tinysdlc: Skill for Claude Code

.agents/skills/send-user-message/SKILL.md

send-user-message is a skill for Claude Code, Codex from Minh-Tam-Solution/tinysdlc. It costs 110 tokens per session (758 once invoked), scanned A, original, MIT.

A skill for sending proactive messages to a paired user through Discord, Telegram, or WhatsApp. It places the message in an outgoing queue for the connected channel client to deliver.

In plain words
What is it for?
Use it for task-completion notices, status updates, alerts, and messages with file attachments.
Why use it?
It lets an agent notify someone when there is no active conversation, such as after a scheduled task or an alert. It also supports choosing among multiple approved recipients.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Minh-Tam-Solution/tinysdlc's own configuration. It tells Claude Code and Codex how to work on tinysdlc itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tinysdlc configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/you/.tinysdlc/files/report.pdf,/Users/you/.tinysdlc/files/chart.png.

Reuse

Borrowing it

Nothing to install: this file belongs to Minh-Tam-Solution/tinysdlc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Minh-Tam-Solution/tinysdlc/main/.agents/skills/send-user-message/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Minh-Tam-Solution/tinysdlc

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.

agentmods badge for send-user-message

README.md
[![agentmods](https://agentmods.dev/badge/skills/minh-tam-solution/tinysdlc/send-user-message/github.svg)](https://agentmods.dev/skills/minh-tam-solution/tinysdlc/send-user-message)
Your own site
<a href="https://agentmods.dev/skills/minh-tam-solution/tinysdlc/send-user-message"><img src="https://agentmods.dev/badge/skills/minh-tam-solution/tinysdlc/send-user-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.

agentmods 80×15 button for send-user-message

Your own site · 80×15
<a href="https://agentmods.dev/skills/minh-tam-solution/tinysdlc/send-user-message"><img src="https://agentmods.dev/badge/skills/minh-tam-solution/tinysdlc/send-user-message.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 758 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 original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.00758
Opus 5 $0.00055 $0.00379
Sonnet 5 $0.00022 $0.00152
Haiku 4.5 $0.00011 $0.00076

Measured 10d ago against content hash ac56191660af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

send-user-message 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/send_message.ts, scripts/send-message.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/send-user-message/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Send User Message

Send a message to a paired user by writing to the TinySDLC outgoing queue. The message is delivered by the channel client (Discord, Telegram, or WhatsApp) that polls the queue.

When to use

  • Proactively notify a user (e.g., task completion, status update, alert)
  • Send a message during a heartbeat invocation (no active user conversation)
  • Reach a specific user on a specific channel when multiple pairings exist

Workflow

1. Identify the target

If you already know the target from the current conversation context (channel and senderId from the incoming message), skip to step 2.

If you are running from a heartbeat invocation or are unsure which user to send to, list available targets first:

<skill_dir>/scripts/send-message.sh list-targets

This reads pairing.json and prints all approved pairings with their channel, senderId, and sender (display name). Pick the appropriate target.

2. Send the message

<skill_dir>/scripts/send-message.sh send \
  --channel <channel> \
  --sender-id <senderId> \
  --sender "<display name>" \
  --message "<your message>"

With file attachments:

<skill_dir>/scripts/send-message.sh send \
  --channel telegram \
  --sender-id 123456 \
  --sender "Alice" \
  --message "Here's the report you requested." \
  --files "/Users/you/.tinysdlc/files/report.pdf,/Users/you/.tinysdlc/files/chart.png"

Parameters:

  • --channel: One of discord, telegram, whatsapp
  • --sender-id: The channel-specific user ID (from pairing.json or conversation context)
  • --sender: Human-readable display name of the recipient
  • --message: The message text to send (max 4000 chars)
  • --agent: (Optional) Agent ID to attribute the message to
  • --files: (Optional) Comma-separated absolute file paths to attach (files must exist on disk)

The script writes a JSON file to the outgoing queue directory with the correct {channel}_ prefix so the channel client picks it up.

3. Choosing a target when multiple pairings exist

Read the full file on GitHub · 74 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 10d ago First seen · 74 lines · 110 tokens per session scan A ac56191660af

Subscribe to this mod's changes

send-user-message is a skill published in the GitHub repository Minh-Tam-Solution/tinysdlc (10 stars, last pushed 6mo ago), licensed MIT. It adds 110 tokens to every session and 758 once invoked, about $0.0006 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.