agentmods.dev

sara-blakely-voice

sara-blakely-voice is a skill for Claude Code from jpeslar1/john-peslar-ai-skills. It costs 201 tokens per session (3,026 once invoked), scanned A, original, MIT.

A writing guide based on the documented style of Sara Blakely, the founder of Spanx and Sneex. It focuses on warm origin stories, resilience posts, and writing about women founders.

In plain words
What is it for?
Use it to draft founder origin stories, posts about persistence, and personal updates built around a memorable object, scene, joke, and closing lesson.
Why use it?
It helps turn an ordinary experience into a concrete, self-deprecating story with a clear lesson. The supplied style rules provide structure without requiring the writer to invent a voice.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

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

not rated 12repo +1 18d ago A scan 201 tokens original MIT

Good fit Use it to draft founder origin stories, posts about persistence, and personal updates built around a memorable object, scene, joke, and closing lesson.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jpeslar1/john-peslar-ai-skills/sara-blakely-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 sara-blakely-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 sara-blakely-voice

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/sara-blakely-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/sara-blakely-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,026 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 $0.00201 $0.03026
Opus 5.5 $0.00080 $0.01210
Sonnet 5.5 $0.00040 $0.00605
Haiku 4.5 $0.00020 $0.00303

Measured 18d ago against content hash f22347fc4432, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sara-blakely-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.

sara-blakely-voice/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sara Blakely Voice DNA

Sara Blakely is the founder of Spanx and Sneex, the door-to-door fax-machine seller who cut the feet off her pantyhose, built a billion-dollar company without outside capital, and told the story in public for twenty years. Her written voice lives on LinkedIn and Instagram (the same captions, cross-posted): a scene with a physical prop, a self-deprecating joke, exclamation marks and ellipses doing the rhythm, and a closing moral in the imperative. Her spoken voice adds "belief system," "gut and intuition," and the stated tactic that a laugh buys you thirty more seconds. Ground every output in references/voice-corpus.md (verbatim excerpts) and references/source-map.md (sources and refresh notes).

Voice DNA

Cadence and rhythm

  • Scene first, moral last: the post opens on a concrete moment with an object in it (pantyhose, a SPANX license plate, a cardboard sign, a closet during a conference call) and closes on a one- or two-line imperative.
  • Ellipses are breath marks and drumrolls, mid-sentence, several per post: "the before and after butt model 😳... everything!" / "I'll just know." Well that day is today."
  • Sentences are short and spoken, 8-16 words; exclamation marks multiply at peaks ("Spanx turns 19 today!!!!!", "BOOTS!!!").
  • Posts run 80-250 words; brand letters (Sneex launches) run 250-400 and are signed "Xo, Sara Blakely."
  • Spoken register is looser and warmer, with "you know," "I always say," and "belief system" as connective tissue; the fax-machine years are the recurring anchor.

Hook patterns

  1. The prop scene - "So I cut the feet out of my pantyhose and the very first prototype for Spanx was born." Deploy as the opener for any origin or milestone post.
  2. The underestimated setup - "When I first started Spanx it was really difficult to get anyone to take me seriously." Deploy for resilience and women-founder content.
  3. The quoted pressure - what other people kept saying, in quotes: "hang in there, someone is going to figure out you're a good catch." Deploy to set up a reversal ("Oh, and I built my empire too. 👊").
  4. The anniversary count - "Spanx turns 19 today!!!!!" / "Fast forward 22 years later…" Deploy for milestone posts; the number is the hook.
  5. The ridiculous confession - "Cue the DMV!!! I had the brilliant idea of registering SPANX as my license plate." Deploy for humor-led posts that end in a lesson.
  6. The reader question - "Anybody else taking conference calls hiding in a closet?" Deploy as an opener or closer to invite replies.

Read the full file on GitHub · 163 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. 18d ago First seen · 163 lines · 201 tokens per session scan A f22347fc4432

Subscribe to this mod's changes

sara-blakely-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 201 tokens to every session and 3,026 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.

Writing and docs
Related

sara-blakely-voice compared with skills from other repositories

sara-blakely-voice next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sara-blakely-voicejpeslar1/john-peslar-ai-skillsSkill1218d agoMITA201Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code