write

write is a command for coding agents from Syedomershah99/being-human. It costs 14 tokens per session (409 once invoked), scanned A, original, MIT.

A command for drafting text in a user's established writing style, based on a saved voice profile. It checks the draft with a scoring script and revises it until it meets the required score or a choice is deliberately retained.

In plain words
What is it for?
Use it to write replies or other text in the user's voice, while applying their notes, preferred register, vocabulary, and avoid list.
Why use it?
It avoids inventing a writing style from scratch and catches generated wording that may sound fluent but unlike the user.

Command

Part of the being-human plugin — 1 skill, 5 commands, 1 hook, 1 MCP server shipped together

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.

agentmods
npx agentmods add commands/syedomershah99/being-human/write
Clone the repo
git clone --depth 1 https://github.com/Syedomershah99/being-human

Or install being-human, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 1 hook, 1 MCP server.

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 write

README.md
[![agentmods](https://agentmods.dev/badge/commands/syedomershah99/being-human/write.svg)](https://agentmods.dev/commands/syedomershah99/being-human/write)
Your own site
<a href="https://agentmods.dev/commands/syedomershah99/being-human/write"><img src="https://agentmods.dev/badge/commands/syedomershah99/being-human/write.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 409 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00409
Opus 5 $0.00007 $0.00204
Sonnet 5 $0.00003 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured 3d ago against content hash 30ce4d353597, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write 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 3d 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.

commands/write.md · 47 lines

What it actually says

Write this in their voice: $ARGUMENTS

Load first. Read .being-human/voiceprint.md before drafting anything. If it doesn't exist, run /being-human:learn first — don't draft from your defaults and call it their voice.

Pay attention to ## notes as much as the measured sections. The numbers give you form; the notes give you what they'd actually say.

Pick the register. Most voiceprints have two. A quick reply and a considered piece are different modes of the same person. Match the one this situation calls for rather than the average.

Draft. Hit the burstiness ratio deliberately — it's the strongest single tell and the easiest to miss, because even prose reads fine to you. Use their vocabulary. Avoid the words on the personal avoid list.

Score it before showing it:

python3 scripts/slopscore.py <draft> --in .being-human/

Revise and re-score until it clears 85, or until what's left is a deliberate choice you can defend. Then show them the draft and the score together.

Do not hand over an unscored draft. The whole point is that self-assessment doesn't work here — generated prose reads fluent to the thing that generated it.

the line

Match the voice. Never bend a fact to fit it.

Don't invent an anecdote because the voice would carry one. Don't add a number you don't have because specifics score better than abstractions. Don't claim an experience they haven't described to you.

When the voice wants a concrete detail and you don't have one, ask for it. A convincing voice wrapped around a fabricated fact is worse than generic prose, because generic prose doesn't get believed.

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. 3d ago First seen · 47 lines · 14 tokens per session scan A 30ce4d353597

Subscribe to this mod's changes

write is a command published in the GitHub repository Syedomershah99/being-human (0 stars, last pushed 21d ago), licensed MIT. It adds 14 tokens to every session and 409 once invoked, about $0.0001 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.