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 mattwynne/yaks --skill yx-sandboxgit clone --depth 1 https://github.com/mattwynne/yaksWrote 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/mattwynne/yaks/yx-sandbox)<a href="https://agentmods.dev/skills/mattwynne/yaks/yx-sandbox"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/yx-sandbox/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/mattwynne/yaks/yx-sandbox"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/yx-sandbox.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 | $0.00030 | $0.00371 |
| Opus 5 | $0.00015 | $0.00186 |
| Sonnet 5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade C, and why
yx-sandbox scanned grade C 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/tmp.xYz123AbC What it actually says
yx Sandbox
Use a sandbox whenever you need to run yx commands that would
pollute the project's real yak list — exploratory testing, UX
reviews, demos, experiments, etc.
Setup
Create a temp directory and capture its literal path:
mktemp -d
# Output: /tmp/tmp.xYz123AbC ← capture this literal path
Usage
Prefix every yx command with the env vars using the literal
path from above:
cd /tmp/tmp.xYz123AbC && YX_SKIP_GIT_CHECKS=1 yx <command>
cd /tmp/tmp.xYz123AbCenters the temp sandbox directoryYX_SKIP_GIT_CHECKS=1avoids git setup requirements in temp dirs- yx will use
.yaksin the current directory when git checks are skipped - Never run bare
yxwithoutYX_SKIP_GIT_CHECKS=1during sandbox work
Note: Shell variables don't persist between Bash tool calls.
Always use the literal path, not a variable like $SANDBOX.
Cleanup
rm -rf /tmp/tmp.xYz123AbC
Common Mistakes
| Mistake | Fix |
|---|---|
Running yx without the prefix |
Every command needs both env vars |
Using $SANDBOX variable |
Literal path only — vars don't persist between calls |
| Forgetting to clean up | rm -rf <path> when done |
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.
- 11d ago First seen · 51 lines · 30 tokens per session scan C 4f80a42f5a48
yx-sandbox is a skill published in the GitHub repository mattwynne/yaks (58 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 371 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-creator
Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.
skill-index-updater
Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for authoring (skill-creator), improving (skill-auto-improver), or install (asm install).
hello-world
A minimal test skill that greets the user and demonstrates the ASM publish workflow.
openagents-workspace
OpenAgents Workspace collaboration tools — shared files, browser, and multi-agent coordination. Use when: sharing files or reports, browsing websites, reading shared files, checking workspace agents, or collaborating with other agents via @mentions.
refresh-index
Sync every enabled repo in the curated skill index and open a confirmation-gated PR. Use when refreshing already-indexed sources. Don't use for adding new repos, improving a single skill, or installing skills locally.
coding
Use when five specialized coding agents (linter, perf, refactor, security, test) that enforce quality gates across the development lifecycle. From lint enforcement through performance profiling, refactoring, security auditing, and test coverage. Use when working with coding agents.