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 miron-tech/wholesaler-claude-skills --skill conversation-coachgit clone --depth 1 https://github.com/miron-tech/wholesaler-claude-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/miron-tech/wholesaler-claude-skills/conversation-coach)<a href="https://agentmods.dev/skills/miron-tech/wholesaler-claude-skills/conversation-coach"><img src="https://agentmods.dev/badge/skills/miron-tech/wholesaler-claude-skills/conversation-coach/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/miron-tech/wholesaler-claude-skills/conversation-coach"><img src="https://agentmods.dev/badge/skills/miron-tech/wholesaler-claude-skills/conversation-coach.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 | $0.00073 | $0.07996 |
| Opus 5.5 | $0.00029 | $0.03198 |
| Sonnet 5.5 | $0.00015 | $0.01599 |
| Haiku 4.5 | $0.00007 | $0.00800 |
Grade A, and why
conversation-coach 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 29d 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 — 661 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seller Conversation Coach Skill
Purpose: Tell you exactly what to say next in a seller conversation — based on what they've already said, what they're feeling, what your property intel shows, and what will move the deal forward.
WHAT THIS SKILL DOES
- Analyzes any seller conversation — text threads, email exchanges, call notes, or transcripts
- Identifies the seller's motivation level, emotional state, and objections
- Detects creative finance opportunities from what the seller says about their mortgage
- Incorporates Property Recon / Comp Analyzer data when available (value, comps, tax status)
- Recommends the exact next message or talking point
- Explains WHY the recommendation works (so you learn, not just copy)
- Predicts likely seller responses and how to handle each one
- Flags red flags, deal-killers, and channel switching opportunities
WHAT THIS SKILL DOES NOT DO
- Does not auto-send messages for you
- Does not replace building genuine rapport — it coaches, not controls
- Does not generate fake empathy or manipulative scripts
- Does not make legal promises ("we can stop your foreclosure")
INPUTS NEEDED
| Input | Required | Example |
|---|---|---|
| Conversation transcript | Yes | Paste the full text thread, email chain, or call notes |
| Lead source | Helpful | "Probate," "pre-foreclosure," "cold call," "driving for dollars," "tax delinquent" |
| What you want to accomplish | Helpful | "Get them to agree to a walkthrough," "overcome the price objection," "re-engage after going cold" |
| Your offer / numbers | Helpful | "I'm thinking $65K cash, ARV is $180K" |
| Property Recon data | Helpful | If already run — value, owner info, tax status, comps, mortgage history |
GOAL
- Primary: Move the conversation one step closer to a signed contract
- Secondary: Detect creative finance opportunities and coach the right questions to gather deal data
- Tertiary: Teach the wholesaler to read seller signals and respond strategically
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.
- 29d ago First seen · 661 lines · 73 tokens per session scan A bdbcd647dfcb
conversation-coach is a skill published in the GitHub repository miron-tech/wholesaler-claude-skills (53 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 7,996 once invoked, about $0.0003 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 2026-10-09.
conversation-coach compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| conversation-coachmiron-tech/wholesaler-claude-skills | Skill | 53 | 1mo ago | MIT | A | 73 | Claude Code, Codex |
| Stripedanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 83 | Claude Code, Codex |
| CardBenefitsdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 137 | Claude Code, Codex |
| prompt-proximity-architectureelvisun/newsjack | Skill | 1.7k | yesterday | MIT | A | 67 | Claude Code |
| agent-spending-mandatemohitagw15856/pm-claude-skills | Skill | 1.5k | yesterday | MIT | A | 113 | Claude Code |
| company-cfocoreyhaines31/makerskills | Skill | 890 | yesterday | MIT | A | 202 | Claude Code |
| personal-cfocoreyhaines31/makerskills | Skill | 890 | yesterday | MIT | A | 209 | Claude Code |