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 DCS-Premium-Freight-SRL/claude-for-freight --skill rfq-draftinggit clone --depth 1 https://github.com/DCS-Premium-Freight-SRL/claude-for-freightWrote 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/dcs-premium-freight-srl/claude-for-freight/rfq-drafting)<a href="https://agentmods.dev/skills/dcs-premium-freight-srl/claude-for-freight/rfq-drafting"><img src="https://agentmods.dev/badge/skills/dcs-premium-freight-srl/claude-for-freight/rfq-drafting/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/dcs-premium-freight-srl/claude-for-freight/rfq-drafting"><img src="https://agentmods.dev/badge/skills/dcs-premium-freight-srl/claude-for-freight/rfq-drafting.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 | $0.00205 | $0.02182 |
| Opus 5 | $0.00102 | $0.01091 |
| Sonnet 5 | $0.00041 | $0.00436 |
| Haiku 4.5 | $0.00020 | $0.00218 |
Grade A, and why
rfq-drafting 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RFQ drafting
Drafts the email that asks for or answers a freight quote. Direction matters: inbound and outbound have different structures, different tones, and different required fields.
Read the profile first
Pull from CLAUDE.md:
- Company identity (legal name, address, contact, sign-off block)
- Reference format
- Default incoterms (inbound and outbound)
- Default currency
- Agent network for lane suggestions
- Lane preferences and time-critical defaults
- Example RFQ captured at cold-start (for tone)
If no profile, prompt the operator to run
/freight-forwarding:cold-start-interview first. Skill refuses to draft
without identity, because a draft with placeholder sender details is worse
than no draft.
Classify direction
First decide: is this inbound (we're answering a customer) or outbound (we're asking a carrier/agent)?
Signals:
- "draft RFQ to [an agent name we recognize]" → outbound
- "respond to RFQ from [customer]" or pasted customer enquiry → inbound
- "ask Aramex / DHL / our Frankfurt agent for a rate" → outbound
- "the customer wants a quote on" → inbound
If genuinely ambiguous, ask once: "This for the carrier (asking for a rate) or for the customer (replying with a quote)?"
Outbound RFQ — workflow
Required fields
Gather, then draft:
- Origin — city + country + (airport IATA / port / postal code)
- Destination — same
- Cargo — pieces × dimensions, gross weight (compute chargeable via the
cargo-calculationskill if not already done) - Commodity — generic description; HS code if known
- Incoterms — from profile default if customer didn't specify
- Ready date or "ready immediately"
- Special requirements — time-critical, ADR, temperature, automotive line-stop, OBC eligible, DG class
- Carrier(s) to send to — from profile agent network, or operator-named
Lane-specific routing
When the lane matches a lane in the profile, suggest the trusted agents for that lane in priority order. "For OTP–FRA you usually go to [Agent A] then [Agent B] — send to both for benchmark?"
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 · 264 lines · 205 tokens per session scan A b28ee1c80ea9
rfq-drafting is a skill published in the GitHub repository DCS-Premium-Freight-SRL/claude-for-freight (8 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 205 tokens to every session and 2,182 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
logistics-expert
Expert-level supply chain management, logistics optimization, warehouse systems, and fleet management. Use when the user mentions supply chain, warehouse, fleet, or optimization, or when the task involves Supply Chain Management or Technologies.
maritime-expert
Expert-level maritime systems, vessel tracking, port operations, cargo management, and maritime logistics. Use when the user mentions shipping, logistics, vessel, port, or Cargo, or when the task involves Maritime Systems, Maritime Technologies, Standards and Protocols, or Vessel Operations.
supply-chain-expert
Build comprehensive supply chain solutions including demand planning, inventory management, supplier coordination, and logistics optimization. Use when the user mentions supply chain, demand planning or forecasting, inventory and safety stock, procurement, supplier management, warehousing, or logistics optimization.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.