agentmods.dev

balaji-srinivasan-voice

balaji-srinivasan-voice is a skill for Claude Code from jpeslar1/john-peslar-ai-skills. It costs 276 tokens per session (3,982 once invoked), scanned A, original, MIT.

A style guide based on Balaji Srinivasan’s numbered, future-focused essays and posts. It favours compressed theses, defined opposing ideas, historical evidence, and step-by-step arguments.

In plain words
What is it for?
Use it for technology essays, posts about networks and society, and structured arguments about possible futures.
Why use it?
It helps organise ambitious or controversial ideas into a structure readers can follow. It also makes new terms and claims explicit instead of leaving them unexplained.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the voice-dna plugin — 79 skills shipped together

not rated 12repo +1 changed 17d ago A scan 276 tokens original MIT

Good fit Use it for technology essays, posts about networks and society, and structured arguments about possible futures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jpeslar1/john-peslar-ai-skills/balaji-srinivasan-voice
View source ↗ jpeslar1/john-peslar-ai-skills
Install

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.

Any agent
npx skills add jpeslar1/john-peslar-ai-skills --skill balaji-srinivasan-voice
Clone the repo
git clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-skills

Made for: Claude Code.

Or install voice-dna, the plugin that ships this one along with the rest of its 79 skills.

Wrote 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.

agentmods badge for balaji-srinivasan-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/balaji-srinivasan-voice/github.svg)](https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/balaji-srinivasan-voice)
Your own site
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/balaji-srinivasan-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/balaji-srinivasan-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.

agentmods 80×15 button for balaji-srinivasan-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/balaji-srinivasan-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/balaji-srinivasan-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 276 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,982 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00276 $0.03982
Opus 5.5 $0.00110 $0.01593
Sonnet 5.5 $0.00055 $0.00796
Haiku 4.5 $0.00028 $0.00398

Measured 17d ago against content hash 366d6ddde4cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

balaji-srinivasan-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.

balaji-srinivasan-voice/SKILL.md · 167 lines

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.

Balaji Srinivasan Voice DNA

Balaji Srinivasan writes the future as an engineering spec. A chapter or a post opens on a one-sentence thesis compressed to the edge of outrage ("All property becomes cryptography." / "History is running in reverse." / "We're headed for something far worse than 2008."), hinges on "Let me explain why." or "Let's go.", and then enumerates: seven steps, ten thoughts, one commandment. New ideas arrive as paired terms (network state versus nation state, lands versus minds, polytheistic versus monotheistic AI) that are defined once and then used bare. Evidence is history with a receipt attached (thalidomide behind the FDA, 722 banks, ~40:1 odds), and the stance is exit rather than protest: "a toolbox, not a manifesto." Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).

Voice DNA

Cadence and rhythm

  • Median sentence around 14 words in the book and Substack; on X, one complete clause per line, 3-9 words, five to seven lines per post, no bullets or numerals needed: "Rate hikes weren't telegraphed. / Go back to March 2021. / Inflation was a conspiracy theory."
  • The thesis is a one-liner, the support is enumerated, and the closer repeats the thesis: "All property becomes cryptography. Let me explain why." ... "All property becomes cryptography."
  • Rhetorical question answered in the next line: "Why am I not that worried about AGI? Because I think if it happens, we'll have multiple AGIs."
  • Engineer's connectives carry the lecture: "That is:", "Basically,", "So,", "Indeed,", "The reason is that".
  • Spoken (Uncapped 2025, documented ASR): the same thesis-then-enumeration skeleton as a long monologue, heavy "you know" / "right?" / "okay" tags, quiz questions he answers himself ("you know what tech is?"), and "Anyway, point is" to return from digressions.
  • Native length: a 1,500-4,000 word Substack essay built from a thread, with charts and footnotes; a book section of 300-1,000 words; a 5-7 line X post.

Read the full file on GitHub · 167 lines

Files

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.

Changes

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.

  1. 17d ago Changed · +1 lines 366d6ddde4cc
  2. 18d ago First seen · 166 lines · 276 tokens per session scan A 7bcdf7206204

Subscribe to this mod's changes

balaji-srinivasan-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 276 tokens to every session and 3,982 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.

Learning and teachingWriting and docs
Related

balaji-srinivasan-voice compared with skills from other repositories

balaji-srinivasan-voice next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
balaji-srinivasan-voicejpeslar1/john-peslar-ai-skillsSkill1218d agoMITA276Claude Code
hr-onboardingnexu-io/open-designSkill106kyesterdayApache-2.0A62Claude Code, Codex
book-mirrorgarrytan/gbrainSkill32kyesterdayMITA138Claude Code
exam-forecastanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A73Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA81Claude Code
eli5companion-inc/feynmanSkill10k6d agoMITA63Claude Code, Codex
deck-course-modulenexu-io/html-anythingSkill9.4k25d agoApache-2.0A25Claude Code, Codex