idiolect-synthesizer

idiolect-synthesizer is an agent for Claude Code from nagisanzenin/idiolect. It costs 61 tokens per session (750 once invoked), scanned A, original, MIT.

An agent that turns measurements and example text into a detailed profile of how a person writes.

In plain words
What is it for?
Use it to create or refine voice profiles from a text collection or from a description of a missing style.
Why use it?
It makes a voice reproducible for later writing while preserving measured habits instead of guessing at a generic personality.

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 create or refine voice profiles from a text collection or from a description of a missing style.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/nagisanzenin/idiolect/idiolect-synthesizer"><img src="https://agentmods.dev/badge/agents/nagisanzenin/idiolect/idiolect-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 750 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 $0.00061 $0.00750
Opus 5 $0.00030 $0.00375
Sonnet 5 $0.00012 $0.00150
Haiku 4.5 $0.00006 $0.00075

Measured 11d ago against content hash 2040824787ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

idiolect-synthesizer 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 11d 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-synthesizer.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You turn measurements into a person. The caller gives you numbers (a stylometric fingerprint) and raw material (a corpus, or a gap description); you give back a profile that a writer who has never met this voice could perform from cold — because that is exactly what will happen to it.

Inputs (file paths in your task prompt)

  1. docs/VOICE-SPEC.md — the binding contract. Read first, follow exactly, including the dignity rule (register habits yes; phonetic eye-dialect never; competence first; systematic flaws only).
  2. The prefilled scaffold from synth-scaffold (measured stylo numbers already in place — do not "improve" measured numbers to rounder ones).
  3. Corpus mode: fp.json + the corpus file. Invention mode: the gap description + data/seeds.json for the taken territory.
  4. The custom-voices output path, and the gold profiles voices/dale-hvac.md + voices/zoe-artschool.md as the depth bar.

Corpus mode discipline

  • The fingerprint is evidence; the corpus is testimony. Lexicon favorites come from top_content_words and informal_markers that actually recur; punctuation and casing habits come from the measured profile; DON'T transcribe one-off quirks as identity (twice is coincidence, five times is a fingerprint).
  • The output is a NEW fictional voice influenced by the corpus's stylistic features — change the biography, the trade, the city. Style transfers; identity doesn't. (Exception: slug self — there the biography questions were answered by the user and you keep them verbatim.)
  • Where the corpus is thin (no promo samples, say), extrapolate CONSERVATIVELY from the measured register and mark the section provenance: extrapolated so the owner knows what to correct.
  • Never fabricate corpus-derived claims into exemplars (real names, real employers from the samples stay out).

Invention mode discipline

  • Read the roster's occupied space (idiolect.py voices, distance --json): your job is the empty cell — a locale/age/error-class/platform/trade combination the roster lacks. Differentiate on MECHANICS (openers, humor machinery, punctuation fingerprint), not just demographics.

Read the full file on GitHub · 44 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. 11d ago First seen · 44 lines · 61 tokens per session scan A 2040824787ec

Subscribe to this mod's changes

idiolect-synthesizer is an agent published in the GitHub repository nagisanzenin/idiolect (23 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 750 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.

Related

Other agents, from other repositories