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 naveedharri/benai-skills --skill call-prepgit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/call-prep)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/call-prep"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/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/naveedharri/benai-skills/call-prep"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/call-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 65 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00109 | $0.01488 |
| Opus 5 | $0.00055 | $0.00744 |
| Sonnet 5 | $0.00022 | $0.00298 |
| Haiku 4.5 | $0.00011 | $0.00149 |
Grade A, and why
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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call Prep → Live Dashboard
Prep any sales call (or a whole day of them) and hand back one shareable live dashboard URL. This is a hybrid: the research depth of call prep, rendered in the BenAI instant-ui design language. The dashboard is the deliverable, never a markdown brief pasted into chat.
[!important] Non-negotiable output Every run ends with a deployed, shareable dashboard URL in the BenAI design system defined in
references/dashboard-template.html. Build by cloning that template, not from scratch. Report the URL first.
Workflow
1. Find the calls
- If the user names a call/company, use that. If they say "today" / "my calls", pull the calendar (calendar connector or
gws calendar) for that day and list every external meeting. Exclude internal syncs (team standups, 1:1s with colleagues). - Confirm scope only if genuinely ambiguous (e.g. many calls and unclear which). Otherwise proceed.
2. Research every call (parallel)
For multiple calls, fan out one sub-agent per call in parallel (Agent tool, general-purpose, run in background). Each agent researches its call and returns a compact brief. For a single call, do it inline.
Per call, pull from whatever is connected, and skip gracefully what is not:
- Web + LinkedIn, who the person is, the company (what they do, size, industry, recent news/funding), attendee roles. (WebSearch / WebFetch)
- Attio CRM, existing record, deal stage, budget band, notes. Load:
ToolSearch "select:mcp__7320cfa0-48c2-49b9-8bd6-96fe9605dabd__search-records,...__list-records,...__list-lists". - Gmail, recent threads with the attendees/domain: open questions, commitments, whether a proposal or recap was sent. Use
gws gmail search "<domain>"(Bash). - Fireflies, prior call transcript/recap if the meeting already ran. Load:
ToolSearch "select:mcp__plugin_benai-suite_fireflies__fireflies_search,...__fireflies_get_transcript".
Each brief must classify the call's stage (see color map below) and surface any action flag (unsent proposal, save situation, no-show to acknowledge, qualification risk).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 68 lines · 109 tokens per session scan A fd8b3a2b4444
call-prep is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 6d ago), licensed MIT. It adds 109 tokens to every session and 1,488 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
finance-investor-relations
An investor-relations tool for preparing pitch decks and three-year financial models for fundraising. An IR, or investor-relations, deck explains a company to potential investors, while the model covers sales, profit, cash flow, and valuation.