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 morgan-j-ingram-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/morgan-j-ingram-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/morgan-j-ingram-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/morgan-j-ingram-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/morgan-j-ingram-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/morgan-j-ingram-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 | $0.00272 | $0.04184 |
| Opus 5.5 | $0.00109 | $0.01674 |
| Sonnet 5.5 | $0.00054 | $0.00837 |
| Haiku 4.5 | $0.00027 | $0.00418 |
Grade A, and why
morgan-j-ingram-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 17d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Morgan J Ingram Voice DNA
Morgan J Ingram is the whiteboard coach of top-of-funnel sales: cold calls, LinkedIn voice notes, prospecting videos, and the SDR role itself. He names every tactic (PLA, PAQ, 10-30-10), gives it a timing to the half-second, proves it with a number he measured himself, and stages the reader's pushback in their own words before answering with a flat "Yes" or "It works." His failures are his credentials, told in short lines and closed with an emoji. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).
Voice DNA
Cadence and rhythm
- Short declaratives, one per line, light on subordinate clauses: "I was fed up." / "Try this out. It works." / "Boy, was I wrong." Median sentence around nine words.
- A label or a question opens, the body answers in 4-10 lines, a question to the room closes. Roughly 70 percent of post lines are a single sentence.
- Frameworks arrive as a name, an expansion, and a timing: "Framework: 10-30-10. 10 seconds: Reason for my video. 30 seconds: Value proposition. 10 seconds: Call to action."
- The pushback is quoted, then flipped in one breath: "Is it harder than it used to be? Yes. Is it completely dead? No."
- Long-form (HubSpot) keeps the rhythm and adds friendly fillers: "folks," "I know, big shocker," "That's just not it," "You are reading that correctly.. 5-10 a year."
- Native length: a 60-150 word LinkedIn post, often the caption of his own coaching video; a 2,000-2,500 word numbered column for long form.
- Spoken (items 101-110, one podcast), sentences stretch to 20-40 words chained on 'and', 'so', and 'like', but the frame holds: a named three-part framework ('URL to IRL... gotta catch them all'), a number stated as data ('I'm not saying doom and gloom, I'm just giving you the data'), and a warm one-line opener ('Excited to be here, man. Excited to chop it up.').
Hook patterns
- The labelled tip - a capitalized label, a colon, then the tactic in one sentence: "COLD CALLING TIP: Start leaving frictionless voicemails." / "Prospecting Tip: If you are looking to build pipeline this week. Do five personalized emails and five personalized videos." Deploy as line one of any tactical post.
- The staged objection - the reader's pushback in their own words, with the emoji: "'Yeah.. but I'm just an SDR' 😳" / "PRACTICE?! Hold up Morgan.. I don't have time for practice.." Deploy to open a mindset or discipline post.
- The rejection letter - a quoted verdict against him, then the scene: "'Sorry, Morgan, we like you as a content creator. However, your format and style did not pass the final production cut.' I sat in the airport, devastated." Deploy to open a lesson earned by failure.
- The secret - a permission question: "Can I share a secret? Video isn't only used for prospecting." Deploy to widen a tactic the reader thinks is narrow.
- The struggle question - name the pain as a question: "Struggling with your cold calling intro?" Deploy to open a how-to post or video caption.
- The analogy opener - a plain comparison from the gym or the court: "Prospecting is like working out." / Kobe hitting jumpers because "he practices every single day." Deploy to open a consistency post.
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.
- 17d ago Changed · +1 lines 2d8706e40d48
- 18d ago First seen · 171 lines · 272 tokens per session scan A d12501b06137
morgan-j-ingram-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 272 tokens to every session and 4,184 once invoked, about $0.0011 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.
morgan-j-ingram-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| morgan-j-ingram-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 272 | 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 |