A set of instructions and tools for connecting coding agents to Danish services and other systems through existing APIs, browser automation, or local connectors.

It helps discover APIs, turn API descriptions or browser network recordings into agent connectors, automate browsers, and crawl information locally.

It provides a decision process for finding an available integration before building one from scratch, while avoiding unnecessary hosted services.

agentaccess — Skill for Claude Code and Codex by klh

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 klh/speedy-claude --skill agentaccess

Clone the repo

git clone --depth 1 https://github.com/klh/speedy-claude

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/klh/speedy-claude/agentaccess/github.svg)](https://agentmods.dev/skills/klh/speedy-claude/agentaccess)

Your own site

<a href="https://agentmods.dev/skills/klh/speedy-claude/agentaccess"><img src="https://agentmods.dev/badge/skills/klh/speedy-claude/agentaccess/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/klh/speedy-claude/agentaccess"><img src="https://agentmods.dev/badge/skills/klh/speedy-claude/agentaccess.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,291 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00080	$0.01291
Opus 5	$0.00040	$0.00646
Sonnet 5	$0.00016	$0.00258
Haiku 4.5	$0.00008	$0.00129

Measured yesterday against content hash 486c4d01b58d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agentaccess 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 yesterday.

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/agentaccess/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentAccess — dansk tjeneste-adgang & lokal MCP-byggestak

Hovedregel 1: DANSK tjeneste → tjek https://agentaccess.dk (directory + /enablers) FØR der bygges noget selv. Sitet er agent-nativt: ethvert sidenavn som .md, llms.txt-sitemap, /mcp JSON-RPC, /api/openapi.json, SPARQL/RDF.

Hovedregel 2 (hård): Open-source og lokalt frem for alt andet. Ingen abonnementer, ingen betalte API'er, ingen "free credits then pay", ingen cloud-afhængigheder i stakken. Model-adgang er den ENESTE betalte komponent.

Adgangshierarki (beslutningstræ — alle gratis/lokale)

Officiel MCP findes            → brug den (fx Dineros mcp.dinero.dk; Grundfast gf_test_-sandbox)
OpenAPI/spec findes            → OpenAPI MCP Proxy: spec → MCP (IKKE PrintingPress — freemium)
Ingen docs, men netværks-API    → Har2MCP: Chrome DevTools-HAR → generér MCP
Prædikabelt DOM / explorering  → Playwright MCP (modellen styrer browseren selv —
                                  ingen ekstra LLM-omvej som Stagehand kræver)
Viden-indhentning i stor skala → Crawl4AI self-hosted (Docker-API, forbruges fra TS)
Kun menneske-auth (MitID!)     → browser i brugerens session + HITL-gate — ALDRIG credentials

Den lokale nul-cost stak (CC + GLM + TS, model-uafhængig)

                    Claude Code → GLM-5.3[1m]
        skills (SKILL.md) · subagents (.claude/agents) · MCP
                              │
     Playwright MCP (browser) · Crawl4AI (web→MD) · egne MCP'er (FastMCP TS + Zod)
                              │
                        Har2MCP (HAR→MCP)

De seks der installeres (alt OSS, alt lokalt):

FastMCP TS — @prefecthq/fastmcp-ts (Apache-2.0): FastAPI-agtig MCP-udvikling. Forveksl IKKE med forældet fastmcp-npm-pakke. Lav-niveau-kontrol → @modelcontextprotocol/server v2 (serveStdio/registerTool, Zod via Standard Schema)
MCP Inspector — npx @modelcontextprotocol/inspector (MIT): interaktiv test/debug af alle MCP'er; altid i dev-loopet
Playwright MCP — browser-adgang; modellen navigerer/klikker/ekstraherer selv
Crawl4AI — self-hosted web→ren Markdown (bedste gratis Firecrawl-alternativ; Python-kerne, kør Docker-API'en og forbrug fra TS)
Har2MCP — HAR-captures → MCP-værktøjer til reverse-engineerede portaler
BAML — typede LLM-funktioner (Apache-2.0) — når selvstændige TS-agenter skrives

Read the full file on GitHub · 62 lines

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.

yesterday First seen · 62 lines · 80 tokens per session scan A 486c4d01b58d

Subscribe to this mod's changes

agentaccess is a skill published in the GitHub repository klh/speedy-claude (11 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 1,291 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 2026-09-11.

Browser automation Building agents

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens