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-loopgit 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-loop)<a href="https://agentmods.dev/skills/vyuh-labs/dxkit/dxkit-loop"><img src="https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-loop/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-loop"><img src="https://agentmods.dev/badge/skills/vyuh-labs/dxkit/dxkit-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 11 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 27 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 36 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 39 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 45 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 48 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 65 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 87 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 88 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 89 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 102 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 103 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 | $0.00116 | $0.01741 |
| Opus 5.5 | $0.00046 | $0.00696 |
| Sonnet 5.5 | $0.00023 | $0.00348 |
| Haiku 4.5 | $0.00012 | $0.00174 |
Grade A, and why
dxkit-loop 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dxkit-loop
This skill owns the loop pack: the deterministic preflight/postflight layer that keeps an autonomous coding loop from declaring "done" while it has introduced net-new findings. Reach for it to set the gate up, to explain a block, or to tune the posture.
What the loop pack is
When Claude Code runs in a loop (it keeps working until it decides to stop), a Stop hook runs vyuh-dxkit hook stop-gate every time the agent tries to stop. The gate re-runs the guardrail check against the baseline and:
- net-new findings → blocks the stop and feeds the exact findings back to the model so it repairs them, then tries to stop again;
- clean → allows the stop (optionally after a configured test command passes);
- gate can't run (no baseline / config error) → blocks once for the operator (a problem the model can't fix), then allows on the next attempt to avoid thrashing.
Every Stop event is appended to an audit trail at .dxkit/loop/ledger.jsonl.
The value is predictability, not a new scanner: the gate bounds the "loop shipped debt and never fixed it" failure mode to zero. It uses the same findings, baseline, and identity contract as the rest of dxkit — it does not detect anything new.
See it first (no setup)
# No API key, no Claude Code, no scanners — runs the real gate over an example
# finding and shows the block → repair → clean flow offline.
npx vyuh-dxkit demo loop-guardrail
Setup
# Register the Stop hook + CLAUDE.md loop norm + default preset.
# Additive: merges into existing .claude/settings.json + CLAUDE.md,
# never clobbering your hooks or prose.
npx vyuh-dxkit init --claude-loop
# Pick the posture up front (default is security-only):
npx vyuh-dxkit init --claude-loop --loop-preset full-debt
A loop is only safe if a baseline exists, the hook is registered, and the guardrail can run. Always verify before an unattended run:
npx vyuh-dxkit loop doctor
It checks: git repo, baseline present/resolvable, Stop hook registered, active preset, optional postflight test command, graph freshness. Exit non-zero = not safe to run unattended yet — each failing check carries a fix command. The most important one it catches is the silent failure: an unregistered hook never fires, so the loop would run with no gate and no error. If loop doctor says the baseline is missing, capture one first (npx vyuh-dxkit baseline create).
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 · 115 lines · 116 tokens per session scan A a554a4805a02
dxkit-loop is a skill published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,741 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.