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-learnnpx skills add vyuh-labs/dxkit --skill dxkit-learngit 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-learn)<a href="https://agentmods.dev/skills/vyuh-labs/dxkit/dxkit-learn"><img src="https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-learn.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 | $0.00076 | $0.02339 |
| Opus 5 | $0.00038 | $0.01170 |
| Sonnet 5 | $0.00015 | $0.00468 |
| Haiku 4.5 | $0.00008 | $0.00234 |
Grade A, and why
dxkit-learn 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 5d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dxkit-learn
This skill explains how dxkit works. Reach for it when the user asks about dxkit concepts before they take an action.
Mental model
dxkit measures a codebase along 6 dimensions (Security, Code Quality, Tests, Documentation, Maintainability, Developer Experience) using deterministic scanners (gitleaks, semgrep, cloc, jscpd, graphify, ruff, eslint, …). Findings are anchored to a baseline (.dxkit/baselines/main.json) so today's pre-existing issues don't block tomorrow's PR. A guardrail check diffs current state against the baseline and blocks net-new regressions; two additive contract gates ride the same check when configured — flow (net-new broken UI→API integrations) and schema drift (breaking data-model changes, opt-in). Hooks + CI wire the guardrail into the developer's workflow.
The three contracts to remember:
- Baseline = the brownfield anchor. Pre-existing findings are recorded once; future scans only block on additions.
- Hooks fire fast (pre-push); CI fires thorough. Both use the same guardrail logic.
- Reports are deterministic — same code + same baseline = same findings. The salt mode (
deterministicvsrandom) controls per-finding identity stability across runs.
Discovering the full capability set (don't rely on this list staying complete)
dxkit's capabilities grow. Rather than trust a hand-written list, read the live capability registry — the single source of truth for what dxkit can do:
npx vyuh-dxkit capabilities --json
This returns every capability with its group, one-line summary, the dxkit-*
skill that drives it, and — grounded in this repo — which ones are
recommended (capabilities the repo would benefit from but isn't using yet).
It never drifts: a new capability appears here the moment it ships.
Pair it with the repo-grounded advice from doctor:
npx vyuh-dxkit doctor --json # .recommendations[] = what to adopt here, with the command to run
When a user asks "what can dxkit do for me?" or "what should I set up here?",
read those two, then propose the fitting capabilities and drive each through
its skill (the skill field tells you which). This is how a user configures
dxkit by talking to you — the menu is machine-readable so you never guess.
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.
- 5d ago First seen · 137 lines · 76 tokens per session scan A a59cc40df921
dxkit-learn is a skill published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 7d ago), licensed MIT. It adds 76 tokens to every session and 2,339 once invoked, about $0.0004 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
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).
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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
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…