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 agentmods add skills/stripe/link-cli/check-link-walletnpx skills add stripe/link-cli --skill check-link-walletgit clone --depth 1 https://github.com/stripe/link-cliWrote 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/stripe/link-cli/check-link-wallet)<a href="https://agentmods.dev/skills/stripe/link-cli/check-link-wallet"><img src="https://agentmods.dev/badge/skills/stripe/link-cli/check-link-wallet.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00626 |
| Opus 5 | $0.00032 | $0.00313 |
| Sonnet 5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
check-link-wallet 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 4d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check a Link wallet
Read-only inspection of the connected Link account through the Link MCP server. Nothing here moves money or changes a spend request.
To actually buy something, use the complete-link-purchase skill instead.
Tools
| Question | Tool |
|---|---|
| Which account is connected? | get_userinfo |
| What cards and bank accounts are saved? | list_payment_methods |
| What shipping addresses are saved? | list_shipping_addresses |
| What purchases are pending or approved? | list_spend_requests |
| What is the status of one purchase? | get_spend_request |
Call only the tool that answers the question. Do not sweep all five to build a picture the user did not ask for.
Spend request status
list_spend_requests returns only active requests by default — those in
created, pending_approval, or approved. Pass includeHistory when the
user is asking about something that already finished or expired.
The statuses mean:
created— exists, but the user has not been asked to approve it yet.pending_approval— waiting on the user. They approve in the Link app.approved— ready to spend against.- Expired and terminal states are only visible with
includeHistory, and cannot be spent against. A user who still wants the purchase needs a fresh one, raised withrequest_virtual_card— but only if they ask for it. Do not offer to re-run a purchase off the back of a status question.
get_spend_request returns the status of a single request by id. Do not pass
the include parameter here. include: ["card"] and
include: ["shared_payment_token"] return live payment credentials, and they
belong only in the moment of paying, which is the other skill's job.
What to expose
- Summarize. Do not dump raw JSON or object ids unless the user asks.
- Payment methods: brand, type, and last four only. Never a full number.
- Shipping addresses: city and postcode by default. Give the full address only if the user asks for it.
- Never surface tokens, credentials, or internal identifiers as an aside.
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.
- 4d ago First seen · 61 lines · 63 tokens per session scan A ab80b1ad4092
check-link-wallet is a skill published in the GitHub repository stripe/link-cli (745 stars, last pushed 5d ago), licensed MIT. It adds 63 tokens to every session and 626 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
convex-add
Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…