Borrowing it
Nothing to install: this file belongs to zdavison/deer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zdavison/deer/main/.claude/skills/kadai/SKILL.mdgit clone --depth 1 https://github.com/zdavison/deerWrote 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/zdavison/deer/kadai)<a href="https://agentmods.dev/skills/zdavison/deer/kadai"><img src="https://agentmods.dev/badge/skills/zdavison/deer/kadai.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00593 |
| Opus 5 | $0.00017 | $0.00296 |
| Sonnet 5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
kadai 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 6d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kadai — Project Script Runner
kadai manages and runs project-specific shell scripts stored in .kadai/actions/.
Discovering Actions
kadai list --json
Returns a JSON array of available actions:
[
{
"id": "database/reset",
"name": "Reset Database",
"emoji": "🗑️",
"description": "Drop and recreate the dev database",
"category": ["database"],
"runtime": "bash",
"confirm": true
}
]
Use --all to include hidden actions: kadai list --json --all
Always use kadai list --json for the current set of actions — do not hardcode action lists.
Running Actions
kadai run <action-id>
Runs the action and streams stdout/stderr directly. The process exits with the action's exit code. Confirmation prompts are automatically skipped in non-TTY environments.
Examples
kadai run hello
kadai run database/reset
Creating Actions
Create a script file in .kadai/actions/. Supported extensions: .sh, .bash, .ts, .js, .mjs, .py, .tsx.
Add metadata as comments in the first 20 lines using # kadai:<key> <value> (for shell/python) or // kadai:<key> <value> (for JS/TS):
#!/bin/bash
# kadai:name Deploy Staging
# kadai:emoji 🚀
# kadai:description Deploy the app to the staging environment
# kadai:confirm true
echo "Deploying..."
Available metadata keys:
| Key | Description |
|---|---|
name |
Display name in menus |
emoji |
Emoji prefix |
description |
Short description |
confirm |
Require confirmation before running (true/false) |
hidden |
Hide from default listing (true/false) |
fullscreen |
Use alternate screen buffer for ink actions (true/false) |
If name is omitted, it is inferred from the filename (e.g. deploy-staging.sh → "Deploy Staging").
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.
- 6d ago First seen · 93 lines · 34 tokens per session scan A f7f1b920fab0
kadai is a skill published in the GitHub repository zdavison/deer (5 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 593 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…