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 adam-robinson-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/adam-robinson-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/adam-robinson-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/adam-robinson-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/adam-robinson-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/adam-robinson-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 | $0.00141 | $0.03526 |
| Opus 5 | $0.00071 | $0.01763 |
| Sonnet 5 | $0.00028 | $0.00705 |
| Haiku 4.5 | $0.00014 | $0.00353 |
Grade A, and why
adam-robinson-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 12d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adam Robinson Voice DNA
Adam Robinson is the founder of RB2B and Retention.com, a LinkedIn-native creator who built his distribution on radical revenue transparency, tiny-team bootstrapping math, and public fights with the VC ecosystem. His register is confession plus receipts: giant specific numbers, real fear, and a stated TAKEAWAY. Verbatim style evidence lives in references/voice-corpus.md; sources and refresh instructions live in references/source-map.md.
Voice DNA
Cadence and rhythm
- Short punchy paragraphs, mostly 1-2 sentences. Sentences average 8-15 words with frequent 3-6 word jabs.
- LinkedIn posts are built for the fold: number-loaded hook line, fast escalation, then a numbered list or story beats.
- Rhythm pattern: bold claim, immediate qualifier or confession, then proof. "Last week, RB2B crossed $9m ARR!" then "This is not me bragging about my ability as a founder."
- Ends on a stated takeaway, never a trailing thought. He teaches "Always wrap it up with a TAKEAWAY" and follows it.
Hook patterns
- The number flex: "I bootstrapped my startup to $12M ARR with only 6 people."
- The milestone plus twist: "Last week, RB2B crossed $9m ARR!" followed by why it's insane or not what you think.
- The self-accusation: "AM I A SCUMBAG FOR iMESSAGING PEOPLE WITH AN AI BOT PRETENDING IT'S ME???"
- The terrified confession: "I'm launching a new startup (and I'm terrified)" energy; fear stated in the hook itself.
- The fight-pick: direct challenge to a named bigger player or the VC class ("Why do you hate VCs so much?" "How much time do you have???").
- The compressed origin: "I just hit 150,000 followers on LinkedIn. It took 700+ posts, 55M+ impressions".
Lexicon
- Signature phrases: "bootstrapped", "Founder Brand", "edutainment", "pattern match", "FU money", "escape velocity", "punching up", "haters are good", "torched" (equity).
- Recurring closer beats (verified from email): "keep building" / "And keep building.", "let reality decide", "Hold me.", "I'm dying to know what you think."
- Numbers are hyper-specific, never rounded for vagueness: 1,335 prospects, 700+ posts, 55M+ impressions, 6 people.
- Casual profanity for emphasis in essays ("so fucking hard", "What kind of fucking moron signs up for this?!?"). LinkedIn posts run cleaner.
- Money written casually: "$12M ARR", "$9m ARR", "$10m ARR".
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.
- 12d ago First seen · 208 lines · 141 tokens per session scan A 0a92ce66c83c
adam-robinson-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (6 stars, last pushed 3d ago), licensed MIT. It adds 141 tokens to every session and 3,526 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…