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 ArrowsHQ/arrows-sales-skills --skill arrows-pre-call-prepgit clone --depth 1 https://github.com/ArrowsHQ/arrows-sales-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/arrowshq/arrows-sales-skills/arrows-pre-call-prep)<a href="https://agentmods.dev/skills/arrowshq/arrows-sales-skills/arrows-pre-call-prep"><img src="https://agentmods.dev/badge/skills/arrowshq/arrows-sales-skills/arrows-pre-call-prep/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/arrowshq/arrows-sales-skills/arrows-pre-call-prep"><img src="https://agentmods.dev/badge/skills/arrowshq/arrows-sales-skills/arrows-pre-call-prep.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 | $0.00193 | $0.10686 |
| Opus 5.5 | $0.00077 | $0.04274 |
| Sonnet 5.5 | $0.00039 | $0.02137 |
| Haiku 4.5 | $0.00019 | $0.01069 |
Grade A, and why
arrows-pre-call-prep 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 7d 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 — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A brief for one upcoming call that the person can scan in 60 seconds before joining. It's for them only, never the buyer.
| Section | What's in it |
|---|---|
| What this call is for | The agenda and what the buyer wants from it |
| Who's on the call | Each attendee's role on the deal, with flags (new, skeptic, champion) |
| What they want to solve | Their pain, goals and numbers, in their words |
| Last time and what's owed | What happened before, and commitments still open on either side |
| Still unknown | Gaps against the person's qualification method |
| What to push for | 2–4 outcomes for this call |
| Watch out for | Real risks, each with how to handle it |
| Their words | Phrases the buyer uses, to echo on the call |
Every section is optional. A first call with no history might be three sections long; that's right.
Step 1: Find the call
Look at the calendar for upcoming meetings with the company they named over the next 14 days, and match each one to a CRM deal.
- One match: go straight on. Name the call in the brief's header so a wrong pick is obvious. Don't stop to confirm; an extra round trip right before a call is the moment people give up.
- Several meetings, same deal: prep the next one and mention the later ones in a line at the end.
- Meetings for different deals or groups at the same company (for example two business units): ask which one, in one line per option with date, time, attendees and deal. This is the only time to ask.
- No company named: prep their next sales call: an external meeting with a buyer, prospect or customer (a CRM deal or contact, or a booking from a prospect), today or the next working day. Skip vendors, partners, agencies, recruiting and personal meetings (a partner or customer who booked through a sales or demo link counts as a sales call), and name what you skipped in one line at the end ("Skipped the 8:00 agency kickoff: not a sales call.").
- The company named is a vendor or partner (they sell to the person, or there's no buyer relationship): say so under the header and give a short meeting brief instead: who's attending, what's open on both sides, and what to get out of the call. Leave out the deal and qualification sections.
- No match: say so in two lines with the likely reason (different name on the invite, a calendar you can't see, not booked yet), and ask for the buyer's name or the meeting details.
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.
- 7d ago Changed · +6 lines 650f4f6976f8
- 11d ago Changed · +1 lines 80241ba68e45
- 21d ago Changed · +90 lines · +41 tokens per session d5b0350f9427
- 1mo ago First seen · 359 lines · 152 tokens per session scan A 0bae963ed1a4
arrows-pre-call-prep is a skill published in the GitHub repository ArrowsHQ/arrows-sales-skills (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 193 tokens to every session and 10,686 once invoked, about $0.0008 per session on Opus 5.5. 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
ib_0dte
Find and place the best 0DTE (zero-days-to-expiration) credit spreads from Interactive Brokers. Default execution route is the EMA9/EMA21 + VIX/VXN regime strategy (emavix0dte.py), which auto-selects bullput or bearcall from a bare EMA cross and skips the trade when the vol index is elevated (VXN ≥ 30 for NDX/QQQ, VIX…
ib-pmcc-advisor
Analyze PMCC (Poor Man's Covered Call / diagonal spread) positions from IB portfolio. For each diagonal spread, reports short leg risk (delta, IV, assignment probability), daily P&L projections, top-3 roll candidates, and a side-by-side comparison table. Requires TWS or IB Gateway running locally.
ib-stop-loss
Downside stop-loss management for PMCC, naked LEAPS, and stock positions in IB. Computes stop prices, detects alerts, and places conditional combo orders. Dry-run by default. Requires TWS or IB Gateway running locally.
ib-trades-history
Fetch trade executions from Interactive Brokers filtered by account, date range, or symbol. Supports live API (7 days history) and FlexReport (full history). Use when user asks about their trades, executions, or transaction history. Requires TWS or IB Gateway running locally.
ib-trailing-stop
Server-side trailing stop management for stocks and naked LEAPS in IB. Places native TRAIL orders that auto-ratchet the stop as price climbs. Dry-run by default. Requires TWS or IB Gateway running locally.
scanner-pmcc
Scan stocks for Poor Man's Covered Call (PMCC) suitability. Analyzes LEAPS and short call options for delta, liquidity, spread, IV, yield, trend direction, and earnings proximity. Use when user asks about PMCC candidates, diagonal spreads, or LEAPS strategies.