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-deal-nudgegit 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-deal-nudge)<a href="https://agentmods.dev/skills/arrowshq/arrows-sales-skills/arrows-deal-nudge"><img src="https://agentmods.dev/badge/skills/arrowshq/arrows-sales-skills/arrows-deal-nudge/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-deal-nudge"><img src="https://agentmods.dev/badge/skills/arrowshq/arrows-sales-skills/arrows-deal-nudge.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 | $0.00166 | $0.04616 |
| Opus 5.5 | $0.00066 | $0.01846 |
| Sonnet 5.5 | $0.00033 | $0.00923 |
| Haiku 4.5 | $0.00017 | $0.00462 |
Grade A, and why
arrows-deal-nudge 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 6d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gets a quiet or slipping deal moving again with one specific, honest move.
| Mode | When | What you get |
|---|---|---|
| One deal | A company is named | The play, and a send-ready nudge in the person's voice |
| Pipeline scan | "Which deals need a nudge?" | The deals at risk, ranked, with nudges drafted for the top 3 |
At risk
The same definition every Sales Skill uses. An open deal (not won, lost, or in an archived or closed-out stage) is at risk if any of these is true:
- Quiet: 14+ days with no two-way touch (a buyer reply, a meeting held, a buyer message in chat; unanswered outbound emails don't count). Check CRM, email, calendar and chat before calling a deal quiet.
- No next step: no next step recorded in the CRM and no future meeting on the calendar. A deal created in the last 14 days isn't at risk just for having no next step yet; that's noise on a new deal.
- Missed next step: a next step or promise, by either side, whose date passed without it happening ("I'll send the proposal Friday").
Say which of the three applies, with the date or day count, for every flagged deal ("quiet 23 days; last reply was [date]"). If you judged a deal from CRM fields alone (no email or calendar check), mark it "per CRM" so nobody acts on a false alarm.
Step 1: Find the deals
- One deal: find the open deal for the named company owned by (or shared with) the person. One match: go straight on, and name the deal in the first line of the output so they can redirect. Several open deals at that company: pick the one with the most recent activity, say which, and name the others in one line. None: say where you looked and ask for the exact deal name.
- Pipeline scan: apply the at-risk test to their open deals. Rank by what's at stake (amount, stage, close date) and how at risk (a missed next step beats quiet; longer quiet beats shorter).
Reading budget, so this finishes in one chat: filtered CRM queries, not record-by-record reads; up to 100 open deals; full context (Step 2) for at most 8. If there are more, take the largest and say so ("checked 100 of 240 open deals, largest first").
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.
- 6d ago Changed · +6 lines 212ef2c0510e
- 11d ago Changed · +1 lines b4db6eff7cd1
- 21d ago Changed · -71 lines · +11 tokens per session fa5c3679e50b
- 1mo ago First seen · 267 lines · 155 tokens per session scan A f669891ee33f
arrows-deal-nudge is a skill published in the GitHub repository ArrowsHQ/arrows-sales-skills (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 166 tokens to every session and 4,616 once invoked, about $0.0007 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.