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 diillson/chatcli --skill send-messagegit clone --depth 1 https://github.com/diillson/chatcliWrote 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/diillson/chatcli/send-message)<a href="https://agentmods.dev/skills/diillson/chatcli/send-message"><img src="https://agentmods.dev/badge/skills/diillson/chatcli/send-message/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/diillson/chatcli/send-message"><img src="https://agentmods.dev/badge/skills/diillson/chatcli/send-message.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.00830 |
| Opus 5.5 | $0.00030 | $0.00332 |
| Sonnet 5.5 | $0.00015 | $0.00166 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
send-message scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
shell out to `curl`/`pywhatkit`/browser automation when `@send` covers the platform. How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send Message
Deliver a message to a person/chat through ChatCLI's gateway platform adapters —
the same Telegram/WhatsApp/Discord/Slack/webhook integrations the gateway daemon uses,
now reachable to initiate a message. This is the native, no-gambiarra path: do not
shell out to curl/pywhatkit/browser automation when @send covers the platform.
The tool
@send has two subcommands. Always pass the JSON envelope on one line:
<tool_call name="@send" args='{"cmd":"send","args":{"to":"telegram","message":"Build is green ✅"}}' />
<tool_call name="@send" args='{"cmd":"list"}' />
send {to, message}
tois either:- a bare platform —
"telegram","whatsapp","discord","slack","webhook"— which delivers to that platform's configured home channel (CHATCLI_<PLATFORM>_HOME_CHANNEL); or - a
platform:chat_idtarget — e.g."telegram:-1001234567890","whatsapp:+5511999999999","slack:C0123ABC","discord:<channel_id>". Anything after the first:is passed verbatim, so thread/suffix forms like"telegram:-100123:42"are preserved.
- a bare platform —
messageis plain text. Messaging apps render plain text best — avoid tables, ASCII banners, and code fences unless the user explicitly wants code.
list
Reports which platforms are configured and whether each has a home channel.
Run it first when you're unsure what's available or which to to use.
How to decide
- Which platform? If the user named one ("manda no Telegram"), use it. If a
gateway conversation is in progress, prefer the platform you're already on. If
unsure, run
@send listand pick the only configured one, or ask. - Which target? If the user means "me" and a home channel is set, use the bare
platform. To reach a specific group/chat, use
platform:chat_id. - Write for the channel. Short, natural, plain text. One message unless asked.
Failure handling
"... is not configured"→ that platform has no credentials. Run@send listand use a configured one, or tell the user which env vars to set (e.g.CHATCLI_TELEGRAM_BOT_TOKEN)."No target for <platform>"→ nochat_idgiven and no home channel set. Either passplatform:chat_idor tell the user to setCHATCLI_<PLATFORM>_HOME_CHANNEL.- Delivery errors are reported verbatim from the platform API — surface them; don't retry blindly.
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.
- 2mo ago First seen · 73 lines · 74 tokens per session scan A fb96dd86e25b
send-message is a skill published in the GitHub repository diillson/chatcli (94 stars, last pushed yesterday), licensed Apache-2.0. It adds 74 tokens to every session and 830 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
12-cook
Manages project recipes and practical guides. Use when the user wants to find a recipe, document a technique, research improvements, follow an existing guide, or check that its steps are usable.
05-improve
Reads complete conversation evidence, measures visible cost, and recommends minimal improvements. Use when the user wants to improve a conversation, reduce wasted time or tokens, or choose files to revise. Not for delivery review or automatic edits.
09-for-sure
Run an iterative agent loop that retries until a runnable success condition passes. Use when the user says "for sure", "keep trying until", or wants guaranteed completion against a success command. Not for one-shot tasks or uncheckable goals.
claudeshrink
Automatically compress large natural text or log files before processing. Trigger when the user pastes massive text blobs, or asks to analyze a large file (logs, docs, transcripts), or provides a prompt that is too large for the context window. DO NOT trigger on source code files or structural data (JSON, XML).
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.