NeoHaskell: Skill for Claude Code

.pi/skills/neohaskell-concept-derivation/SKILL.md

neohaskell-concept-derivation is a skill for Claude Code, Codex from neohaskell/NeoHaskell. It costs 118 tokens per session (1,874 once invoked), scanned A, original, Apache-2.0.

A guide for declaring NeoHaskell concepts such as queries, commands, events, and integrations with Template Haskell markers. These markers generate routine type-class code automatically.

In plain words
What is it for?
Use it when creating or editing marked concept types, their companion functions, and business-logic instances.
Why use it?
It prevents duplicated generated code and the compile errors that can result from writing those instances by hand.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is neohaskell/NeoHaskell's own configuration. It tells Claude Code and Codex how to work on NeoHaskell itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NeoHaskell configures →

Reuse

Borrowing it

Nothing to install: this file belongs to neohaskell/NeoHaskell. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/neohaskell/NeoHaskell/main/.pi/skills/neohaskell-concept-derivation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/neohaskell/NeoHaskell

Made for: Claude Code, Codex.

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 neohaskell-concept-derivation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/neohaskell/neohaskell/neohaskell-concept-derivation"><img src="https://agentmods.dev/badge/skills/neohaskell/neohaskell/neohaskell-concept-derivation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,874 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00118 $0.01874
Opus 5 $0.00059 $0.00937
Sonnet 5 $0.00024 $0.00375
Haiku 4.5 $0.00012 $0.00187

Measured 11d ago against content hash 278c2cbf6bb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

neohaskell-concept-derivation 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.

.pi/skills/neohaskell-concept-derivation/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NeoHaskell concept derivation

Every core concept type (query, command, event, outbound integration) has a Template Haskell marker that emits the mechanical instances it needs. The marker is the canonical way to declare the concept. Your job is to author the data type plus the required companion functions and business-logic instances — never the boilerplate the marker owns.

The rule

Use the marker. Author only what the marker cannot: the data type, the required companion functions, the required marker-specific type instances (a command's EntityOf/TransportsOf — never the query NameOf/EntitiesOf the marker generates), and the business-logic instances. Never hand-write an instance the marker emits.

Markers are idempotent (they call Service.TH.Boilerplate.emitInstanceIfMissing, which reifies existing instances and skips them). So a hand-written deriving (Show, Generic) or instance ToJSON next to a marker is silently redundant at best — and a hard Duplicate instance GHC error if you place it after the marker. Both are the noise this skill exists to remove.

The markers (ground truth — read the module, don't recall)

Concept Marker Module Emits (skipped if already in scope) You author
Query deriveQuery ''Q [''E1, ''E2] Service.Query.TH Show, Generic, FromJSON, ToJSON, ToSchema, NameOf Q = "Q", EntitiesOf Q = '[E1,E2], Query (wires canAccessImpl = canAccess, canViewImpl = canView, and maxResultsImpl = maxResults if maxResults is defined), KnownHash the data type; canAccess and canView (required, top-level); maxResults :: Int (optional cap); one QueryOf entity Q instance per contributing entity (business logic)
Command command ''C Service.CommandExecutor.TH Show, Generic, FromJSON, ToJSON, NameOf C = "C", Command (wires getEntityIdImpl = getEntityId, decideImpl = decide, and the multi-tenancy mode), KnownHash the data type; getEntityId and decide (required); type instance EntityOf C = SomeEntity (required); type instance TransportsOf C = '[WebTransport] for HTTP commands
Event event ''E Service.Event.TH Show, Generic, FromJSON, ToJSON the data type; for a domain event driven through the store: type instance EventOf/EntityOf and instance Event (business getEventEntityIdImpl)
Outbound outboundIntegration ''O Service.OutboundIntegration.TH KnownHash + the JSON/deriving boilerplate the data type + the companion functions the module's error messages name — read Service/OutboundIntegration/TH.hs before use

Read the full file on GitHub · 125 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 · 125 lines · 118 tokens per session scan A 278c2cbf6bb1

Subscribe to this mod's changes

neohaskell-concept-derivation is a skill published in the GitHub repository neohaskell/NeoHaskell (347 stars, last pushed 3d ago), licensed Apache-2.0. It adds 118 tokens to every session and 1,874 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

resolve-conflicts

Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling…

tailcallhq/forgecode · 68 tokens

github-pr-description

Generate and create pull request descriptions automatically using GitHub CLI. Use when the user asks to create a PR, generate a PR description, make a pull request, or submit changes for review. Analyzes git diff and commit history to create comprehensive, meaningful PR descriptions that explain what changed, why it…

tailcallhq/forgecode · 72 tokens

execute-plan

Execute structured task plans with status tracking. Use when the user provides a plan file path in the format plans/{current-date}-{task-name}-{version}.md or explicitly asks you to execute a plan file.

tailcallhq/forgecode · 46 tokens

vibe-research

Research an app idea or resolve product and technical uncertainties before committing to a design.

KhazP/vibe-coding-prompt-template · 21 tokens

a-philosophy-of-software-design

Apply John Ousterhout-inspired software design rules when reducing complexity, designing module boundaries, or reviewing APIs and abstractions.

ciembor/agent-rules-books · 33 tokens

domain-driven-design

Apply Eric Evans-inspired DDD rules when modeling a complex domain, defining bounded contexts, protecting ubiquitous language, or designing aggregates.

ciembor/agent-rules-books · 29 tokens