A guarded tool for sending one KakaoTalk message through the macOS app using accessibility controls. It supports a dry run and requires explicit confirmation of the recipient and final message before sending.

Use it to check a target, preview a message, and send one explicitly approved message through KakaoTalk.

It reduces the risk of sending a private or irreversible message to the wrong person, and blocks bulk, unsolicited, or unattended delivery.

katok-send — Skill for Claude Code and Codex by changeroa/lazykatok

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 changeroa/lazykatok --skill katok-send

Clone the repo

git clone --depth 1 https://github.com/changeroa/lazykatok

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/changeroa/lazykatok/katok-send/github.svg)](https://agentmods.dev/skills/changeroa/lazykatok/katok-send)

Your own site

<a href="https://agentmods.dev/skills/changeroa/lazykatok/katok-send"><img src="https://agentmods.dev/badge/skills/changeroa/lazykatok/katok-send/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/changeroa/lazykatok/katok-send"><img src="https://agentmods.dev/badge/skills/changeroa/lazykatok/katok-send.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,388 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.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.01388
Opus 5.5	$0.00021	$0.00555
Sonnet 5.5	$0.00011	$0.00278
Haiku 4.5	$0.00005	$0.00139

Measured 1mo ago against content hash a432d2b481b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

katok-send 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 1mo 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.

Origin

This is a copy

100% identical to katok-send — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/katok-send/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

katok-send

Use the katok CLI only. This skill controls an irreversible external side effect, so user confirmation and the repository's use policy are mandatory.

Mandatory Rules

Read ACCEPTABLE_USE_POLICY.md and DISCLAIMER.md before the first send.
Never infer permission to send from a request to search, summarize, draft, configure, test, or inspect KakaoTalk.
Never use this skill for:
- unsolicited commercial messages or spam;
- sending after refusal, blocking, reporting, or a request to stop;
- impersonation, account theft, phishing, fraud, stalking, or harassment;
- repeated, bulk, scheduled, unattended, or recipient-list delivery;
- privacy violations, secret monitoring, or access-control evasion.
Do not pass --accept-use-policy until the user explicitly confirms the exact target and final payload in the current interaction.
Prefer an unambiguous --chat <chat-id> over a room name.
Always run --dry-run first and show the resolved target to the user.
Never retry a failed send automatically. Report the error and stop. Exception: the single documented recovery in Troubleshooting (webp/HEIC paste-confirm miss → one PNG convert + one --take-focus-now resend). That is a payload fix, not a blind retry of the same path. If it fails again, stop.
Never log or repeat the message body unnecessarily.
--text and --image are mutually exclusive. Text + image = two separate katok send calls (text first, then image), each after user confirmation of that payload.

Workflow

1. Check readiness

katok doctor --json
katok permissions macos --accessibility

Opening System Settings is not permission to send. The user must still approve the exact message.

2. Resolve the target without sending

katok send --chat <chat-id> --dry-run --json

If only a room name is available:

katok send --room "정확한 방 이름" --dry-run --json

Stop if the room is missing, ambiguous, or different from what the user named.

Read the full file on GitHub · 162 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.

1mo ago First seen · 162 lines · 53 tokens per session scan A a432d2b481b8

Subscribe to this mod's changes

katok-send is a skill published in the GitHub repository changeroa/lazykatok (45 stars, last pushed 18d ago), licensed MIT. It adds 53 tokens to every session and 1,388 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to katok-send, differing in 0 lines, and is treated as a copy.

Productivity

katok-send next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
katok-sendchangeroa/lazykatok	Skill	45	18d ago	MIT	A	53	Claude Code, Codex
orbit-notionnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex

katok-send

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

katok-send

Mandatory Rules

Workflow

1. Check readiness

2. Resolve the target without sending

What this file has done since we first saw it

katok-send compared with skills from other repositories