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 agentmods add skills/vyuh-labs/dxkit/dxkit-extensionsnpx skills add vyuh-labs/dxkit --skill dxkit-extensionsgit clone --depth 1 https://github.com/vyuh-labs/dxkitWrote 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/vyuh-labs/dxkit/dxkit-extensions)<a href="https://agentmods.dev/skills/vyuh-labs/dxkit/dxkit-extensions"><img src="https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-extensions.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00133 | $0.01080 |
| Opus 5 | $0.00067 | $0.00540 |
| Sonnet 5 | $0.00027 | $0.00216 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
dxkit-extensions 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dxkit-extensions
An extension is a script the repo already owns — any language — that dxkit orchestrates: it runs at refresh time, emits one JSON document, and dxkit validates it and routes it through the same machines native output gets.
Before writing one, climb the ladder from the bottom — most needs stop early:
-
Config — a
.dxkit/policy.jsonkey. No code. -
Declared artifact — you already have a Postman collection, Pact file,
.httprequests, HAR capture, or OpenAPI document? Declare it:// .dxkit/policy.json { "flow": { "sources": [ { "kind": "postman", "path": "collections/checkout.postman_collection.json" }, { "kind": "pact", "path": "pacts/web-api.json" }, { "kind": "har", "path": "fixtures/session.har" }, ], }, }Zero code; the artifacts join the flow map and gate like extracted calls.
-
External extension (this skill's core) — a committed manifest points at your existing script.
-
TypeScript plugin — only for what the rungs above can't express: a bespoke HTTP-client wrapper flow can't see (
httpFlowDialect), a custom artifact format forflow.sources(contractReader), base-URL logic beyondstripUrlPrefixes(urlNormalizer), or an assertion over the gathered flow model (integrationVerifier). Scaffold withvyuh-dxkit extensions init <name> --plugin; the dxkit-author-extension skill writes one from a prose description. You probably don't need it.
What an extension can contribute
contributes |
The document it emits | Where it lands |
|---|---|---|
contract |
contract.v1 — consumed calls / served routes |
the flow map + integration gate |
inventory |
inventory.v1 — named entities (screens, permissions, …) |
committed store + entity-count trend on report history |
findings |
findings.v1 — located findings |
the guardrail: net-new blocks/warns per the manifest's gating, pre-existing debt grandfathered |
export |
export.v1 receipt (it RECEIVES the report to deliver) |
your dashboard / spreadsheet / notifier, unchanged |
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.
- 6d ago First seen · 90 lines · 133 tokens per session scan A cc99fce8b379
dxkit-extensions is a skill published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 8d ago), licensed MIT. It adds 133 tokens to every session and 1,080 once invoked, about $0.0007 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.
Other skills, from other repositories
csharp-nullable-reference-types
Guidelines for introducing and using nullable reference types (NRT) and System.Diagnostics.CodeAnalysis nullable attributes in C# / .NET codebases. Covers the nullability model, flow analysis, the null-forgiving operator, API design rules, the full attribute catalog (AllowNull, DisallowNull, MaybeNull, NotNull…
typescript-rules
React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.
ESLint for Test Quality
Enforce test quality with ESLint - eslint-plugin-jest, eslint-plugin-playwright, and eslint-plugin-testing-library rules in flat config, blocking focused tests, missing assertions, and flaky waits via a CI lint gate.
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.
ring:adopting-lib-commons-huma-wrapper
Adopting the lib-commons/v5 shared Huma (OAS 3.1) OpenAPI wrapper + RFC 9457 problem model (commons/net/http/{openapi,problem}) in a Lerian Go service: wire openapi.New/ServeSpec + problem.Install (central >=500 scrub) on BOTH runtime and spec-gen paths, the per-rail problem.MapError flex seam, and rename-only spec…
ring:applying-licenses
Applying or switching a repository's license (Apache 2.0, Elastic License v2, or Proprietary): rewrites the LICENSE file, updates Go/TS source headers, sets SPDX identifiers, and validates consistency after user confirmation. Use when asked to set, apply, or switch a license, or when scaffolding a service with no…