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 agentmods add skills/wangyendt/wayne-skills/toolsetupnpx skills add wangyendt/wayne-skills --skill toolsetupgit clone --depth 1 https://github.com/wangyendt/wayne-skillsWhat 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 | $0.00088 | $0.01508 |
| Opus 5 | $0.00044 | $0.00754 |
| Sonnet 5 | $0.00018 | $0.00302 |
| Haiku 4.5 | $0.00009 | $0.00151 |
Grade B, and why
pywayne-bin-toolsetup 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
The task runs the official Linux installer, enables `tailscaled` when systemd is active, and runs `sudo tailscale up`. Explain that first use normally prints an authentication URL. Do not suggest this task for macOS or W How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pywayne Bin Toolsetup
Use toolsetup as the source of truth for repeatable developer-machine setup. Prefer its task interface over pasting ad-hoc rc snippets or long installer command sequences because it provides platform checks, idempotent managed blocks, confirmation, and dry-run output.
Start safely
Identify the target platform and requested task, then preview installation work first unless the user explicitly asks you to execute it:
toolsetup --task <shortcuts|npm|tailscale|mongodb|all> --platform <auto|macos|linux|windows> --dry-run
Use --yes only when the user has authorized actual installation. npm, Tailscale, and MongoDB may download software and use sudo; shortcut-only configuration does not require the confirmation flag.
An explicit platform that differs from the host is accepted only with --dry-run. Do not work around that guard.
Support matrix
| Task | macOS | Linux | Windows |
|---|---|---|---|
shortcuts |
bash/zsh | bash/zsh, including gpu |
PowerShell |
npm |
yes | yes | no |
tailscale |
no | yes | no |
mongodb |
yes | yes | no |
--task all selects only tasks supported by the target platform. On Windows this means shortcuts only. Do not claim that the gpu command is available on macOS or Windows; by design it is Linux-only.
Shortcut configuration
Use the detected shell, or select it explicitly:
toolsetup --task shortcuts --platform macos --shell zsh
toolsetup --task shortcuts --platform linux --shell bash
toolsetup.cmd --task shortcuts --platform windows
The Unix block provides:
proxy_on/proxy_off: toggle HTTP, HTTPS, SOCKS, and NO_PROXY variables and Git global proxy settings.goto: persist directory shortcuts in~/.goto_paths.gpu: on Linux only, show NVIDIA hardware, compute processes, and VRAM totals by user.
PowerShell provides proxy_on, proxy_off, and goto, storing paths in ~/.goto_paths.json.
Customize defaults and seed paths with:
toolsetup --task shortcuts --platform auto \
--http-proxy http://127.0.0.1:7890 \
--socks-proxy socks5://127.0.0.1:7890 \
--no-proxy 'localhost,127.0.0.1,.example.com' \
--goto code="$HOME/Documents/work/code" \
--goto tools="$HOME/Documents/tools"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 144 lines · 88 tokens per session scan B 3e432f8c5fc9
pywayne-bin-toolsetup is a skill published in the GitHub repository wangyendt/wayne-skills (8 stars, last pushed 6d ago), licensed MIT. It adds 88 tokens to every session and 1,508 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…