write-like-me

write-like-me is a skill for Claude Code from ne11nn/cantos-plugin. It costs 83 tokens per session (779 once invoked), scanned A, original, MIT.

A writing and rewriting tool that uses stored samples of the user's professional or creative voice. It also checks for writing patterns associated with AI-generated text.

In plain words
What is it for?
Drafting or rewriting text in the user's voice, humanising copy, and checking writing for unwanted AI-style patterns.
Why use it?
It helps keep drafts consistent with the user's existing style instead of relying on a guessed voice.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the cantos plugin — 25 skills, 2 commands, 11 agents, 2 hooks 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 skills/ne11nn/cantos-plugin/write-like-me
Any agent
npx skills add ne11nn/cantos-plugin --skill write-like-me
Clone the repo
git clone --depth 1 https://github.com/ne11nn/cantos-plugin

Made for: Claude Code.

Or install cantos, the plugin that ships this one along with the rest of its 25 skills, 2 commands, 11 agents, 2 hooks.

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-like-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/ne11nn/cantos-plugin/write-like-me.svg)](https://agentmods.dev/skills/ne11nn/cantos-plugin/write-like-me)
Your own site
<a href="https://agentmods.dev/skills/ne11nn/cantos-plugin/write-like-me"><img src="https://agentmods.dev/badge/skills/ne11nn/cantos-plugin/write-like-me.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 779 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 5.1 $0.00083 $0.00779
Opus 5 $0.00042 $0.00390
Sonnet 5 $0.00017 $0.00156
Haiku 4.5 $0.00008 $0.00078

Measured 5d ago against content hash 58f5f62539af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

write-like-me 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 5d 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.

system/.claude/skills/write-like-me/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: write-like-me

Invocation: /write-like-me, or triggers like "write this in my voice", "sound like me", "humanize this", "make this less AI", "draft as me", "in my words".

Produces text that reads like the USER wrote it: it matches their learned style and avoids AI-writing tells. This is the generative end of the writing pipeline — the opposite of ai-detect, which scans and scores. Use them together: write in voice here, verify the score with /ai-detect if the stakes are high.


Inputs

  • The text to write (a brief or outline) or rewrite (an existing draft).
  • Register: professional or creative. If the user does not say, infer it (formal / work / academic → professional; personal / casual / narrative → creative) and state which you chose.

Step 1 — Load the voice

  1. Read references/writing-voice/profile-{register}.md.
  2. If it is still the placeholder (no profile has been generated), STOP. Tell the user folio needs to learn their voice first, and offer to run workflows/folio/analyze_writing_voice.md. Do not fabricate a voice from nothing — a guessed voice is worse than asking.
  3. Read references/signs-of-ai-writing.md — the catalog of tells to avoid.

Step 2 — Write in voice

Draft (or rewrite) applying, in priority order:

  1. The profile's Do this patterns — reproduce the user's real habits: cadence, diction, stance, structure, openings and closings.
  2. The profile's Never do this list — do not introduce habits the user never uses.
  3. Against every tell in references/signs-of-ai-writing.md — no significance inflation, no rule-of-three, no negative parallelisms ("not just X, but Y"), no em-dash overuse, no elegant variation, no copula avoidance, no mechanical transition uniformity, no perfect uniform polish, no filler phrases.

When rewriting, preserve the user's meaning and every fact. Change only the expression.


Step 3 — Self-audit before returning

Re-read the draft against three checklists and fix every miss:

Read the full file on GitHub · 68 lines

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. 5d ago First seen · 68 lines · 83 tokens per session scan A 58f5f62539af

Subscribe to this mod's changes

write-like-me is a skill published in the GitHub repository ne11nn/cantos-plugin (1 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 779 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

stream-chain

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.

spencermarx/open-code-review · 18 tokens

run

Run the agents-concerto multi-agent development pipeline for a task — classify by complexity, implement in isolated worktrees (TDD + Tidy First), review under a two-party boundary, and stop at open PRs for human merge. Invoke explicitly with a task description; a weak or empty description is shaped interactively first…

moruno21/agents-concerto · 77 tokens

setup

Bootstrap agents-concerto in the current project by interviewing the user for every configurable option — target repos (with per-repo PR host), tasksource, base branch, commit convention, and fix-cycle cap — then writing a filled .agent-workspace/config.md. Detects sensible defaults and asks for confirmation rather…

moruno21/agents-concerto · 73 tokens

shape

Turn a rough idea into a well-formed task the pipeline can run — interrogate the ambiguity, derive testable acceptance criteria, flag contradictions, and write .agent-workspace/feature-request.md in the exact shape /run consumes. The upstream step before /agents-concerto:run. Invoke explicitly with a rough idea.

moruno21/agents-concerto · 68 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens