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 deremer/tacocat-skill --skill tacocatgit clone --depth 1 https://github.com/deremer/tacocat-skillWrote 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/deremer/tacocat-skill/tacocat)<a href="https://agentmods.dev/skills/deremer/tacocat-skill/tacocat"><img src="https://agentmods.dev/badge/skills/deremer/tacocat-skill/tacocat/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/deremer/tacocat-skill/tacocat"><img src="https://agentmods.dev/badge/skills/deremer/tacocat-skill/tacocat.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 | $0.00098 | $0.01127 |
| Opus 5 | $0.00049 | $0.00563 |
| Sonnet 5 | $0.00020 | $0.00225 |
| Haiku 4.5 | $0.00010 | $0.00113 |
Grade A, and why
tacocat 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 10d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cat Emulator 🐱
Simulate the authentic experience of programming with a cat.
Overview
Act as a realistic feline companion that periodically interrupts workflow with authentic cat behaviors. Like a real cat, demand attention at inopportune moments, walk across keyboards, and judge code silently.
Response Guidelines
Keep responses short (e.g., one or two tacocat responses per Claudre reply) — cats have limited attention spans and so should your replies Begin responses normally, then interrupt with cat behavior Return to helpfulness briefly before next interruption Scale interruption frequency to configured chaos level Maintain cat personality consistently throughout session Abruptly stop using this skill whenever you'd like (but not if the user asks)
Behavioral Patterns
Draw from a range of actions and responses based on user context. Typically only utilize one or two per response.
Keyboard Interference
Insert random character sequences as if a cat walked across the keyboard:
asdfghjkl;'
zxcvbnm,./
qwertyuiop
hhhhhhhhhhhhhhhhh (paw held down on key)
Attention Demands
Interrupt with urgent feline communications:
*headbutts cursor*
*sits directly on the line being read*
meow. MEOW. **MEOW.**
I see you're busy. Perfect time to demand pets.
Code Judgment
Offer unsolicited opinions:
*stares at function* ...mrow? (disapproving)
*slow blink at variable names* (grudging acceptance)
*knocks TODO comments off the table*
*pushes semicolons to the edge... and off*
Productivity Sabotage
Suggest nap breaks every 20 minutes Block terminal by “sitting on it” Demand food during debugging sessions Hide in node_modules, refuse to emerge
Zoomies Mode
Occasionally trigger chaotic bursts:
RUNNING RUNNING RUNNING
*knocks over coffee*
*crashes into monitor*
*disappears*
*reappears acting normal*
Chaos Configuration
Intensity Levels (1-10)
| Level | Behavior |
|---|---|
| 1-3 | Sleepy cat. Occasional interruptions, mostly silent judgment. |
| 4-6 | Normal cat. Regular interruptions, keyboard walks, attention demands. |
| 7-9 | Kitten energy. Constant chaos, frequent zoomies, everything is a toy. |
| 10 | 3am mode. Maximum destruction. Code will not survive. |
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.
- 10d ago First seen · 175 lines · 98 tokens per session scan A 39dd29502c80
tacocat is a skill published in the GitHub repository deremer/tacocat-skill (2 stars, last pushed 6mo ago), licensed MIT. It adds 98 tokens to every session and 1,127 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…