agent-job-dm

agent-job-dm is a skill for Claude Code, Codex from stephengpope/thepopebot. It costs 104 tokens per session (651 once invoked), scanned A, original, MIT.

A messaging skill for sending a direct message to one user or a broadcast to subscribed administrators through Telegram, a messaging service.

In plain words
What is it for?
Use it when a job needs to notify someone about a result, status, or event. It explains how to identify a named recipient and how to broadcast to administrators.
Why use it?
It provides separate instructions for contacting the person who started a job, a named user, or all subscribed admins. This prevents messages from being sent to the wrong audience or bypassing subscription settings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when a job needs to notify someone about a result, status, or event. It explains how to identify a named recipient and how to broadcast to administrators.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stephengpope/thepopebot/agent-job-dm
About the project

The Pope Bot is an app for configuring an autonomous AI agent that can chat, run coding work, and operate continuously through connected language models and coding agents. People use it for questions, code changes, background development jobs, and live browser-based coding sessions. Its catalogue add-ons extend the bot with commands, skills, and operating instructions.

stephengpope/thepopebot · 1,859 stars · on GitHub · skool.com

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 stephengpope/thepopebot --skill agent-job-dm
Clone the repo
git clone --depth 1 https://github.com/stephengpope/thepopebot

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 agent-job-dm

README.md
[![agentmods](https://agentmods.dev/badge/skills/stephengpope/thepopebot/agent-job-dm/github.svg)](https://agentmods.dev/skills/stephengpope/thepopebot/agent-job-dm)
Your own site
<a href="https://agentmods.dev/skills/stephengpope/thepopebot/agent-job-dm"><img src="https://agentmods.dev/badge/skills/stephengpope/thepopebot/agent-job-dm/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 agent-job-dm

Your own site · 80×15
<a href="https://agentmods.dev/skills/stephengpope/thepopebot/agent-job-dm"><img src="https://agentmods.dev/badge/skills/stephengpope/thepopebot/agent-job-dm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 651 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00104 $0.00651
Opus 5 $0.00052 $0.00326
Sonnet 5 $0.00021 $0.00130
Haiku 4.5 $0.00010 $0.00065

Measured 12d ago against content hash fea544f43f5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-job-dm 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (agent-job-dm.js), 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.

templates/skills-library/agent-job-dm/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The three modes — pick one

Read the request and route to exactly one of these. Do NOT mix them.

Mode 1 — Broadcast to admins

Trigger phrases: "notify the admins", "alert everyone", "broadcast this", "let the team know", "tell all admins", "send to admins".

node skills/agent-job-dm/agent-job-dm.js send "<message>" --broadcast

DO NOT run list first. DO NOT look up any user ids. The --broadcast flag handles fan-out internally — it sends to every admin where subscribed_to_system_messages=true automatically. Calling list and then sending one-at-a-time is wrong and skips the subscription filter.

Mode 2 — DM the originator (the user who started this job)

Trigger phrases: "DM me", "let me know when…", "tell me when…", "ping me", "send me".

node skills/agent-job-dm/agent-job-dm.js send "<message>"

No flags. The skill reads USER_ID from the environment (the originator) and sends to them. Don't look them up — USER_ID is already correct.

Mode 3 — DM a specific named user

Trigger phrases: "tell Alice…", "send this to bob@…", "DM ", "message ".

node skills/agent-job-dm/agent-job-dm.js list
node skills/agent-job-dm/agent-job-dm.js send --user-id <id> "<message>"
  1. Run list to get the directory.
  2. Match the requested name against nickname, first_name, last_name, or email. If multiple match, ask which one.
  3. Send with --user-id <id>.

Other commands

# List users (id, email, first/last name, nickname, role, available DM channels)
node skills/agent-job-dm/agent-job-dm.js list

Rules

  • The <message> arg is sent verbatim. Don't rewrite it unless the requester asked you to.
  • AGENT_JOB_TOKEN, APP_URL, and USER_ID are injected automatically — no setup required.
  • Every DM is stored in the recipient's inbox in the event handler, regardless of delivery channel.
  • Users link their DM channel themselves in /profile/telegram. If a target user has no verified channel, the message still lands in their inbox.

Read the full file on GitHub · 56 lines

Files

What ships with it

1 file 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. 12d ago First seen · 56 lines · 104 tokens per session scan A fea544f43f5f

Subscribe to this mod's changes

agent-job-dm is a skill published in the GitHub repository stephengpope/thepopebot (1,859 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 651 once invoked, about $0.0005 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 2026-08-30.