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 agentmods add skills/onewave-ai/open-agent-stack/call-prepnpx skills add OneWave-AI/open-agent-stack --skill call-prepgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWhat 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 | $0.00044 | $0.00410 |
| Opus 5 | $0.00022 | $0.00205 |
| Sonnet 5 | $0.00009 | $0.00082 |
| Haiku 4.5 | $0.00004 | $0.00041 |
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 2d 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
Call Prep
Walk in knowing more than the other side expects. Input: company name and meeting context (first call, demo, negotiation, renewal); attendee names/LinkedIn URLs if known; anything from the CRM or email thread history available.
Workflow
- Research the company. Web-search recent news, funding, leadership changes, hiring signals (what roles they are posting reveals priorities), and their own positioning language. Find the thing that changed recently -- meetings exist because something changed.
- Read the attendees. Role, tenure, likely care-abouts by function (a CFO hears risk and payback; an ops lead hears hours saved). Note shared ground if it is real; skip manufactured rapport.
- Pull the history. From CRM/email/notes provided: every prior touch, what was promised, open threads, and anything they told us before -- asking a question they already answered costs credibility.
- Write the brief, one page: why this meeting is happening (their trigger, not our pipeline stage), 5-7 discovery questions sequenced from situation to pain to stakes -- specific to their business, not a generic SPIN list; the 3 objections most likely for this profile, each with an honest answer; the single realistic goal for the call and the specific next step to propose before hanging up.
Rules
- Every discovery question must be un-Googleable -- if the answer is on their website, asking it burns the meeting.
- Objection answers are honest, including "that's a real limitation, here's the trade" where true.
- One goal per call. A brief with four goals produces a call with none.
- Flag what you could not verify; a brief with a wrong fact is worse than a gap.
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.
- 2d ago First seen · 23 lines · 44 tokens per session scan A f74b40545042
call-prep is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 410 once invoked, about $0.0002 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
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
agentmail
Use when an agent needs AgentMail CLI email inboxes.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
one-three-one-rule
1-3-1 decision briefs: problem, three options, one pick.