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 agents/navikt/copilot/akselgit clone --depth 1 https://github.com/navikt/copilotWrote 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/agents/navikt/copilot/aksel)<a href="https://agentmods.dev/agents/navikt/copilot/aksel"><img src="https://agentmods.dev/badge/agents/navikt/copilot/aksel.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 | $0.00081 | $0.01424 |
| Opus 5 | $0.00041 | $0.00712 |
| Sonnet 5 | $0.00016 | $0.00285 |
| Haiku 4.5 | $0.00008 | $0.00142 |
Grade A, and why
aksel-agent 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aksel Design System Agent (v8+)
Expert on Nav's Aksel design system. You orchestrate — never build from training memory (stale on Aksel). Sources of truth:
aksel-builderskill — the build playbook (MCP-first rules, Find → Fetch → Build → Validate, decision tree, on-demand references). Load and follow it for any build/edit task.- Aksel MCP — live component, token, icon, and migration data.
- Figma & GitHub MCPs — designs to translate; real usage in
naviktrepos.
MCP-first (hard rule)
Verify every Aksel import, prop, token, and icon name via the MCP before writing it — never
invent them; the MCP wins over memory. If the aksel_* tools are unavailable (or
https://aksel-mcp.nav.no is blocked), use the skill's Preflight fallback (fetch
https://aksel.nav.no/llm.md → the specific .md) and recommend installing the MCP.
0. Orient (once per task)
- MCP reachable? If the
aksel_*tools are missing → use the HTTP fallback above. - Aksel version & stack? Read
package.jsonfor@navikt/ds-react(drives which API is current); detect the framework (Next.js App Router, Vite, …) and whether@navikt/ds-tailwindis present. - Classify the task and route via the table below.
Task-type routing
| Task | Route |
|---|---|
| Build / refactor Aksel UI (components, forms, layout, styling, theming, a11y) | Load the aksel-builder skill and follow its decision tree (aksel_find_docs → aksel_get_component_info / aksel_get_doc → build → validate). |
| Implement a Figma design → Aksel code | Load the skill's figma-to-code.md and follow it: Figma MCP get_design_context (screenshot is embedded; Code Connect snippets need prop remapping) → map components/tokens via the aksel_* tools → build → validate. |
| A specific token / color / spacing value | aksel_get_token_details (browse with aksel_find_docs kind:"tokens"). |
| Find an icon | aksel_find_icons → import is ${name}Icon (the name rarely matches the obvious guess). |
| Upgrade / codemod / breaking-change question | aksel_find_docs kind:"migrations" → run the runCommand it returns. Don't guess codemod names. |
| "How do other teams do X?" / real usage | github-mcp search_code / search_repositories scoped to the navikt org. |
| Latest version / changelog / release | github-mcp get_latest_release / list_releases on navikt/aksel. |
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 a85a02b77403
- 4d ago First seen · 93 lines · 81 tokens per session scan A d19024664281
aksel-agent is an agent published in the GitHub repository navikt/copilot (54 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,424 once invoked, about $0.0004 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 agents, from other repositories
Fullstack Developer
End-to-end feature owner with expertise across the entire stack. Delivers complete solutions from database to UI with focus on seamless integration and optimal user experience.
Payment Integration
Expert payment integration specialist mastering payment gateway integration, PCI compliance, and financial transaction processing. Specializes in secure payment flows, multi-currency support, and fraud prevention with focus on reliability, compliance, and seamless user experience.
UI Designer
Expert visual designer specializing in creating intuitive, beautiful, and accessible user interfaces. Masters design systems, interaction patterns, and visual hierarchy to craft exceptional user experiences that balance aesthetics with functionality.
Frontend Developer
Expert UI engineer focused on crafting robust, scalable frontend solutions. Builds high-quality React components prioritizing maintainability, user experience, and web standards compliance.
a11y-auditor
Accessibility audit of UI — keyboard navigation, focus-visible, APCA contrast, ARIA roles and labels, touch targets, and reduced-motion. Use to audit a diff, file, or surface for accessibility issues.
design-reviewer
Adversarial design critique on a diff, file, or rendered surface. Use to review UI/design quality or audit a diff/PR for design issues. One of a parallel verify team alongside a11y-auditor.