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/developing-yolo-jail)<a href="https://agentmods.dev/skills/mschulkind-oss/yolo-jail/developing-yolo-jail"><img src="https://agentmods.dev/badge/skills/mschulkind-oss/yolo-jail/developing-yolo-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/developing-yolo-jail"><img src="https://agentmods.dev/badge/skills/mschulkind-oss/yolo-jail/developing-yolo-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 | $0.00062 | $0.03082 |
| Opus 5 | $0.00031 | $0.01541 |
| Sonnet 5 | $0.00012 | $0.00616 |
| Haiku 4.5 | $0.00006 | $0.00308 |
Grade A, and why
developing-yolo-jail 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 today.
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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developing yolo-jail
This jail is running against the yolo-jail source tree itself. /workspace is
bind-mounted live.
The image does not contain yolo (since 2026-09-06). /opt/yolo-jail is two
:ro bind mounts the LAUNCH supplies — the linux binaries at bin/, the flake
bundle at share/yolo-jail/ — and the image bakes only those mountpoints plus
the /bin/<name> symlinks that point into them. Two things follow, and they pull
in opposite directions so keep both: a commit touching only cmd/ or internal/
no longer moves the image at all (no rebuild, no image delivery — the Go source
left the image derivation), and there is still no dev-override wrapper, so you
cannot live-patch the running jail's binaries either. A nested jail builds the
live checkout's own .#installPrefix and mounts THAT — but only when you pass
YOLO_REPO_ROOT=/workspace, and only from a throwaway workspace (see "The
flake a launch builds from" and "Never launch a nested jail on /workspace"
below). Then your edited Go code is what runs. These are
the build/deploy traps that have no yolo --help home — the authoritative
version lives in /workspace/AGENTS.md (bind-mounted, always current); read it
for the full detail.
Verifying a change on macos-user
A macos-user jail cannot launch a jail, so the nested-jail loop does not exist
there. Two kernel rules, not a missing feature: sudo cannot exec inside any
Seatbelt sandbox, and sandbox_apply refuses a profile that differs from the active
one. Nesting is unavailable however the code is written.
What DOES work from inside, and covers most of the backend:
yolo run --dry-run— the whole plan, invariants included.yolo internal darwin-bootstrapwithHOME/JAIL_HOMEpointed at a temp dir — the real generators, the real shims, the real overlay install.- the staging argv from the plan, with
sudodropped and the destination redirected — the copies, the modes, and the fresh-inode rule.
Both of the last two are automated (internal/entrypoint/darwinbootstrap_darwin_test.go,
internal/macosuser/staging_darwin_test.go) and run on any Mac with no privilege.
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.
- today Changed · +39 lines 72408f70227c
- 5d ago Changed · +21 lines ddd52cb647ef
- 6d ago Changed · +55 lines 5da2514e9537
- 10d ago First seen · 91 lines · 62 tokens per session scan A 7e84e0a287e3
developing-yolo-jail is a skill published in the GitHub repository mschulkind-oss/yolo-jail (2 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 3,082 once invoked, about $0.0003 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
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.