dxkit-describe

dxkit-describe is a skill for Claude Code from vyuh-labs/dxkit. It costs 128 tokens per session (915 once invoked), scanned A, original, MIT.

A read-only tool that creates a clear summary of a code repository, including its technology stack, web routes, network calls, connections between them, and data models. It labels each fact as directly seen, derived, inferred, or unknown.

In plain words
What is it for?
Use it to document an unfamiliar repository, inspect how its web requests connect, review its data structures, or create a shareable contract map.
Why use it?
It shows what the tool can actually establish from the code instead of presenting guesses as facts. It also creates a self-contained HTML map that can be shared or saved explicitly.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to document an unfamiliar repository, inspect how its web requests connect, review its data structures, or create a shareable contract map.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vyuh-labs/dxkit/dxkit-describe
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 vyuh-labs/dxkit --skill dxkit-describe
Clone the repo
git clone --depth 1 https://github.com/vyuh-labs/dxkit

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-describe

README.md
[![agentmods](https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-describe/github.svg)](https://agentmods.dev/skills/vyuh-labs/dxkit/dxkit-describe)
Your own site
<a href="https://agentmods.dev/skills/vyuh-labs/dxkit/dxkit-describe"><img src="https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-describe/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.

agentmods 80×15 button for dxkit-describe

Your own site · 80×15
<a href="https://agentmods.dev/skills/vyuh-labs/dxkit/dxkit-describe"><img src="https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-describe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 915 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00128 $0.00915
Opus 5 $0.00064 $0.00458
Sonnet 5 $0.00026 $0.00183
Haiku 4.5 $0.00013 $0.00092

Measured 9d ago against content hash 588f94b8c676, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dxkit-describe 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 9d 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-describe/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dxkit-describe

This skill turns a repo into a shareable, honest picture: what dxkit can see about the stack and its HTTP contracts, and — the part that builds trust — how much of it dxkit actually resolved versus inferred or could not see.

It is zero-write by default. Nothing lands in the repo unless the user explicitly saves the HTML map with --out.

The one command

vyuh-dxkit describe [path]            # terminal summary (zero-write)
vyuh-dxkit describe --json            # the versioned repo card (dxkit.repo-card.v1)
vyuh-dxkit describe --html            # the contract-map HTML to stdout
vyuh-dxkit describe --html --out map.html   # save the map (explicit opt-in write)

Everything is computed from the code (flow spine, seams, models) via the same canonical analyzers the gate uses — no new heuristics, no second confidence scale.

What it produces

  • A repo card: stack, routes, calls, bindings, and models, each count broken down by epistemic label:
    • observed — dxkit parsed the source itself,
    • derived — from a declared contract (a spec) dxkit trusts but didn't see,
    • inferred — a heuristic binding that carries a confidence and may be wrong,
    • unknown — the fact exists but can't be resolved (a runtime URL, a missing scanner).
  • The seams, which a linter cannot see:
    • unresolved calls — client calls that reach no served route (integration gaps),
    • unconsumed routes — served routes nothing calls (dead-surface candidates).
  • A holistic contract-map HTML: a self-contained, offline, light/dark page that joins dxkit's OWN call graph (deeper than graphify — it keeps the framework/stdlib calls graphify drops) to the HTTP contract layer, ACROSS repos. Swimlanes per repo, left→right callers → routes → handlers; seams (broken call / dead route) glow; cross-repo edges are distinct; each handler expands on click to its internal + framework calls (the depth graphify can't see). The honesty rides on the picture. When a .dxkit/workspace.json declares local-path participants, the map spans them (offline — it never fetches).

Read the full file on GitHub · 68 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. 9d ago First seen · 68 lines · 128 tokens per session scan A 588f94b8c676

Subscribe to this mod's changes

dxkit-describe is a skill published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 11d ago), licensed MIT. It adds 128 tokens to every session and 915 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.

Related

Other skills, from other repositories

habit-hooks-review

Spawn a reviewer sub-agent to assess a change set against habit-hooks's coding principles. Use AFTER habit-hooks reports clean — habit-hooks catches structural smells; this catches what it cannot (correctness, tests, design, missed edge cases).

habit-hooks/habit-hooks · 51 tokens

release-habit-hooks

Cut a new release of the habit-hooks packages. Use when asked to release, publish, or bump the version. Reviews what lands, enforces the in-sync versioning rule, validates the changelog, and drives the tag-triggered PyPI publish.

habit-hooks/habit-hooks · 56 tokens

habit-hooks-prompting

Write or revise a habit-hooks coaching prompt. Use when a linter / knip / jscpd rule fires and the agent's default fix is wrong or shallow, or when adding a project-local override prompt. Keeps prompts short and outcome-focused using the ROSE pattern.

habit-hooks/habit-hooks · 61 tokens

explore-codebase

MUST BE USED PROACTIVELY. Universal read-only codebase exploration. Combines jrag graph navigation (call chains, routes, service boundaries, impact analysis, FQN resolution) with broad file-system search (grep, glob, file reading). Use for any exploration: locating code, tracing dependencies, finding patterns, 'where…

HumanBean17/jrag · 117 tokens

explore-codebase-cli

MUST BE USED PROACTIVELY. Universal JVM (Java + Kotlin) codebase exploration (CLI surface): graph navigation (jrag callers/callees/routes/impact/flow/…) plus jrag search (locate code/config by meaning or keywords) and file-system search. Use for any exploration task: locating code, tracing dependencies, finding…

HumanBean17/jrag · 129 tokens

investigate

Manage structured investigations with multi-agent evidence collection, synthesis, tagging, and PHI sanitization. Use when user says "start an investigation", "root cause analysis", or "collect evidence about X". Subcommands: new, run, collect, synthesize, close, status, list, search. Do NOT use for casual debugging or…

john-wilmes/claude-agentic-coding-playbook · 82 tokens