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 OneWave-AI/open-agent-stack --skill account-briefgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/account-brief)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/account-brief"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/account-brief.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00483 |
| Opus 5 | $0.00028 | $0.00242 |
| Sonnet 5 | $0.00011 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
account-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.
What it actually says
Account Brief
The account rep's answer to "catch me up on this account" -- assembled from what the systems already know. Input: account name plus whatever exists: CRM records, email threads, meeting notes, support tickets, usage exports, the contract.
Workflow
- Timeline. Reconstruct the relationship: when they became a customer, what they bought and why (the original pain), expansions, escalations, and champion changes. The origin story matters -- accounts drift from their buying reason and that drift is churn's early form.
- Stakeholder map. Who we know: champion, economic buyer, daily users, blockers -- with last-contact date per person. Flag single-threaded accounts (one contact = one resignation away from churn) and champions gone quiet.
- Health read. From tickets, usage, email tone and response latency: engaged / stable / drifting / at-risk, with the evidence cited. Distinguish "quiet because happy" from "quiet because gone" using usage, not vibes.
- The clocks. Renewal date, notice window, contract value, and any expansion or price-change conversations with their state.
- Openings. Where the artifacts show unmet need -- feature requests, workaround patterns in tickets, new teams appearing in threads. Expansion asks trace to observed need or they do not appear.
- Output. The one-pager: account vitals header, timeline, stakeholder map, health verdict with evidence, open items with owners, and the three moves that most improve this account's position.
Rules
- Every claim cites its artifact; a brief the exec can't trust once is a brief they never trust again.
- Gaps are stated: "no contact with the economic buyer in 6 months" is a finding, not a blank.
- Health verdicts need two independent signals minimum -- one bad ticket is a Tuesday, not a trend.
- Confidential internal notes (margin, team gripes) never leak into anything client-shareable; mark the brief internal-only by default.
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 First seen · 25 lines · 55 tokens per session scan A 0e0066e08be8
account-brief is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 26d ago), licensed MIT. It adds 55 tokens to every session and 483 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 skills, from other repositories
comps-analysis
Build comparable-company valuation workbooks in Excel.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
pretext
Build creative browser demos with DOM-free text layout.
pinggy-tunnel
Zero-install localhost tunnels over SSH via Pinggy.
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.