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 vyuh-labs/dxkit --skill dxkit-describegit 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-describe)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00128 | $0.00915 |
| Opus 5.5 | $0.00051 | $0.00366 |
| Sonnet 5.5 | $0.00026 | $0.00183 |
| Haiku 4.5 | $0.00013 | $0.00092 |
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 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 — 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.jsondeclares local-path participants, the map spans them (offline — it never fetches).
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 · 68 lines · 128 tokens per session scan A 588f94b8c676
dxkit-describe is a skill published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 915 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
Code Coverage Analysis
Measure and enforce test coverage with Istanbul/nyc, c8, Jest, and Vitest. Covers branch versus line coverage, per-directory thresholds, CI gates, and correctly excluding generated code from reports.
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-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).
duo-build
Build an issue or feature interactively toward an indexed shared goal, with automatic read-only peer review; resume the same run across Claude Code and Codex.
specflow
Spec-driven development with executable contracts.
specflow-loop-selector
Choose the lightest Specflow workflow that covers an ask’s size, uncertainty and risk, then select a loop only when needed. Use for work triage, proportionate verification, loop selection, or explicit spec-build, feature-build and Gate D requests. A lightweight decision does not start a loop.