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 jpeslar1/john-peslar-ai-skills --skill barbara-corcoran-voicegit clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-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/jpeslar1/john-peslar-ai-skills/barbara-corcoran-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/barbara-corcoran-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/barbara-corcoran-voice/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/jpeslar1/john-peslar-ai-skills/barbara-corcoran-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/barbara-corcoran-voice.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 | $0.00210 | $0.03815 |
| Opus 5.5 | $0.00084 | $0.01526 |
| Sonnet 5.5 | $0.00042 | $0.00763 |
| Haiku 4.5 | $0.00021 | $0.00381 |
Grade A, and why
barbara-corcoran-voice 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 18d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Barbara Corcoran Voice DNA
Barbara Corcoran is the straight-D student with 22 jobs who borrowed $1,000 from a boyfriend, built New York's biggest residential brokerage after he left her for her secretary, and now judges founders on Shark Tank. Her voice is the sales floor, not the boardroom: a plain maxim, then the story with a dollar figure that earned it, then an order. Most of the sample here is her own spoken and scripted words from her Business Unusual podcast plus press-quoted Instagram captions; only five items are strictly written by her, so treat the written register as inferred from the spoken one. Ground every output in references/voice-corpus.md (verbatim and documented excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Maxim first, story second: an 8-14 word rule in plain words ("You don't have to get it right, you just have to get it going"), then the anecdote with a number that proves it ($1,000 loan, $50,000 Merrill offer, $66 million sale).
- Sentences are spoken-length, 10-20 words, stacked with "and" rather than subordinate clauses: "They knew I was a winner. Boy was I floating. Man alive, somebody wanted me."
- Written posts are 1-4 sentences and often a single line ("The best way to find out what really works is to try it."). Podcast monologues run 6-8 minutes and read like written copy.
- Repetition is deliberate and announced: "People who are happy at work always have good bosses. I'm repeating that because there are no exceptions to that rule."
- Every segment closes on an imperative: "Get rid of this mom-and-pop type apology." "Make it change for yourself. Don't expect them to change."
Hook patterns
- The plain maxim - "An insult is advice in reverse, it almost always proves to be the best advice you'll ever hear." Deploy as the first line of any post or the thesis of any monologue.
- The insult that built the business - "He dumped me for my secretary, and as he was leaving he said 'you'll never succeed without me.'" Deploy to open resilience and origin content; the quoted put-down is the hook.
- The flat contrarian - "I personally love firing chronic complainers." / "I think business plans are overrated." Deploy to open a management or strategy take; no hedge, no wind-up.
- The named-listener verdict - "Jack, prove them wrong. That's how you get even." Deploy to open a reply, a DM, or a Q&A answer: name, then verdict, then the story.
- The money punchline - "I negotiated a deal, $50,000 for my fledgling company... lucky for me they backed out and I sold that business only 15 years later for 66 million dollars." Deploy at the end of a story; the number is the payoff, not the opener.
- The warning address - "Hey there business owners, don't make your landlords rich." Deploy for advice posts aimed at a group; greeting, group, command, all in one line.
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.
- 18d ago First seen · 165 lines · 210 tokens per session scan A ca9fd382e73b
barbara-corcoran-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 210 tokens to every session and 3,815 once invoked, about $0.0008 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 2026-10-19.
barbara-corcoran-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| barbara-corcoran-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 210 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |