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.
npx agentmods add skills/neohaskell/neohaskell/neohaskell-implementernpx skills add neohaskell/NeoHaskell --skill neohaskell-implementergit clone --depth 1 https://github.com/neohaskell/NeoHaskellWrote 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.
[](https://agentmods.dev/skills/neohaskell/neohaskell/neohaskell-implementer)<a href="https://agentmods.dev/skills/neohaskell/neohaskell/neohaskell-implementer"><img src="https://agentmods.dev/badge/skills/neohaskell/neohaskell/neohaskell-implementer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.01751 |
| Opus 5 | $0.00024 | $0.00875 |
| Sonnet 5 | $0.00010 | $0.00350 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
neohaskell-implementer 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NeoHaskell implementer
Rebuilt 2026-07-07 (Phase 2 of the pipeline plan). The dialect rules below are mechanically gated (hook → hlint → GHC); the working discipline (copy-adapt, repair protocol, circuit breaker) is protocol — followed because it works, verified at review.
The one structural rule: copy-adapt, never blank-buffer
No .hs file is ever created from scratch. A model editing 200 lines of
real NeoHaskell produces NeoHaskell; a model facing an empty buffer produces
Stack Overflow Haskell. Before writing:
- Copy-adapt from the plan-resolved nearest-neighbor module — the one the
localizer pinned at plan time (pipeline step 6 records "which neighbor
module each copy-adapts from"). Which module to copy is a "where things
live" question, so implementation never searches the tree for one (AGENTS.md
HARD RULE). Plan didn't pin one? The neighbor is a planning output, never an
implementation-time lookup: stop, park the run (
wrong-localization), and return to planning so the localizer pins it and records it at step 6. Resume never re-plans (AGENTS.md), so discovering or looking up a missing neighbor here is never allowed — fix the localization asset and re-enter. The neighbor shares the target's architectural shape (command, entity, query, transport feature, integration, Core primitive, spec). - Copy its skeleton — imports block, module header, structure.
- Adapt. Your imports section should look like the neighbor's, not like your training data.
Creating or editing a concept (query, command, event, outbound integration)?
These are declared through a Template Haskell marker — load the
neohaskell-concept-derivation skill and follow it: use the marker
(deriveQuery / command / event / outboundIntegration) and author only
the required companion functions and business-logic instances; never hand-write
the Show/Generic/JSON/ToSchema/NameOf/EntitiesOf/Query/KnownHash
instances the marker emits. Do not copy the boilerplate of a pre-marker module.
(Entities are the exception — no marker; hand-write their Entity instance.)
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.
- today Changed 77683391aedb
- 2d ago Changed · +21 lines 0e5fbb361126
- 6d ago First seen · 119 lines · 48 tokens per session scan A e686ceb624e2
neohaskell-implementer is a skill published in the GitHub repository neohaskell/NeoHaskell (347 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 1,751 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 2026-08-30.
Other skills, from other repositories
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…
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.
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
vibe-build
Build your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or says "build my MVP", "start coding", or "implement the project".
tokf-filter
This skill should be used when the user asks to "create a filter", "write a tokf filter", "add a filter for ", "how do I filter output", or needs guidance on tokf filter step types, templates, pipes, or placement conventions.
Concurrency Testing Patterns
Testing concurrent code including race condition detection, deadlock prevention, thread safety verification, and parallel execution correctness.