dxkit-flow

dxkit-flow is a skill for Claude Code from vyuh-labs/dxkit. It costs 112 tokens per session (3,922 once invoked), scanned A, original, MIT.

A setup and repair tool for checking whether frontend requests connect to backend routes. It detects when a user interface calls an API endpoint that the server does not provide, or when a still-used route has been removed.

In plain words
What is it for?
Use it to configure or diagnose flow checks, fix newly broken UI-to-API connections, and publish a cross-repository route map.
Why use it?
It catches broken links between the part of an application users see and the server code behind it before the change is accepted.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is { "name": "backend", "path": "../backend" } // local sibling.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 dxkit-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-flow.svg)](https://agentmods.dev/skills/vyuh-labs/dxkit/dxkit-flow)
Your own site
<a href="https://agentmods.dev/skills/vyuh-labs/dxkit/dxkit-flow"><img src="https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,922 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00112 $0.03922
Opus 5 $0.00056 $0.01961
Sonnet 5 $0.00022 $0.00784
Haiku 4.5 $0.00011 $0.00392

Measured 6d ago against content hash 8a2e448ccb36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dxkit-flow 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 6d 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.

src-templates/.claude/skills/dxkit-flow/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dxkit-flow

This skill owns the UI→API integration gate: dxkit statically reconstructs which client calls (METHOD url) bind to which server routes, and fails a PR that net-new breaks one — a frontend call to an endpoint no backend serves, or a removed route a consumer still calls.

It is thin orchestration over the deterministic CLI. It never re-implements extraction: it runs init / doctor / guardrail check / flow publish, reads their structured output, and supplies judgment + code edits. The determinism stays in the CLI; the agent supplies the reasoning.

Language coverage. Source extraction is per language pack: TypeScript/JavaScript (fetch/axios/wrappers; Express/LoopBack/NestJS/Next.js routes), Python (requests/httpx; FastAPI/Flask/Django routes — a Django path() route is method-agnostic and matches any verb; re_path() regex routes are out of scope), Go (http.Get/Post + http.NewRequest + client wrappers; stdlib HandleFunc/Handle incl. Go 1.22 "GET /x" patterns, chi/echo/gin/fiber verb methods on conventional receiver names — an unusually-named router falls back to flow.specs), Java (Spring MVC/WebFlux annotations with class-level @RequestMapping prefixes, JAX-RS @GET+@Path pairs; RestTemplate verbs, WebClient/java.net.http/OkHttp builder chains, Retrofit interfaces — exchange(...)'s enum verb is counted as a dynamic call, not extracted), Kotlin (the Ktor routing DSL incl. nested route(...) prefixes and Spring annotations; the Ktor client, Retrofit, builder chains — client.request { method = … } is deliberately not extracted), C# (ASP.NET attribute routing with the [controller] token substituted from the enclosing class, minimal APIs app.MapGet(...); HttpClient verb methods with interpolated $"…" URLs — MapGroup chains and HttpRequestMessage enum verbs are out of scope), Ruby (Rails routes.rb — explicit verbs qualify only in a routing context, so request-spec get '/x' calls never mint routes; resources/resource expand the RESTful set with only:/except:; nested resource blocks are skipped rather than mis-pathed; Sinatra verb+block; Net::HTTP/HTTParty/Faraday clients with #{…} interpolation), and Rust (actix-web/Rocket route attributes; axum .route(...) as method-agnostic ANY routes with .nest(...) argument-side prefixes — Rocket mount prefixes are opaque; reqwest clients, format! URLs count as dynamic). Any language also participates on the served side without pack coverage: point flow.specs at an OpenAPI document, or have the service publish its served.json as a workspace participant.

Read the full file on GitHub · 156 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.

  1. 6d ago First seen · 156 lines · 112 tokens per session scan A 8a2e448ccb36

Subscribe to this mod's changes

dxkit-flow is a skill published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 8d ago), licensed MIT. It adds 112 tokens to every session and 3,922 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 2026-08-31.