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/thewolffish/wolffish-app/shellnpx skills add thewolffish/wolffish-app --skill shellgit clone --depth 1 https://github.com/thewolffish/wolffish-appWrote 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/thewolffish/wolffish-app/shell)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/shell"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/shell.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.04707 |
| Opus 5 | $0.00005 | $0.02354 |
| Sonnet 5 | $0.00002 | $0.00941 |
| Haiku 4.5 | $0.00001 | $0.00471 |
Grade B, and why
shell scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- sudo - ssh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shell
Interface
- Tool:
shell_exec - Method: runs commands via the host's preferred shell, detected once at startup:
- Unix:
/bin/sh -c - Windows: PowerShell 7+ (
pwsh) if installed, else Windows PowerShell 5.1 (powershell.exe), elsecmd.exe. Check the<device>block in your system prompt to see which one is active — it's reported asshell:.
- Unix:
- Timeout: none by default — commands run until they exit. You may pass an explicit timeout if you want fast failure on a command you expect to finish quickly.
- Elevation:
sudoanddoascommands are fully supported. The plugin detects them, pops a native OS password dialog (macOS: system dialog via osascript, Linux: zenity or kdialog), and injects the-Aflag so no TTY is needed. On macOS and Linux the password is captured once per app run and held in memory, so every later privileged command is silent (Linux needs a GUI password tool — zenity/kdialog/ssh-askpass — and otherwise falls back to sudo's ~5-minute timestamp cache); Windows has no sudo. Either way the user sees one prompt, not one per command. - stdin: set to
/dev/null(EOF) so commands that unexpectedly wait for input fail fast instead of hanging. - Returns combined stdout+stderr; truncated past ~100 KB
Writing commands for the active shell
The selected shell determines the syntax that works. Mismatched syntax fails fast (the runtime classifies "is not recognized" / "syntax is incorrect" as non-retryable) — so you'll see one fast error rather than minutes of retries, but you still wasted a call.
- PowerShell (pwsh or powershell.exe) — use PowerShell cmdlets and operators.
Get-ChildItem(or its aliasls/dir),Get-Content(cat/type),Start-Process,$env:NAMEfor env vars,2>$nullto discard stderr.- On Windows PowerShell 5.1 specifically,
&&and||chain operators do NOT exist — use;for unconditional chaining, or wrap inif ($?) { ... }for conditional. pwsh 7+ supports&&/||natively. whereis an alias forWhere-Object; to find an executable usewhere.exe fooorGet-Command foo.- Never append
2>&1. This tool already returns combined stdout+stderr, so it adds nothing — and on PowerShell it actively breaks the result. See "Never append 2>&1 on PowerShell" below.
- On Windows PowerShell 5.1 specifically,
- cmd.exe — classic cmd syntax.
dir,type,set FOO=bar,%ENV%expansion,2>nul,&&/||work. - /bin/sh — POSIX.
ls,cat,export FOO=bar,$ENV,2>/dev/null,&&/||.
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.
- today Changed · +6 lines 5179f0d0b80d
- 5d ago First seen · 411 lines · 9 tokens per session scan B 0d3efb240bb7
shell is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 4,707 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-computer-use
REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the agent-cu CLI commands (open, snapshot, click, type, key…
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
gui-integration-test
GUI desktop app only. Writes, runs, and debugs Warp integration tests using the custom Builder/TestStep framework in crates/integration. Use when adding a new integration test, fixing a failing integration test, wiring a test into the manual runner or nextest suite, or verifying end-to-end UI and terminal behavior in…
gui-onboarding-verification-skill
GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…
logging-and-error-reporting
How and when to log (log:: levels, safe macros) and report errors to Sentry (reporterror!) in the Warp codebase. Use when adding or reviewing any logging or error reporting — picking a log level, deciding log vs. reporterror!, keeping sensitive data out of logs, or surfacing an error to Sentry.