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 linkfox-ai/linkfox-skills --skill linkfox-1688-procurementgit clone --depth 1 https://github.com/linkfox-ai/linkfox-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/linkfox-ai/linkfox-skills/linkfox-1688-procurement)<a href="https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-1688-procurement"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-1688-procurement/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/linkfox-ai/linkfox-skills/linkfox-1688-procurement"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-1688-procurement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 System Prompt Leakage · line 107 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- high Privilege Escalation · line 112 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 90 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 122 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00142 | $0.03249 |
| Opus 5 | $0.00071 | $0.01625 |
| Sonnet 5 | $0.00028 | $0.00650 |
| Haiku 4.5 | $0.00014 | $0.00325 |
Grade A, and why
linkfox-1688-procurement 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 12d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1688 Procurement Workflow
This skill helps LinkFox users run authorized 1688 procurement: OAuth status checks, SKU and address lookup, order preview, guarded order creation, payment URL retrieval, order tracking, logistics, cancellation, receipt confirmation, and post-completion invoicing.
Use linkfox-1688-search-by-image for image-based product discovery. This skill does not include image search.
Core Rules
- Every script requires LinkFox platform identity from
LINKFOX_AGENT_API_KEYorLINKFOXAGENT_API_KEY. authorize_url.pystarts 1688 OAuth;authorized_stores.pychecks the current LinkFox user's 1688 OAuth state.- Except those two authorization scripts, every procurement operation runs a script-level
authorizedStoresprecheck before calling the target endpoint. - If no store has
status=ACTIVEandexpired=false, the target endpoint is not called. - After authorization is valid, procurement tools may be used independently as the user requests; the workflow is guidance, not a mandatory linear script. Image search remains in
linkfox-1688-search-by-image. - Treat the workflow as a map, not full automation. Do not create orders, get payment URLs, cancel orders, confirm receipt, or apply for invoices based on earlier phrases like "continue".
- Use exact internal request field names from
references/api.mdwhen calling scripts. Do not show these field names in normal user-facing text. - Treat ordinary 1688 procurement as the only user-facing procurement mode. Apply backend defaults internally per
references/api.md; do not mention procurement type or ask users to choose one. cancel_order.pyonly attempts to cancel a 1688 order. It is not a refund or after-sales request. For paid orders, including paid-but-unshipped orders, do not call cancellation as a workaround; tell the user this Skill has no refund-application tool and refunds/after-sales must be handled on 1688 unless the backend adds that ability.- MCP enable/disable only controls MCP exposure. These scripts call tool-gateway HTTP routes directly; fully disabling a capability requires disabling the route or backend operation.
What ships with it
19 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.
- references/api.md 18 KB
- references/onboarding.md 2.0 KB
- references/workflow.md 9.4 KB
- scripts/_alibaba1688_common.py 15 KB runs code
- scripts/authorize_url.py 124 B runs code
- scripts/authorized_stores.py 128 B runs code
- scripts/cancel_order.py 123 B runs code
- scripts/confirm_receive.py 126 B runs code
- scripts/create_order.py 123 B runs code
- scripts/invoice_amount.py 125 B runs code
- scripts/invoice_apply.py 124 B runs code
- scripts/logistics_trace.py 126 B runs code
- scripts/logistics.py 121 B runs code
- scripts/onboarding.py 24 KB runs code
- scripts/order_preview.py 124 B runs code
- scripts/order_status.py 123 B runs code
- scripts/payment_url.py 122 B runs code
- scripts/receive_address_list.py 130 B runs code
- scripts/sku.py 115 B 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.
- 12d ago First seen · 159 lines · 142 tokens per session scan A e61a4a0dabee
linkfox-1688-procurement is a skill published in the GitHub repository linkfox-ai/linkfox-skills (101 stars, last pushed 21d ago), licensed MIT. It adds 142 tokens to every session and 3,249 once invoked, about $0.0007 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
asc-ppp-pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.
stripe
Stripe API integration with managed OAuth. Manage customers, subscriptions, invoices, products, prices, and payments. Use this skill when users want to process payments, manage billing, or handle subscriptions with Stripe. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).…
etsy-pricing-strategy
Etsy pricing — cost calculation, competitor pricing, perceived value, shipping cost integration, sales and coupons.
amazon-wholesale-sourcing
Wholesale product sourcing — supplier discovery, negotiation, MOQ optimization, margin analysis.
ai-slop
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…
payment-processor
Skill "payment-processor" from Signal-Execution-Labs/forex-trading-ai-agent, covering payment processor skill, supported services, capabilities, view balances and get all balances.