Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/mschulkind-oss/yolo-jail/configuring-the-jail)<a href="https://agentmods.dev/skills/mschulkind-oss/yolo-jail/configuring-the-jail"><img src="https://agentmods.dev/badge/skills/mschulkind-oss/yolo-jail/configuring-the-jail/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/mschulkind-oss/yolo-jail/configuring-the-jail"><img src="https://agentmods.dev/badge/skills/mschulkind-oss/yolo-jail/configuring-the-jail.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00068 | $0.03020 |
| Opus 5 | $0.00034 | $0.01510 |
| Sonnet 5 | $0.00014 | $0.00604 |
| Haiku 4.5 | $0.00007 | $0.00302 |
Grade B, and why
configuring-the-jail scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Your own agent config — `~/.claude/settings.json`, `~/.codex/config.toml`, How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuring the Jail
Use this when a change must be baked into how the jail is built so it survives a restart: a package/runtime the project always needs, a resource limit, a published port or mount, an MCP/LSP server, an env source, or enabling a host-capability loophole.
Do NOT use this for one-off installs. The jail has internet and you can
npm i -g, pip install, uv pip install, or mise use a tool right now with
no config change and no restart. Only reach for yolo-jail.jsonc when the tool
must persist across restarts or be present for every future session.
You already know the loop — here's what it leaves out
The always-on briefing already states the rule: edit → yolo check --no-build
→ fix any [FAIL] → then STOP and ask the human to restart (you cannot
restart this jail from inside it). Assume that. This skill covers the parts that
rule leaves out.
Rebuild vs. restart — which changes are slow
Most changes take effect on the next restart (config is re-read at launch). Only changes to the image package set force a slower image rebuild first, and there are exactly two ways to change that set:
packages— nix packages baked into the image.gpu.vaapi: true— but only whengpu.enabled: trueandgpu.vendor: "amd", which pullsmesa+libva-utilsinto the package set.
Everything else — mise_tools, resources, network, mounts,
mcp_servers, lsp_servers, env_sources, loopholes, packs — is
restart-only, no rebuild. Prefer mise_tools over packages for CLIs and
runtimes: it avoids the rebuild entirely. When you touch packages (or trigger
vaapi), say so in your handoff — on the yolo-jail dev repo a rebuild also needs
a host just load.
Which file — and how the layers merge
Three layers merge, later wins:
~/.config/yolo-jail/config.jsonc— user/machine defaults.<workspace>/yolo-jail.jsonc— the committed per-project config. Edit this one unless told otherwise.<workspace>/yolo-jail.local.jsonc— gitignored per-machine tweaks (auto-merged when present).
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.
- 2d ago Changed · +13 lines f11f887f6592
- 11d ago First seen · 218 lines · 68 tokens per session scan B 5fd7e2d53382
configuring-the-jail is a skill published in the GitHub repository mschulkind-oss/yolo-jail (2 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 3,020 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…