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 changeroa/lazykatok --skill katok-sendgit clone --depth 1 https://github.com/changeroa/lazykatokWrote 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/changeroa/lazykatok/katok-send)<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.
<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>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 | $0.00026 | $0.00694 |
| Sonnet 5 | $0.00011 | $0.00278 |
| Haiku 4.5 | $0.00005 | $0.00139 |
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 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.
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.
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.mdandDISCLAIMER.mdbefore 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-policyuntil 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-runfirst 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-nowresend). 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.
--textand--imageare mutually exclusive. Text + image = two separatekatok sendcalls (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.
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 · 162 lines · 53 tokens per session scan A a432d2b481b8
katok-send is a skill published in the GitHub repository changeroa/lazykatok (32 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 1,388 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.