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 thewolffish/wolffish-app --skill utilitiesgit 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/utilities)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/utilities"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/utilities/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/thewolffish/wolffish-app/utilities"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/utilities.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 | $0.00032 | $0.01459 |
| Opus 5 | $0.00016 | $0.00730 |
| Sonnet 5 | $0.00006 | $0.00292 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
utilities 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 8d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Utilities
A grab-bag of small, always-available helpers that are too small to each be their own capability. Add new general-purpose utility tools here rather than spinning up a new capability for every one-off.
send_file — deliver a file to the user
Use send_file to actually hand a file to the user inside the conversation. Saving a
file to disk and telling the user "saved to …/files/report.pdf" is not delivery —
on WhatsApp and Telegram the user never sees the file, and even in the app the path is
not the file. send_file closes that gap on every channel at once.
When to call it — the default, every time
Call send_file for any file you created, edited, converted, downloaded, or saved — a
Python/PIL image edit, an ImageMagick call, a shell/script output, a download, a file saved
outside the workspace (the Desktop, etc.), a pre-existing file the user asked for. Deliver it as
the last real step, then write your short wrap-up. A file the user can't see is a failed task —
when in doubt, send it.
Re-deliver every version when the user is iterating. If they're refining a file — you edit,
regenerate, "make it red", "now orange" — call send_file on the updated file each time,
even if you delivered a file at that same path in an earlier turn. Each new version is a new
result the user must see. A new turn, a different file, or an edited version always gets sent.
Chart cards. A file whose name ends in .chart.json is a chart spec: send_file delivers
it as an interactive chart card in the in-app chat (on WhatsApp/Telegram it arrives as a plain
document, so prefer a text table there). The spec format and when to chart live in the core
dataviz tool's manual — call dataviz before authoring one.
When NOT to call it — almost never
NOTHING auto-attaches anymore: no generation tool (pdf, browser_pdf, ffmpeg, image/meme
generation, shell open) delivers its own output. If you don't call send_file, the user
receives nothing — on every channel. The only reasons to skip it: (1) you already sent this
exact file this turn (the runtime status lists your sends), or (2) the user explicitly asked
for the file to be placed somewhere without delivery — and if you're merely unsure, ASK
whether they want it sent rather than silently withholding it.
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.
- 8d ago First seen · 101 lines · 32 tokens per session scan A 35dba1e4743f
utilities is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,459 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
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.
figma-create-design-system-rules
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server…
figma-generate-design
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the…
figma-generate-library
Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. This skill teaches WHAT to build and in WHAT ORDER — it…