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 OpenCoven/coven --skill coven-kittygit clone --depth 1 https://github.com/OpenCoven/covenWrote 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/opencoven/coven/coven-kitty)<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>- NVIDIA SkillSpector warn
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.
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 | $0.00057 | $0.00609 |
| Opus 5 | $0.00028 | $0.00304 |
| Sonnet 5 | $0.00011 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
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.
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.
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 · 86 lines · 57 tokens per session scan A ab19452e53fb
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.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
ppt-review
Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.
package-installer
Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.