klarsprak

klarsprak is a skill for Claude Code, Codex from navikt/copilot. It costs 126 tokens per session (5,430 once invoked), scanned A, original, MIT.

A Norwegian-language editing guide for making Bokmål text clear, correct, and natural. It checks for unclear wording, unnecessary technical terms, English influence, and mixed language forms.

In plain words
What is it for?
Use it to revise Norwegian READMEs, user-interface text, documentation, emails, blog posts, commit messages, and pull-request descriptions.
Why use it?
It helps developers produce Norwegian text that readers can understand without decoding formal or machine-like phrasing.

Skill for Claude CodeCodex

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

Good fit Use it to revise Norwegian READMEs, user-interface text, documentation, emails, blog posts, commit messages, and pull-request descriptions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/navikt/copilot/klarsprak
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 navikt/copilot --skill klarsprak
Clone the repo
git clone --depth 1 https://github.com/navikt/copilot

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 klarsprak

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/navikt/copilot/klarsprak"><img src="https://agentmods.dev/badge/skills/navikt/copilot/klarsprak.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,430 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 $0.00126 $0.05430
Opus 5 $0.00063 $0.02715
Sonnet 5 $0.00025 $0.01086
Haiku 4.5 $0.00013 $0.00543

Measured 8d ago against content hash b6994c2929c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

klarsprak 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 8d 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/klarsprak/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Klarspråk

Redigér norsk bokmål så teksten blir klar, korrekt og menneskelig. Målgruppa er typisk utviklere, driftere og arkitekter, men prinsippene gjelder all norsk sakprosa.

Språkloven pålegger offentlige organer å bruke klart, korrekt språk tilpassa mottakerne. Følg Språkrådets klarspråk-prinsipper og ISO 24495-1.

Arbeidsflyt

  1. Les hele teksten først.
  2. Skann etter mønstrene under: AI-markører, substantivsyke, anglisismer, feiloversatte fagtermer, nynorsk/svensk-innblanding, dårlig struktur.
  3. Skriv om. Bevar meningen og faglig innhold: endre bare språk, form og struktur.
  4. Selvrevisjon: «Hva avslører at dette er KI-generert?» Fiks det som gjenstår.
  5. Tilpass til teksttypen (ADR, README, UI-tekst, blogg).

Klarspråk-prinsipper

Det viktigste først

Start med konklusjonen eller det leseren trenger å vite. Bakgrunn kommer etterpå.

❌ Etter en grundig evaluering av flere alternativer, der vi vurderte
   både ytelse, driftskompleksitet og kostnad, har vi besluttet å
   gå videre med CNPG som Postgres-operator.

✅ Vi bruker CNPG som Postgres-operator. Den gir oss automatisk
   failover, backup og oppgradering uten nedetid.

Skriv for leseren

Tenk: Hva trenger leseren å gjøre etter å ha lest dette? Kutt alt som ikke hjelper dem. Ikke definer ting målgruppa allerede vet.

Unngå substantivsyke

Bruk verb, ikke substantiv laget av verb. Typisk mønster: -ing + av.

❌ Vi foretar en gjennomgang av implementasjonen.
✅ Vi gjennomgår implementasjonen.

❌ Gjennomføring av migrering til ny plattform.
✅ Vi migrerer til ny plattform.

Kort over langt

  • Kort setning over lang. Én idé per setning — må leseren lese setningen to ganger, del den i to.
  • Vanlig ord over fint ord: «bruke» ikke «benytte», «hjelpe» ikke «fasilitere», «mange» ikke «tallrike», «hvis» ikke «i det tilfellet at».
  • Aktiv form over passiv: «vi bruker» ikke «det benyttes». Fang «blir/ble + partisipp» og navngi aktøren: «spørringer valideres» → «kompilatoren validerer spørringer». Passiv er greit bare når aktøren er ukjent eller uvesentlig.
  • Konkret over abstrakt: «vi bygger nytt image» ikke «det kreves en tilpasning av image-artefaktet».
  • Kutt fyllord: «i bunn og grunn», «i stor grad», «på mange måter», «det er viktig å merke seg at».
  • Kutt adverb, eller bruk et sterkere verb: «kjører raskt» → «er rask» eller tallet. «forbedrer betydelig» → den målte forskjellen.
  • Si hva ting gjør, ikke hvordan det føles. «SQL du kan lese» og «databasen er alltid nær» navngir en følelse. Skriv heller mekanismen eller tallet: «.toSQL() returnerer strengen som sendes til databasen». Kan setningen stå uendret i dokumentasjonen til et helt annet prosjekt, sier den ingenting om dette — kutt den.

Read the full file on GitHub · 373 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 373 lines · 126 tokens per session scan A b6994c2929c8

Subscribe to this mod's changes

klarsprak is a skill published in the GitHub repository navikt/copilot (54 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 5,430 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 2026-09-03.

Related

Other skills, from other repositories

skill-guide

Design, write, and review SKILL.md files using proven patterns. Use when creating, improving, or reviewing agent skills, choosing a design pattern (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline), structuring progressive disclosure, writing skill descriptions, or composing patterns. Also trigger for 'skill…

AndyElessar/skills · 102 tokens

microsoft-webui

Microsoft WebUI Framework expertise — a language-agnostic server-side rendering framework where templates compile to a binary protocol and interactive Web Components hydrate as islands. Use when authoring, reviewing, or debugging WebUI components (.html + .css + .ts triplets), wiring up routes, hydrating with…

AndyElessar/skills · 212 tokens

plugin-creator

Guide AI agents through creating GitHub Copilot CLI and Claude Code plugins and plugin marketplaces — from scaffolding plugin directories and writing plugin.json manifests to building marketplace.json registries and testing installations. Use this skill whenever the user wants to create, scaffold, configure, package…

AndyElessar/skills · 181 tokens

prose-guide

Guide AI-native development using the PROSE methodology — Progressive Disclosure, Reduced Scope, Orchestrated Composition, Safety Boundaries, Explicit Hierarchy. Use when: setting up AI-native projects, creating agent primitives (.instructions.md, .prompt.md, .agent.md, SKILL.md, .spec.md, AGENTS.md), designing…

AndyElessar/skills · 162 tokens

csharp-source-generator

Use when writing, reviewing, debugging, or testing C# source generators and Roslyn incremental generators. Covers IIncrementalGenerator architecture, SyntaxProvider pipelines, generated-code snapshots with Verify, analyzer packaging, marker attributes, AnalyzerConfigOptionsProvider, SDK compatibility, diagnostics, and…

AndyElessar/skills · 152 tokens

aspire-dev

Orchestrates Aspire distributed applications using the Aspire CLI and MCP tools. USE FOR: aspire start/stop, aspire describe, aspire doctor, view logs/traces, add integrations, debug resources, AppHost management. Also trigger for DistributedApplication.CreateBuilder, AddProject, AddContainer, or Aspire resource…

AndyElessar/skills · 146 tokens