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 mcpgit 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/mcp)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/mcp"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/mcp/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/mcp"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/mcp.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 | $0.00052 | $0.01695 |
| Opus 5 | $0.00026 | $0.00847 |
| Sonnet 5 | $0.00010 | $0.00339 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
mcp 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 9d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP — manage your own tool servers
MCP (Model Context Protocol) servers are external tool providers the user can connect to Wolffish. Each connected server contributes a group of tools — namespaced by that server — that you can call like any other tool. This capability lets you manage those connections yourself, entirely by conversation: add one, check it, pause it, or remove it. Everything you do here is the exact same operation the user could do by hand in Settings → MCP, so your changes show up there live (status dots, tool counts, the connection list) and theirs show up to you.
Two kinds of server
- Local (stdio) — a command Wolffish runs on this machine, e.g.
uvx tafsir-mcpornpx -y @scope/some-server. Pass the whole command line astarget. If it needs secrets, pass them inenv. - Remote (HTTP) — a hosted server at an
http(s)://…URL, e.g.https://mcp.example.com/mcp. Pass the URL astarget. Some remote servers require sign-in (see below).
You never choose the transport — mcp_add detects it from the target.
How connections behave (so you set the right expectations)
- Adding connects immediately. No restart. The server's tools become callable on your next turn — if the user asks you to use a just-added server in the same message, add it, tell them it's connected, and use it on your following turn.
- Failures are silent and self-healing. If a server crashes or a remote endpoint drops, Wolffish keeps running and reconnects it in the background with backoff; its tools quietly drop out until it's back. A tool call to a momentarily-unreachable server returns a retryable "temporarily unreachable" error — retry shortly or proceed without it. You don't need to babysit this.
mcp_testis your probe. Use it to confirm a new server works, or to force an offline one to retry now. It also resets the retry backoff.
Signing in (remote OAuth)
If mcp_add or mcp_list shows a server as needs sign-in, call
mcp_authorize — it opens the user's browser to approve access. It does not
finish by itself: tell the user to complete sign-in in the browser, and once
they're back, confirm with mcp_test or mcp_list. Never ask the user for
passwords or tokens to type to you; the browser flow is how they authenticate.
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.
- 9d ago First seen · 126 lines · 52 tokens per session scan A c576d908211b
mcp is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,695 once invoked, about $0.0003 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…