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.
git 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/commands/dcs-premium-freight-srl/claude-for-freight/cold-start-interview)<a href="https://agentmods.dev/commands/dcs-premium-freight-srl/claude-for-freight/cold-start-interview"><img src="https://agentmods.dev/badge/commands/dcs-premium-freight-srl/claude-for-freight/cold-start-interview/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/commands/dcs-premium-freight-srl/claude-for-freight/cold-start-interview"><img src="https://agentmods.dev/badge/commands/dcs-premium-freight-srl/claude-for-freight/cold-start-interview.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 | $0.00057 | $0.01789 |
| Opus 5 | $0.00028 | $0.00894 |
| Sonnet 5 | $0.00011 | $0.00358 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade A, and why
cold-start-interview 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold-start interview
You are running the first-time setup for the freight-forwarding plugin.
The output is a Markdown file at:
~/.claude/plugins/config/claude-for-freight/freight-forwarding/CLAUDE.md
Every other skill in this plugin reads from that file before doing anything else. Your job here is to capture enough about the operator's practice that the next skill run produces output the operator could actually use, not a generic template.
Two modes
Ask the operator which mode they want:
Quick start (2 minutes, 6 questions). Minimum viable — company identity and one example RFQ. Everything else fills in over the next few uses as the operator corrects the skills.
Full setup (10–15 minutes, 25 questions). Recommended. Walks through lanes, escalations, agent network, currency conventions, document standards. The output is materially sharper.
Default to quick start if the operator doesn't pick — and offer the full setup explicitly at the end ("want to go deeper? takes another 10 min").
Quick start questions
Ask these six, in this order, one at a time. Wait for the answer before moving on.
- Company. "What's the legal name of your company, the EORI/VAT number, and the address you use as default shipper on documents?"
- Contact. "What's the email and phone you sign documents with?"
- Modes. "Which modes do you cover — air, sea, road, rail, multimodal?" (Multi-select. Use as default for skill output.)
- Reference format. "What format do your shipment reference numbers
follow? (e.g.,
DCS-2026-0142,ACME-25-####)" - Currency. "Default currency for quotes?" (EUR, USD, GBP, other.)
- Example RFQ. "Paste one real RFQ email you handled recently — inbound or outbound, doesn't matter. I'll learn your tone and reference style from it."
Write the quick-start profile and confirm to the operator. Then ask:
"Quick start done. Want to do the full setup now? Adds ten minutes and makes everything sharper — covers your lanes, escalation thresholds, trusted agents per lane, IATA divisor preferences, and how you handle charter / OBC / DG."
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 · 220 lines · 57 tokens per session scan A c6c3e0047fcf
cold-start-interview is a command published in the GitHub repository DCS-Premium-Freight-SRL/claude-for-freight (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,789 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 2026-08-31.
Other commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
discuss
5-phase requirements-elicitation interview that produces an EARS-validated context/ .md.
fix
Universal debugging and fix application with semantic code analysis.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
design
A command that turns an existing plan into a detailed technical design for building the feature.