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 ReachRobin/skills --skill prospect-twingit clone --depth 1 https://github.com/ReachRobin/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/reachrobin/skills/prospect-twin)<a href="https://agentmods.dev/skills/reachrobin/skills/prospect-twin"><img src="https://agentmods.dev/badge/skills/reachrobin/skills/prospect-twin/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/reachrobin/skills/prospect-twin"><img src="https://agentmods.dev/badge/skills/reachrobin/skills/prospect-twin.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 | $0.00052 | $0.02448 |
| Opus 5 | $0.00026 | $0.01224 |
| Sonnet 5 | $0.00010 | $0.00490 |
| Haiku 4.5 | $0.00005 | $0.00245 |
Grade A, and why
prospect-twin 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prospect Twin
Sales reps practice their pitches on coworkers who have never heard of the prospect and are too polite to push back. Coaches charge several hundred dollars an hour for roleplay that, at best, approximates the buyer. Prospect Twin builds a simulation of any specific LinkedIn prospect - their communication style, their priorities, their BS tolerance - so you can rehearse outreach against THEM before sending anything. The session ends with a debrief that tells you what landed and why.
This is interactive sales prep, not science fiction. The same information has always been available on LinkedIn; this skill just makes it actionable before the conversation starts.
Ethics framing
This is a practice tool. The persona is inferred from public LinkedIn information: headline, About section, experience history, and public posts. Nothing is stored, nothing is scraped beyond what you provide in the session. Functionally equivalent to reading someone's LinkedIn before a call - just interactive. The prospect receives no contact; you're practicing on a model, not the person.
If anything, lean into what this is: serious sales prep has always meant learning who you're talking to. We made it interactive.
When to use
- Preparing for a high-leverage cold DM or outbound call to a specific named prospect
- Iterating on openers before picking which version to actually send
- Testing whether a pitch framing lands with this type of buyer before running it at volume
- Training a new SDR against a realistic buyer archetype instead of a willing-but-uninformed teammate
- Building conviction that your sequence is ready for a high-priority account
When NOT to use
- You actually know the person - skip the simulation, use your own knowledge
- You have no meaningful profile data (the profile is mostly empty, or the person has no public posts or activity) - a thin profile produces a thin persona; note this and reduce confidence accordingly
- The prospect is a non-public-figure private individual without a professional LinkedIn presence - do not build personas on private individuals outside a professional sales context
What ships with it
2 files 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 · 178 lines · 52 tokens per session scan A 2057003a6f36
prospect-twin is a skill published in the GitHub repository ReachRobin/skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 2,448 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
champion-move-outreach
End-to-end champion/buyer/user job change signal composite. Takes a set of known people (past buyers, champions, power users), detects when they move to a new company, researches the new company for ICP fit, and drafts personalized outreach leveraging the existing relationship. Tool-agnostic — works with any people…
leadership-change-outreach
End-to-end leadership change signal composite. Takes any set of companies, detects recent leadership changes (new VP+, C-suite hires and promotions), evaluates relevance to your product, and drafts personalized outreach. Uses Apollo People Search (free) for fast detection + Apollo Enrichment (1 credit/person) for…
news-signal-outreach
End-to-end news-triggered signal composite. Takes any piece of news — an article, LinkedIn post, tweet, announcement, event, trend, regulation, product launch, acquisition, layoff, expansion, or any other public event — and evaluates whether the companies or people mentioned are ICP fits. If yes, identifies the…
funding-signal-outreach
End-to-end funding signal composite. Takes any set of companies, detects recent funding events, qualifies against your company context, finds relevant people (buyers, champions, users), and drafts personalized outreach. Tool-agnostic — works with any company source, contact finder, and outreach platform.
hiring-signal-outreach
End-to-end hiring signal composite. Takes any set of companies, detects job postings that your product augments or replaces, finds relevant people (the hiring manager, buyers, champions, users), and drafts personalized outreach using the job role as the hook. Tool-agnostic — works with any company source, job board…
email-drafting
Write high-converting cold emails using structured frameworks, personalization tiers, and patterns from real campaigns. Pure reasoning skill — no scripts. Auto-loads when any task requires outreach copy.