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 api-designgit 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/api-design)<a href="https://agentmods.dev/skills/navikt/copilot/api-design"><img src="https://agentmods.dev/badge/skills/navikt/copilot/api-design/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/api-design"><img src="https://agentmods.dev/badge/skills/navikt/copilot/api-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 24 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00035 | $0.01575 |
| Opus 5.5 | $0.00014 | $0.00630 |
| Sonnet 5.5 | $0.00007 | $0.00315 |
| Haiku 4.5 | $0.00003 | $0.00158 |
Grade A, and why
api-design 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 1mo 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Design Skill
REST API design for Nav services. Covers naming conventions, error handling with ProblemDetail, versioning, pagination, and OpenAPI spec.
URL Conventions
# ✅ Correct
GET /api/vedtak # List
GET /api/vedtak/{id} # Get by ID
POST /api/vedtak # Create
PUT /api/vedtak/{id} # Full update
PATCH /api/vedtak/{id} # Partial update
DELETE /api/vedtak/{id} # Delete
# ✅ Sub-resources
GET /api/vedtak/{id}/aktiviteter # List child resources
POST /api/vedtak/{id}/aktiviteter # Create child resource
# ✅ Actions (verb as sub-resource)
POST /api/vedtak/{id}/godkjenn # State transition
# ❌ Wrong
GET /api/getVedtak # Verb in URL
GET /api/vedtak/hentAlle # Verb in URL
POST /api/createVedtak # Verb in URL
GET /api/Vedtak # PascalCase
Error Handling (RFC 7807 / ProblemDetail)
// Spring Boot 3+ — built-in ProblemDetail support
@RestControllerAdvice
class ErrorHandler {
@ExceptionHandler(ResourceNotFoundException::class)
fun handleNotFound(ex: ResourceNotFoundException): ProblemDetail =
ProblemDetail.forStatusAndDetail(HttpStatus.NOT_FOUND, ex.message ?: "Resource not found").apply {
title = "Resource not found"
setProperty("resourceType", ex.resourceType)
setProperty("resourceId", ex.resourceId)
}
@ExceptionHandler(MethodArgumentNotValidException::class)
fun handleValidation(ex: MethodArgumentNotValidException): ProblemDetail =
ProblemDetail.forStatusAndDetail(HttpStatus.BAD_REQUEST, "Validation failed").apply {
title = "Invalid request"
setProperty("errors", ex.bindingResult.fieldErrors.map {
mapOf("field" to it.field, "message" to it.defaultMessage)
})
}
}
For Ktor, use the StatusPages plugin:
install(StatusPages) {
exception<ResourceNotFoundException> { call, cause ->
call.respond(HttpStatusCode.NotFound, ProblemResponse(
title = "Resource not found",
status = 404,
detail = cause.message ?: "Resource not found",
instance = call.request.uri,
))
}
exception<ValidationException> { call, cause ->
call.respond(HttpStatusCode.BadRequest, ProblemResponse(
title = "Invalid request",
status = 400,
detail = "Validation failed",
errors = cause.errors,
))
}
}
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.
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.
- 1mo ago First seen · 215 lines · 35 tokens per session scan A 696738e209f8
api-design is a skill published in the GitHub repository navikt/copilot (56 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,575 once invoked, about $0.0001 per session on Opus 5.5. 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
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
sandbox-next
Build or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.
cloudflare
Discover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security. Use for architecture and product selection, including when the user describes a need without naming a Cloudflare product; then find the relevant skill or documentation.
cloudflare-email-service
Implement or troubleshoot Cloudflare Email Sending and Email Routing integrations and their delivery configuration.
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
bf-to-agents-sdk-typescript-migration
Assess and migrate JavaScript or TypeScript bots from BotBuilder/Bot Framework SDK to Microsoft 365 Agents SDK with AgentApplication. Use to produce a migration report and plan before editing code, map BotBuilder packages and APIs, identify unsupported features, and implement only the supported plan items selected by…