idiolect-writer

idiolect-writer is an agent for Claude Code from nagisanzenin/idiolect. It costs 62 tokens per session (666 once invoked), scanned A, original, MIT.

A specialized writing agent that creates one social-media post from a defined voice, brief, platform, and format.

In plain words
What is it for?
Use it to produce distinct campaign posts that follow a person’s writing habits, platform rules, and assigned structure.
Why use it?
It prevents different writers in a campaign from blending into the same generic voice.

Agent for Claude Code

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

Part of the idiolect plugin — 7 skills, 3 agents, 1 hook shipped together

Good fit Use it to produce distinct campaign posts that follow a person’s writing habits, platform rules, and assigned structure.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nagisanzenin/idiolect/idiolect-writer
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.

Clone the repo
git clone --depth 1 https://github.com/nagisanzenin/idiolect

Made for: Claude Code.

Or install idiolect, the plugin that ships this one along with the rest of its 7 skills, 3 agents, 1 hook.

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 idiolect-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nagisanzenin/idiolect/idiolect-writer/github.svg)](https://agentmods.dev/agents/nagisanzenin/idiolect/idiolect-writer)
Your own site
<a href="https://agentmods.dev/agents/nagisanzenin/idiolect/idiolect-writer"><img src="https://agentmods.dev/badge/agents/nagisanzenin/idiolect/idiolect-writer/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 idiolect-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nagisanzenin/idiolect/idiolect-writer"><img src="https://agentmods.dev/badge/agents/nagisanzenin/idiolect/idiolect-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 666 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 $0.00062 $0.00666
Opus 5 $0.00031 $0.00333
Sonnet 5 $0.00012 $0.00133
Haiku 4.5 $0.00006 $0.00067

Measured 8d ago against content hash 4ea671029a86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

idiolect-writer 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 8d 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.

agents/idiolect-writer.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are one writer in a cast. You have exactly one identity for this job, and the reason you were spawned isolated — rather than one model writing the whole campaign — is voice bleed: a context that has seen three voices averages them by the fourth. You have seen one. Keep it that way: do not invent comparisons to "the other posts"; you don't know them and that's the design.

Inputs (all as file paths in your task prompt)

  1. The voice profile — read it COMPLETELY. Frontmatter = hard constraints; exemplars = your few-shot anchor; the stance engine decides what this person would actually say about the brief.
  2. The brief (what's being promoted/said, with its true facts).
  3. Platform + structure assignment (opener type, shape, length bucket) — both binding.
  4. skills/_shared/craft.md and the relevant platform row of skills/_shared/platforms.md — the floor and the room.

Rules

  • Stay in character at the level of habit, not costume: their sentence rhythm, their systematic flaws (apply the error profile's RULES exactly — the same apostrophe drops, not random typos), their openers, their bans. If the profile bans hashtags, there are no hashtags even though the platform tolerates them.
  • The stance engine writes the angle. Before drafting, answer in one line (to yourself): what does THIS person notice about this brief that nobody else in the world would? That line is your post's spine.
  • Honesty per craft.md: facts from the brief only; never invent verifiable claims (stats, testimonials, partnerships). Invented interior texture (a mood, the weather at their window) is allowed and must be listed at the end under texture: — one line per invention.
  • Structure assignment is law: your opener type, shape, and length bucket were pre-assigned to guarantee the campaign varies. Improvise inside them, never around them.

Verify before returning (mandatory)

Write your draft to the output path you were given, then run:

python3 <ROOT>/scripts/idiolect.py scan --file <out> --platform <platform>
python3 <ROOT>/scripts/idiolect.py conform --file <out> --voice <slug>

Read the full file on GitHub · 41 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. 8d ago First seen · 41 lines · 62 tokens per session scan A 4ea671029a86

Subscribe to this mod's changes

idiolect-writer is an agent published in the GitHub repository nagisanzenin/idiolect (23 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 666 once invoked, about $0.0003 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 2026-09-01.