What is fletch-pmm-voice?

A writing guide based on the style and positioning methods of Fletch PMM, a B2B software messaging consultancy. Positioning means clearly stating who a product is for and why it differs from alternatives.

Use it for homepage critiques, product positioning, narrow target-customer arguments, and B2B software messaging.

It helps find and remove vague homepage copy that tries to speak to everyone. It encourages one clear audience, problem, and difference at a time.

fletch-pmm-voice — Skill for Claude Code by jpeslar1

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 fletch-pmm-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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/fletch-pmm-voice/github.svg)](https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/fletch-pmm-voice)

Your own site

<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/fletch-pmm-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/fletch-pmm-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/fletch-pmm-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/fletch-pmm-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 286 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,920 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.

Model	Per session	Once invoked
Fable 5.1	$0.00286	$0.03920
Opus 5.5	$0.00114	$0.01568
Sonnet 5.5	$0.00057	$0.00784
Haiku 4.5	$0.00029	$0.00392

Measured 17d ago against content hash d82e8d9ea0c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fletch-pmm-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.

fletch-pmm-voice/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fletch (Anthony Pierri and Robert Kaminski) Voice DNA

Fletch is two people with one register. Anthony Pierri is the heckler: conversational, personal, "I'm saying this all as an Attio customer btw," happy to pick a running ad and ask what it means. Rob Kaminski is the framework builder: mirrored pairs ("Every niche company wants a bigger TAM. Every company chasing a big TAM wants a niche they can own."), tidy numbered logic, emoji bullets, a parody methodology with a deadpan closer. The newsletter blends both into a worked parable. The shared doctrine is narrow: a homepage exists to explain the product, positioning is a specific segment plus a differentiation, and the villain is copy that says everything but explains nothing. Ground every output in references/voice-corpus.md (verbatim excerpts, each tagged with its speaker) and references/source-map.md (sources and refresh notes).

Voice DNA

Cadence and rhythm

One idea per line, blank line between, the argument built as a staircase: "Whatever you do, don't question the product. / You're one feature away from product-market fit. / Probably."
Ellipses carry the reader across the break and set up the reversal: "Okay fair enough... / ...but is it possible that they could potentially convert EVEN BETTER if they made sense immediately??"
Rob's mirror pairs: two parallel sentences that swap subject and object. Anthony's asides: a lowercase "btw" or "Anyways" that resets the tone.
Lists are arrows or steps, never prose: "→ why choose us over HubSpot, Salesforce, etc." / "↳ What is it? ↳ Who is it for? ↳ When would I use it?"
Native length: a 6-18 line LinkedIn post, often a caption for a one-slide visual argument; the newsletter runs 1,500-3,000 words as a parable with stats.
Spoken (items 101-110, one podcast with both), Anthony runs long and self-deprecating and argues by analogy (the Shark Tank discovery questions); Rob stays short and flat and lands a deadpan line ('You're the big baby.'). Rob swears casually on air ('didn't know shit'), which the written sample almost never does.

Read the full file on GitHub · 166 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.

17d ago Changed · +1 lines d82e8d9ea0c8
18d ago First seen · 165 lines · 286 tokens per session scan A a0b661dfa6de

Subscribe to this mod's changes

fletch-pmm-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 286 tokens to every session and 3,920 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.

Marketing and SEO Writing and docs

fletch-pmm-voice next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fletch-pmm-voicejpeslar1/john-peslar-ai-skills	Skill	12	18d ago	MIT	A	286	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