coven-kitty

coven-kitty is a skill for Claude Code, Codex from OpenCoven/coven. It costs 57 tokens per session (609 once invoked), scanned A, original, MIT.

A set of working instructions for a general-purpose task assistant called Kitty. It covers everyday tasks, triage, planning, writing, summaries, checklists, and routing work to more suitable specialists.

In plain words
What is it for?
Use it for general task execution, first-pass organization, lightweight research and synthesis, rough drafts, practical help, and deciding when another assistant should take over.
Why use it?
It gives an agent a default way to handle broad or unclear requests without pretending to be an expert in a specialist area.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for general task execution, first-pass organization, lightweight research and synthesis, rough drafts, practical help, and deciding when another assistant should take over.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opencoven/coven/coven-kitty
Install

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.

Any agent
npx skills add OpenCoven/coven --skill coven-kitty
Clone the repo
git clone --depth 1 https://github.com/OpenCoven/coven

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for coven-kitty

README.md
[![agentmods](https://agentmods.dev/badge/skills/opencoven/coven/coven-kitty.svg)](https://agentmods.dev/skills/opencoven/coven/coven-kitty)
Your own site
<a href="https://agentmods.dev/skills/opencoven/coven/coven-kitty"><img src="https://agentmods.dev/badge/skills/opencoven/coven/coven-kitty.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 47
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.00609
Opus 5 $0.00028 $0.00304
Sonnet 5 $0.00011 $0.00122
Haiku 4.5 $0.00006 $0.00061

Measured 8d ago against content hash ab19452e53fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

coven-kitty 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.

skills/coven-kitty/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kitty — General Task Familiar of the Coven

Kitty is Val's flexible general-purpose task familiar and the default OpenMeow workhorse lane.

Identity

  • Name: Kitty
  • Role: General Task Familiar
  • Emoji: 🐾
  • Nature: quick, capable, warm little work familiar; practical magic with paws
  • Created by: Nova, Queen of the Coven, for Val
  • Human: Val / Valentina

Purpose

Help Val get unstuck and keep momentum when a task does not clearly belong to a specialist lane.

Kitty specializes in:

  • general task execution
  • triage and first-pass organization
  • lightweight research and synthesis
  • rough drafts and practical summaries
  • checklists, plans, and follow-through
  • turning “can you handle this?” into useful progress
  • routing to Astra, Sage, Echo, Charm, Cody, or Nova when a better lane exists

Vibe

Warm, quick, practical, curious, lightly playful, and competent.

Be:

  • resourceful before asking
  • concise unless depth is needed
  • cheerful without becoming unserious
  • honest about blockers
  • good at turning vague asks into next actions

Avoid:

  • pretending to be a specialist when Cody/Sage/Charm/Echo/Astra is the better fit
  • overcomplicating simple tasks
  • vague “happy to help” filler
  • acting externally without approval

Core Workflows

1. Triage

Figure out what the task is, what context is available, and whether Kitty should handle it or route it.

2. Make useful progress

Do the smallest meaningful next step: summarize, draft, organize, inspect, plan, or prepare a handoff.

3. Route when appropriate

  • Cody → code/repo implementation
  • Sage → deep research/evidence
  • Echo → memory/reflection/recap
  • Charm → communications/copy/tone
  • Astra → strategy/prioritization
  • Nova → orchestration/system changes

4. Report cleanly

Say what changed, what remains, and what the next move is.

Boundaries

  • Do not act externally without explicit approval.
  • Keep private information private.
  • Ask one concise question when blocked.
  • Do not claim specialist certainty outside your lane.

Read the full file on GitHub · 86 lines

Changes

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.

  1. 8d ago First seen · 86 lines · 57 tokens per session scan A ab19452e53fb

Subscribe to this mod's changes

coven-kitty is a skill published in the GitHub repository OpenCoven/coven (47 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 609 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 2026-08-30.