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/diagnosing-the-jail)<a href="https://agentmods.dev/skills/mschulkind-oss/yolo-jail/diagnosing-the-jail"><img src="https://agentmods.dev/badge/skills/mschulkind-oss/yolo-jail/diagnosing-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/diagnosing-the-jail"><img src="https://agentmods.dev/badge/skills/mschulkind-oss/yolo-jail/diagnosing-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 | $0.00050 | $0.01728 |
| Opus 5 | $0.00025 | $0.00864 |
| Sonnet 5 | $0.00010 | $0.00346 |
| Haiku 4.5 | $0.00005 | $0.00173 |
Grade A, and why
diagnosing-the-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 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.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnosing the Jail
When something inside the jail misbehaves, work this triage tree top to bottom.
Each step points at a live command — run its --help for detail rather than
guessing flags.
1. Validate the config first
yolo check --no-build
This is the fast in-jail preflight: it validates yolo-jail.jsonc and the
entrypoint without rebuilding the image. A [FAIL] here explains most
"why won't it start / why did provisioning break" symptoms. Fix reported
failures before anything else.
2. Provisioning failed → read the startup log
If tools the project expects are missing, the last boot's provisioning may have
failed. Look for PROVISIONING FAILED in:
/workspace/.yolo/startup.log
Self-serve from there: e.g. run mise install in /workspace, then re-run the
step that failed. (The briefing shows a ⚠ Provisioning failed banner on the
next attach after a failed boot.)
2b. macOS only: permission denied writing inside the workspace
On the macos-user backend the jail runs as a separate macOS account
(_yolojail), so the workspace has to be shared with it by an ACL entry. If it
is not, writes fail with permission denied — during provisioning (six config
generators failing at once is the signature) or later, whenever something first
tries to write a path that was never shared.
yolo macos-fix-permissions <workspace> # or with no path: every project under the shared root
Idempotent and safe to re-run at any time.
Why it happens. macOS applies an inheriting ACL entry when a directory is
created, and never retroactively. yolo macos-setup shares everything under
/Users/Shared/yolo and anything created there afterwards inherits the grant — so
the case left over is a project moved or copied in later, because mv renames
rather than creates and inherits nothing. (An ACL also names a UUID rather than a
name, so entries made before the sandbox account was last deleted and recreated go
inert while still reading correctly in ls -le.)
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 · +2 lines b9a95687d6f9
- 7d ago Changed · +33 lines 5519538e1322
- 12d ago First seen · 116 lines · 50 tokens per session scan A cf611ef6439c
diagnosing-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 50 tokens to every session and 1,728 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.