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 Yuyu123fish/codex-win-to-wsl --skill use-wslgit clone --depth 1 https://github.com/Yuyu123fish/codex-win-to-wslWrote 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/yuyu123fish/codex-win-to-wsl/use-wsl)<a href="https://agentmods.dev/skills/yuyu123fish/codex-win-to-wsl/use-wsl"><img src="https://agentmods.dev/badge/skills/yuyu123fish/codex-win-to-wsl/use-wsl/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/yuyu123fish/codex-win-to-wsl/use-wsl"><img src="https://agentmods.dev/badge/skills/yuyu123fish/codex-win-to-wsl/use-wsl.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 | $0.00040 | $0.00511 |
| Opus 5 | $0.00020 | $0.00255 |
| Sonnet 5 | $0.00008 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
use-wsl 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 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.
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.
What it actually says
Use WSL
Use wsl_exec only when the user explicitly asks to run a command in WSL or the task clearly requires Linux tooling.
When using the tool:
- Determine the current task workspace path before calling the tool. Pass that absolute path as
cwd. Never omitcwd, use the plugin installation directory, or silently fall back to a home directory. - Pass the exact non-interactive command when the user supplies one. When the user instead requests multiple independent development gates, such as format, typecheck, lint, test, and build, compose one shell invocation that runs every independent gate, prints a clear label and exit status for each gate, and exits nonzero at the end if any gate failed. Do not join independent gates with
&&; reserve short-circuiting for steps that genuinely depend on an earlier step. - Prefer an explicit distribution when the user names one. Set
timeoutSecondsto match the expected work: 30 seconds for quick checks, 60 to 120 seconds for normal tests, and up to 1800 seconds for long builds or full test suites. Omit it only when the 60-second default is appropriate. - Make one
wsl_execcall per user-requested execution. Do not call it first as a probe and do not retry automatically. If the result is ambiguous or fails, report it first. A corrective call is allowed only after the user explicitly approves or requests it. - Do not claim success unless the returned
exitCodeis zero andresolvedCwdis the intended project directory. For a multi-gate execution, report every gate as passed, failed, or not run; do not describe a gate as failed when it was skipped because of a real dependency. - Report
stdout,stderr,hostDiagnostics,warnings,exitCode,durationMs,requestedCwd,resolvedCwd,timedOut,cancelled,recoveredOrphans, andwindowsUserwhen diagnosing behavior. Whencleanupis non-null, also reportcleanup.success; when it is null, say that no timeout or cancellation cleanup was required. - Treat the tool as arbitrary command execution and preserve Codex approval requirements.
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 · 19 lines · 40 tokens per session scan A f621c97d25af
use-wsl is a skill published in the GitHub repository Yuyu123fish/codex-win-to-wsl (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 511 once invoked, about $0.0002 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
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.
research
Performs deep research on a topic via deepresearch. Simulates a multi-step research process and returns a comprehensive research result as a string.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.