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 sahil-bloom-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/sahil-bloom-voice)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/sahil-bloom-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/sahil-bloom-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/sahil-bloom-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/sahil-bloom-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 | $0.00179 | $0.03405 |
| Opus 5.5 | $0.00072 | $0.01362 |
| Sonnet 5.5 | $0.00036 | $0.00681 |
| Haiku 4.5 | $0.00018 | $0.00341 |
Grade A, and why
sahil-bloom-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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sahil Bloom Voice DNA
Sahil Bloom left a finance career in 2021 and rebuilt his identity as a writer, publishing The Curiosity Chronicle every week since. The voice is a teacher who found his own life through the writing: a scroll-stopping opening line, a slow-told story from history or science, a named framework distilled out of that story, a short personal application, and a question the reader carries away. It is sincere rather than clever, and it treats every essay as a letter he is also writing to his own son. 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 declarative sentences, often one line alone as its own paragraph. Many sentences run 5 to 12 words.
- The essay shape is stable: cold-open hook, a slow narrative (historical figure, scientific study, or personal memory), the turn where he names the pattern, a short list of applications, then a direct question to the reader.
- Fragments are a deliberate rhythm device. "New shoes. An elaborate wooden desk." "More promotions. A new title, but the same arc."
- Repetition as a drumbeat: a key line gets restated near the close almost verbatim. "The fast lane becomes the slow lane" appears twice in one essay.
- Long-form newsletter essays run 900 to 1,600 words. The Friday Five format is short-form, five distinct mini-sections under one header.
Hook patterns
- The single-line cold open - a short, strange claim that starts the piece with no throat-clearing. "A fancy robe nearly destroyed a philosopher's life." Deploy as the first line of any essay.
- The scroll-stopping observation - naming the moment he noticed something. "I was recently sent a New York Times article with a headline that stopped my scroll."
- The mentor question - open on a question someone else asked him that he could not answer well. "So, what's your 5-year plan?"
- The harsh-truth list-opener - state plainly that most advice is comfortable and his will not be. "I'm convinced that the market for telling people what they want to hear is much larger than the market for telling people what they need to hear."
- The historical cold case - open on a year, a king, a scientist, or an explosion, with no framing yet of why it matters. "In 1625, King Gustavus Adolphus of Sweden commissioned the building of a new warship."
- The personal memory - a specific remembered scene, dated and located. "Last weekend, my family and I made our annual pilgrimage to a small community in northwest Connecticut."
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 Changed · +179 tokens per session 0057ff7da7d4
- 1mo ago First seen · 167 lines · 0 tokens per session scan A bcf5b32b9613
sahil-bloom-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 179 tokens to every session and 3,405 once invoked, about $0.0007 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 2026-09-10.
sahil-bloom-voice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sahil-bloom-voicejpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 179 | Claude Code |
| hr-onboardingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | yesterday | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | 25d ago | Apache-2.0 | A | 25 | Claude Code, Codex |