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-checksgit 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-checks)<a href="https://agentmods.dev/skills/vyuh-labs/dxkit/dxkit-checks"><img src="https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-checks.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 20 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 21 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 22 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 23 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 121 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 129 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 63 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00139 | $0.02808 |
| Opus 5 | $0.00069 | $0.01404 |
| Sonnet 5 | $0.00028 | $0.00562 |
| Haiku 4.5 | $0.00014 | $0.00281 |
Grade A, and why
dxkit-checks 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 7d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dxkit-checks
A custom check is any repo command dxkit runs as a first-class gate citizen. Two sources feed one seam:
- User checks you declare in
.dxkit/policy.json:checks— a project invariant (check:no-cross-layer-imports,make lint, a license audit,scripts/arch-gate.sh). - The built-in lint gate — each active language pack's linter (eslint, ruff, golangci-lint, rubocop, clippy, ktlint, dotnet analyzers), enabled with one policy flag.
Both normalize to the same runner and inherit the same machine every native finding gets: fingerprint → baseline → git-aware matcher → brownfield classify → allowlist → guardrail verdict. So the guardrail blocks only a net-new failure and grandfathers pre-existing debt — you can turn on a lint gate against a repo with a thousand existing warnings and it will only ever block the error this change introduced.
It is opt-in, default-off. A repo that declares nothing pays nothing (the runner spawns no process).
See what's configured
npx vyuh-dxkit checks # list configured user checks + active lint gates
npx vyuh-dxkit checks --json # the same, machine-readable (agent-queryable)
npx vyuh-dxkit checks run # DRY-RUN: execute each check, show pass/fail/skip + findings
npx vyuh-dxkit checks run --json
checks run is a diagnostic — it runs the checks and shows what the gate would see right now, but it never blocks and never touches the baseline. Net-new-ness is decided by guardrail check against the committed baseline, not here.
Declare a user check
Add to .dxkit/policy.json:
{
"checks": [
{
"name": "check:no-cross-layer-imports",
"command": "node scripts/check-layers.js",
"blocking": true // default true; false = warn-only
},
{
"name": "license-audit",
"command": ["scripts/license-audit.sh", "--strict"],
"blocking": false
}
]
}
commandis a string (split on whitespace) or an argv array. It resolves the binary onPATH; a missing binary is a fail-open skip, never a block (a developer who hasn't installed a tool locally isn't blocked — CI is the backstop).nameis the durable identity key — keep it stable, or the baseline treats a rename as "old check resolved, new check appeared".expectedExit(default0) sets which exit code means "pass".
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.
- 7d ago First seen · 156 lines · 139 tokens per session scan A 662ffb76b728
dxkit-checks is a skill published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 10d ago), licensed MIT. It adds 139 tokens to every session and 2,808 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
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).
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-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.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
dorodango
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…