io-monad

io-monad is a skill for Claude Code from ncaq/konoka. It costs 45 tokens per session (756 once invoked), scanned A, original, Apache-2.0.

A Haskell guideline for writing input/output code through type classes such as MonadIO and MonadUnliftIO instead of requiring the concrete IO type everywhere. Type classes let the same action work in suitable monads, including monad transformer stacks.

In plain words
What is it for?
Use it when writing or reviewing Haskell IO actions, monad transformers, or functions intended to work across different effect contexts.
Why use it?
It reduces unnecessary liftIO calls and makes effectful code easier to reuse with other monads. It also gives clearer rules for passing actions to libraries that require ordinary IO.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the haskell-tasuke plugin — 19 skills shipped together

Good fit Use it when writing or reviewing Haskell IO actions, monad transformers, or functions intended to work across different effect contexts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ncaq/konoka/io-monad
View source ↗ ncaq/konoka
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.

Any agent
npx skills add ncaq/konoka --skill io-monad
Clone the repo
git clone --depth 1 https://github.com/ncaq/konoka

Made for: Claude Code.

Or install haskell-tasuke, the plugin that ships this one along with the rest of its 19 skills.

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 io-monad

README.md
[![agentmods](https://agentmods.dev/badge/skills/ncaq/konoka/io-monad/github.svg)](https://agentmods.dev/skills/ncaq/konoka/io-monad)
Your own site
<a href="https://agentmods.dev/skills/ncaq/konoka/io-monad"><img src="https://agentmods.dev/badge/skills/ncaq/konoka/io-monad/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 io-monad

Your own site · 80×15
<a href="https://agentmods.dev/skills/ncaq/konoka/io-monad"><img src="https://agentmods.dev/badge/skills/ncaq/konoka/io-monad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 756 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 $0.00045 $0.00756
Opus 5 $0.00023 $0.00378
Sonnet 5 $0.00009 $0.00151
Haiku 4.5 $0.00005 $0.00076

Measured 9d ago against content hash 6cb2dfe14cb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

io-monad 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 9d 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.

plugins/haskell-tasuke/skills/io-monad/SKILL.md · 69 lines

What it actually says

IOモナドの扱い

IOをなるべく直接使わず型クラスを使う

IOモナドはプリミティブすぎます。

他のモナド変換子などと一緒に取り扱うのが不便です。

呼び出すたびにliftIOを使うのは面倒です。

なのでアクションを定義するときは出来る限りIOを直接使うのではなく、 MonadIOや、 MonadUnliftIOといった、 型クラスで抽象化するべきです。

MonadIOの方がより一般的なので、 先にそちらで定義出来ないか検討するべきです。

MonadUnliftIOの定義では、

class MonadIO m => MonadUnliftIO (m :: Type -> Type)

となっているため、 MonadUnliftIOのインスタンスは必ずMonadIOのインスタンスも持ちます。 なのでMonadUnliftIOの中でMonadIOの関数を呼び出すことはできるので、 MonadIOにすることに問題はありません。

MonadUnliftIOが要求される場合はそちらで定義してください。

IO内部でMonadUnliftIOのアクションを実行する

MonadIOMonadUnliftIOの文脈でIOのアクションを実行する場合はliftIOを使うだけで良いです。

IOの文脈でMonadUnliftIOのアクションを実行する場合はひと工夫必要な時があります。

以下の関数を使うことで解決できます。

askRunInIO :: MonadUnliftIO m => m (m a -> IO a)

askRunInIOMonadUnliftIOの文脈で呼び出すことで、 MonadUnliftIOのアクションをIOに変換する関数を取得できます。

この関数をrunInIO関数などの名前で束縛して、 IOを要求するライブラリの型に対して、 MonadUnliftIOのアクションをrunInIOで包んで渡すことが出来ます。

または単発で済むならば以下の関数を使っても良いでしょう。

toIO :: MonadUnliftIO m => m a -> m (IO a)

無駄なliftIOの禁止

既にMonadIO m => m aのような型を持っている関数を、 liftIOに渡しても問題なく動きますが、 無意味に冗長で読みにくいので、 liftIOなしでそのまま呼び出してください。

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. 9d ago First seen · 69 lines · 45 tokens per session scan A 6cb2dfe14cb6

Subscribe to this mod's changes

io-monad is a skill published in the GitHub repository ncaq/konoka (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 756 once invoked, about $0.0002 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.