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-daily-briefgit 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-daily-brief)<a href="https://agentmods.dev/skills/arrowshq/arrows-sales-skills/arrows-daily-brief"><img src="https://agentmods.dev/badge/skills/arrowshq/arrows-sales-skills/arrows-daily-brief/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-daily-brief"><img src="https://agentmods.dev/badge/skills/arrowshq/arrows-sales-skills/arrows-daily-brief.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 | $0.00138 | $0.11540 |
| Opus 5.5 | $0.00055 | $0.04616 |
| Sonnet 5.5 | $0.00028 | $0.02308 |
| Haiku 4.5 | $0.00014 | $0.01154 |
Grade A, and why
arrows-daily-brief 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 — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A daily brief for today, short enough to read on a phone before the first call:
| Section | What's in it |
|---|---|
| Do first | The 2–5 things that matter most today, in order |
| Since yesterday | Buyer replies, stage changes, wins, losses, signed contracts |
| Today's calls | Each external call: who, where the deal stands, what's open |
| Replies waiting | Buyers who are waiting on the person |
| At risk | Deals that are going quiet or slipping |
| Team (leaders) | One line per rep: what's at risk, what's closing, what needs the leader |
| Open time | Free blocks of 30+ minutes |
Step 1: Read the profile
Use the profile files (see the shared context) to decide what matters, not just to describe it:
arrows-how-i-work.md:## What slipsis the person's own list of things to flag; check today's calls and deals for each one.## Where my time goestells you which prep to do for them.## My rulesapply to every suggested action.arrows-sales-process.md: stage names, what has to be true to move on, and the methodology under## Discovery and qualification. Use them to judge whether a deal is stuck.arrows-buyers-and-competitors.md: competitor names, so you recognize them when they come up.arrows-how-we-work.mdor a leader role in## About me: turn on the Team section (Step 3).
No profile, or it doesn't say: they lead a team if other people own most deals they're involved in (as a contact, follower or meeting attendee), or their calendar has recurring 1:1s with reps. If so, turn on Team.
No profile: run the brief anyway and use the CRM's stage names.
Step 2: Gather
Read everything before writing. Stay inside this budget so the brief finishes quickly:
- Calendar: every meeting on today. Sort them into sales calls (with a buyer, prospect or customer: a CRM deal or contact, or a booking from a prospect), other external meetings (vendors, partners, agencies, recruiting) and internal ones. Note open blocks of 30+ minutes.
- Each sales call: the matching CRM deal (stage, amount, close date, next step), the last 3–5 activities, the most recent call summary, and the latest email or chat thread with the attendees. Look for what was promised and whether it happened. If CRM is thin on a new contact, a quick web search for their role is enough. Deeper research belongs to pre-call prep.
- Since yesterday: everything since the start of the previous working day (on Monday, since Friday morning): buyer emails and chat messages received, deal stage changes, deals created, won or lost, contracts signed or viewed. Use CRM activity or stage history where it exists; otherwise compare last-modified dates and say the stage change is inferred.
- Replies waiting: buyer or prospect emails and direct messages from the last 7 days where the buyer wrote last and the person hasn't answered. Skip newsletters, automated mail, internal threads, group channels, and replies to a mass email (a webinar or newsletter) unless they ask the person something.
- Pipeline: open deals the person owns (for leaders, their team's), up to 150, using filtered queries rather than reading each record. Read notes only on deals that look at risk. If there are more, say how many you read.
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 30594b5571a9
- 11d ago Changed · +1 lines 23dc7b93da00
- 21d ago Changed · +112 lines · +59 tokens per session 77236a91e3d2
- 1mo ago First seen · 354 lines · 79 tokens per session scan A e1a50a752113
arrows-daily-brief is a skill published in the GitHub repository ArrowsHQ/arrows-sales-skills (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 138 tokens to every session and 11,540 once invoked, about $0.0006 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
customer-journey-map
Construye un mapa de recorrido del cliente para un producto, servicio o experiencia. Úsalo cuando se te pida mapear un recorrido del cliente, crear un viaje del usuario, documentar puntos de contacto y puntos de fricción, o diseñar un mapa de experiencia. Produce un mapa de recorrido completo con etapas, puntos de…
scenario-zbrush-expert
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted…
feature-prioritisation
Aplica marcos de priorización (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) para clasificar características e items del backlog. Úsalo cuando se te pida priorizar características, clasificar un backlog, decidir qué construir a continuación, o evaluar compensaciones entre ideas competidoras. Produce una lista de…
design-handoff-brief
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context…
outcome-tracker
Record the testable predictions inside a decision, then score them against reality later — so frameworks earn trust from outcomes, not vibes. Use when committing to a prioritisation, forecast, or plan (to log what it predicts), when asked to review what actually happened, or to compute how well-calibrated past RICE…
slide-deck
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDEDECKREPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand…