthropic, Google Cloud / AI Studio, GitHub, AWS, Slack, Supabase, Firebase, Postmark, and generic OAuth providers.
lictor-explain
Takes any security finding, error message, or jargon-heavy security advice and explains it in plain English. Use this when someone is confused by what /lictor-security-check found, or when they got a security warning from another tool and don't understand it.
lictor-fix-it
Applies the fixes recommended by /lictor-security-check, with the user's explicit permission for each change. Walks through findings one at a time, shows the proposed change, gets approval, applies, runs tests if available, and moves on. Some fixes (rotating leaked credentials) require the user to act outside Claude …
competitor-price-tracker
Monitor competitor product pages and alert when prices change.