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-forecastgit 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-forecast)<a href="https://agentmods.dev/skills/arrowshq/arrows-sales-skills/arrows-forecast"><img src="https://agentmods.dev/badge/skills/arrowshq/arrows-sales-skills/arrows-forecast/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-forecast"><img src="https://agentmods.dev/badge/skills/arrowshq/arrows-sales-skills/arrows-forecast.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 | $0.00281 | $0.14911 |
| Opus 5.5 | $0.00112 | $0.05964 |
| Sonnet 5.5 | $0.00056 | $0.02982 |
| Haiku 4.5 | $0.00028 | $0.01491 |
Grade A, and why
arrows-forecast 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 today.
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 — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Period: this month (or the month or quarter the person names)
A CRM forecast is a stage probability and a close date someone typed in. This skill gives the other read: what a bystander who sat in on every call and read every email would say about each deal, how likely it is to close and when, judged only from what the buyer said and did. It shows that next to the CRM's number so the person can see where the pipeline is ahead of the evidence and where it's behind, deal by deal.
It is about the CRM and the buyers, never about the people selling. A gap means the stage or close date doesn't match what the buyer has done yet; it does not mean a rep is wrong.
| Section | What's in it |
|---|---|
| Header | "[Company] objective forecast" (personal view: "[Name]'s objective forecast"), one line explaining the two numbers, a bar of commit / likely / possible / unlikely by value, and four numbers: deals dated this period in the CRM, what the CRM says, what the evidence says, and what's likely to slip (or the goal and coverage, when a goal is known) |
| What will really close, and when | Every deal in the period, most likely first: the label, the buyer's own date when there is one, the one thing the buyer hasn't done yet, and the one move on the seller's side that would get it done; open any deal for the evidence |
| CRM ahead of the evidence | Deals whose stage probability or close date is ahead of what the buyer has done, by money at stake, each with CRM % → evidence %, CRM date → evidence date, and the one fact behind it |
| Further along than the CRM shows | Deals the evidence rates higher than the stage, with the buyer fact that earned it |
| Likely to slip | Deals whose evidence date lands after the period, and the value that leaves the period with them |
| By rep (leaders) | Each rep's CRM total vs. the evidence and one question for their 1:1; open a rep for their deals |
| How the forecast works | The rubric in plain words, so anyone can check a number |
The default output is a visual report built from one fixed template (end of this skill), so it looks the same every run. A short summary goes in the chat alongside it.
Progress
Post a short progress line once at the top, then one line per source as it finishes, with a real number:
Sales Skills by Arrows · Objective forecast ■■□□□ Reading your calls
✓ CRM: 6 deals dated this month ($134k), 3 owners
✓ Calls: 40 calls on those deals in the last 60 days
✓ Email: checked 108 logged threads for buyer-side signals
– Calendar: not connected (using CRM meeting dates)
Stages: Reading your CRM / Reading your calls / Reading your email ■□□□□ · Scoring the evidence ■■■□□ · Building your report ■■■■□ · Done ■■■■■.
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.
- today First seen · 537 lines · 281 tokens per session scan A 185817d1a18b
arrows-forecast is a skill published in the GitHub repository ArrowsHQ/arrows-sales-skills (4 stars, last pushed today), licensed Apache-2.0. It adds 281 tokens to every session and 14,911 once invoked, about $0.0011 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 2026-10-17.
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 ≥ 35 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-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.
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.
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-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.