synthesize

synthesize is a skill for Claude Code from nagisanzenin/idiolect. It costs 67 tokens per session (901 once invoked), scanned A, original, MIT.

A tool for creating a new writing-voice profile from writing samples or a designed style. A voice profile records the patterns that define how text should sound.

In plain words
What is it for?
It is for measuring a writing corpus or designing a new fictional voice with examples and style checks.
Why use it?
It helps when the available writing styles do not fit the desired voice.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; mentions OpenCode.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

Good fit It is for measuring a writing corpus or designing a new fictional voice with examples and style checks.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add nagisanzenin/idiolect
Claude Code
/plugin install 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 synthesize

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nagisanzenin/idiolect/synthesize"><img src="https://agentmods.dev/badge/skills/nagisanzenin/idiolect/synthesize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 901 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 $0.00067 $0.00901
Opus 5 $0.00034 $0.00451
Sonnet 5 $0.00013 $0.00180
Haiku 4.5 $0.00007 $0.00090

Measured 11d ago against content hash a92b8b596d95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

synthesize 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.

skills/synthesize/SKILL.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.

/idiolect:synthesize — grow the roster

New voices are measured into existence, not adjective-ed. A synthesized voice ships with the same contract as the built-ins: full VOICE-SPEC frontmatter, stance engine, systematic error profile, three exemplars that scan clean, and distance ≥ 0.2 from every existing voice.

Setup

ROOT="${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-$IDIOLECT_ROOT}}"
# unset everywhere (opencode)? ROOT = two directories up from this SKILL.md
IDIO="python3 $ROOT/scripts/idiolect.py"
$IDIO path   # note custom_voices dir — new voices are written THERE, never into the plugin

Mode 1 — from a corpus

  1. Consent gate (one question, then done): if the corpus is the writing of a single identifiable person who is not the user, ask once: is this your own writing or writing you're authorized to model? If yes (or it's the user's own / mixed public material), proceed; note the answer in the profile's provenance line. The output is always a NEW fictional voice influenced by the corpus's stylistic features — this skill does not build impersonation kits of named people, and single-author clones overfit anyway.
  2. Concatenate the samples into one scratch file. $IDIO fingerprint --file <f> --json > fp.json — this measures what adjectives can't: sentence-length distribution, burstiness, contraction rate, punctuation profile, casing habits, informal markers, favorite content words.
  3. $IDIO synth-scaffold --slug <slug> --from-fingerprint fp.json — a prefilled skeleton with the measured stylo numbers.
  4. Spawn idiolect-synthesizer with: the scaffold, fp.json, the corpus file path, and $ROOT/docs/VOICE-SPEC.md. It drafts the full profile into the custom voices dir and runs the validate loop itself. (No subagent support on this platform? Do its job yourself following $ROOT/agents/idiolect-synthesizer.md.)
  5. Verify the roster still separates: $IDIO validate <slug> must pass; $IDIO distance --json must show no pair under 0.2. If the new voice sits too close to an existing one, push the DIFFERENTIATING axes (error class, platform habitat, humor mechanics, openers) — not random noise.
  6. Deliver: profile path, the three exemplars, scan scores, nearest-neighbor distance. The voice is immediately usable: /idiolect:write <slug> ....

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 · 67 tokens per session scan A a92b8b596d95

Subscribe to this mod's changes

synthesize is a skill published in the GitHub repository nagisanzenin/idiolect (23 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 901 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens