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 skills add navikt/copilot --skill nav-deep-interviewgit 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/skills/navikt/copilot/nav-deep-interview)<a href="https://agentmods.dev/skills/navikt/copilot/nav-deep-interview"><img src="https://agentmods.dev/badge/skills/navikt/copilot/nav-deep-interview/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.
<a href="https://agentmods.dev/skills/navikt/copilot/nav-deep-interview"><img src="https://agentmods.dev/badge/skills/navikt/copilot/nav-deep-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.02675 |
| Opus 5 | $0.00018 | $0.01337 |
| Sonnet 5 | $0.00007 | $0.00535 |
| Haiku 4.5 | $0.00004 | $0.00267 |
Grade A, and why
nav-deep-interview 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.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Interview — Nav Project Clarification
Kjør et strukturert intervju for å avdekke blindsoner før implementering starter. Basert på vanlige feil og oversikter i Nav-prosjekter.
Workflow
- Identifiser arketype — hva slags ting bygges?
- Still domene-spesifikke spørsmål — basert på arketypen
- Oppsummer funn — krav, risiko, ikke-mål
- Generer output — strukturert kravdokument
Steg 1: Arketype
Still dette spørsmålet først:
Hva slags ting bygger du?
- Backend API (Kotlin/Ktor eller Spring Boot)
- Hendelsekonsument (Kafka / Rapids & Rivers)
- Frontend for innbygger (Next.js + ID-porten)
- Frontend for saksbehandler (Next.js + Azure AD)
- Batchjobb (Naisjob)
- Fullstack (frontend + BFF + backend)
Steg 2: Domene-spesifikke spørsmål
Still spørsmål fra alle fire domener. Tilpass rekkefølge basert på arketype.
Personvern og data
Disse spørsmålene glemmes oftest. Still dem først.
| # | Spørsmål | Hvorfor |
|---|---|---|
| D1 | Behandler tjenesten personopplysninger? Hvilke kategorier? | Bestemmer dataklassifisering og lagringsregler |
| D2 | Hvem har tilgang til dataene — innbygger, saksbehandler, system? | Bestemmer auth og tilgangskontroll |
| D3 | Hva er formålet med behandlingen? (Hjemmel) | Nødvendig for GDPR-vurdering |
| D4 | Hvor lenge skal data lagres? Finnes det sletteregler? | Påvirker database-design og retensjon |
| D5 | Skal data deles med andre tjenester? Hvilke? | Påvirker API-design og accessPolicy |
| D6 | Trenger dere audit-logging av hvem som har sett/endret data? | Påkrevd for sensitive personopplysninger |
Se data-classification.md for Navs dataklassifiseringsnivåer.
Plattform og autentisering
| # | Spørsmål | Hvorfor |
|---|---|---|
| P1 | Hvem initierer forespørsler — bruker, annen tjeneste, batch, ekstern? | Bestemmer auth-mekanisme |
| P2 | Hvilke andre tjenester kaller dere? Hvilke cluster? | Bestemmer outbound accessPolicy og token exchange |
| P3 | Er tjenesten eksponert eksternt (internett) eller bare internt? | Bestemmer ingress og nettverkspolicy |
| P4 | Hva skjer når en avhengighet er nede? | Påvirker retry-strategi og circuit breaker |
| P5 | Trenger dere asynkron kommunikasjon (hendelser)? | Kafka-oppsett eller ikke |
| P6 | Finnes det eksisterende tjenester dere kan gjenbruke? | Unngå duplikering |
What ships with it
3 files 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.
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.
- 11d ago First seen · 218 lines · 36 tokens per session scan A 836d08731671
nav-deep-interview is a skill published in the GitHub repository navikt/copilot (54 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 2,675 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
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…
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…
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…
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…
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…
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…