write

write is a skill for Claude Code, Codex from nagisanzenin/idiolect. It costs 62 tokens per session (1,203 once invoked), scanned A, original, MIT.

A writing workflow for producing short social posts in a selected person’s established voice and checking the result for generated-sounding language.

In plain words
What is it for?
It is used for posts, captions, announcements, and replies written as a named person or a defined personal style.
Why use it?
It helps create platform-appropriate text that matches a particular voice instead of relying on a generic tone.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the idiolect plugin — 7 skills, 3 agents, 1 hook 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/nagisanzenin/idiolect/write
Any agent
npx skills add nagisanzenin/idiolect --skill write
Clone the repo
git clone --depth 1 https://github.com/nagisanzenin/idiolect

Made for: Claude Code, Codex.

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 write

README.md
[![agentmods](https://agentmods.dev/badge/skills/nagisanzenin/idiolect/write.svg)](https://agentmods.dev/skills/nagisanzenin/idiolect/write)
Your own site
<a href="https://agentmods.dev/skills/nagisanzenin/idiolect/write"><img src="https://agentmods.dev/badge/skills/nagisanzenin/idiolect/write.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,203 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 $0.00062 $0.01203
Opus 5 $0.00031 $0.00602
Sonnet 5 $0.00012 $0.00241
Haiku 4.5 $0.00006 $0.00120

Measured 3d ago against content hash 387128407226, 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.

skills/write/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/idiolect:write — one post, one person, verified

You are about to write as a specific human being. Not "in a casual tone" — as a person with a biography, grudges, a phone number, and systematic typing habits. The engine measures whether you succeeded.

Setup

Resolve the engine (works on Claude Code, Codex, opencode):

ROOT="${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-$IDIOLECT_ROOT}}"
# If all three are unset (e.g. opencode skill install), ROOT = two directories
# up from this SKILL.md file (skills/write/SKILL.md -> repo root).
IDIO="python3 $ROOT/scripts/idiolect.py"

Free text (briefs, drafts) reaches the engine ONLY via files or stdin — write it with the Write tool to a scratch file and pass --file. Never inline user text into a shell command (quoting bugs become injection).

Flow

  1. Parse the ask. Voice, platform, brief — all optional except some notion of what to say. Voices may arrive as fuzzy human references ("the HVAC guy", "the Vietnamese food-truck lady", "someone young and lowercase"): resolve them against $IDIO voices --json (display/archetype/locale/domains) and proceed, mentioning the match in passing. No platform stated → infer from the ask and say which you assumed. Never require a flag or a slug from the user.

  2. Pick the voice (if not specified): write the brief to a scratch file, then $IDIO pick --platform <p> --brief-file <f> --n 3 --distinct --json Choose the best fit from the three and tell the user in one line who you chose and why. self is a valid voice if the user has built one ($IDIO voices shows it).

  3. Become the person. Read, fully: the voice profile (path from voices --json), $ROOT/skills/_shared/craft.md, and the platform's row + judgment calls in $ROOT/skills/_shared/platforms.md. The profile's exemplars are your few-shot anchor; the frontmatter is your hard constraint set; the stance engine tells you what this person would actually SAY about the brief — which is the difference between costume and voice.

Read the full file on GitHub · 55 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. 3d ago First seen · 55 lines · 62 tokens per session scan A 387128407226

Subscribe to this mod's changes

write is a skill published in the GitHub repository nagisanzenin/idiolect (22 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,203 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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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