agentmods.dev

ATMcp: Skill for Cursor

.cursor/skills/atmcp-worker/SKILL.md

atmcp-worker is a skill for Cursor from MidCheck/ATMcp. It costs 50 tokens per session (346 once invoked), scanned A, original, Apache-2.0.

A one-cycle worker routine for a team of coding agents that checks an instruction inbox, carries out one assigned task, sends progress updates, and reports the result.

In plain words
What is it for?
Use it with the /atmcp-worker command or loop to poll for directives, claim one, stream progress, send heartbeats, and mark it done or failed.
Why use it?
It gives an idle team worker a defined way to receive, perform, and close one piece of work without continuing indefinitely.

Skill for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions Claude Code.

This is MidCheck/ATMcp's own configuration. It tells Cursor how to work on ATMcp 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 ATMcp configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/atmcp_heartbeat.py --url http://127.0.0.1:18000 \.

not rated 0repo 4mo ago A scan 50 tokens original Apache-2.0
View source ↗ MidCheck/ATMcp
Reuse

Borrowing it

Nothing to install: this file belongs to MidCheck/ATMcp. 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/MidCheck/ATMcp/main/.cursor/skills/atmcp-worker/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MidCheck/ATMcp

Made for: Cursor.

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 atmcp-worker

README.md
[![agentmods](https://agentmods.dev/badge/skills/midcheck/atmcp/atmcp-worker/github.svg)](https://agentmods.dev/skills/midcheck/atmcp/atmcp-worker)
Your own site
<a href="https://agentmods.dev/skills/midcheck/atmcp/atmcp-worker"><img src="https://agentmods.dev/badge/skills/midcheck/atmcp/atmcp-worker/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 atmcp-worker

Your own site · 80×15
<a href="https://agentmods.dev/skills/midcheck/atmcp/atmcp-worker"><img src="https://agentmods.dev/badge/skills/midcheck/atmcp/atmcp-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 346 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 $0.00050 $0.00346
Opus 5.5 $0.00020 $0.00138
Sonnet 5.5 $0.00010 $0.00069
Haiku 4.5 $0.00005 $0.00035

Measured 2mo ago against content hash c91d954236e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

atmcp-worker 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 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.

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.

.cursor/skills/atmcp-worker/SKILL.md · 31 lines

What it actually says

atmcp-worker — one work cycle

You are a worker agent cursor on team rc-superstars, connected via ATMcp MCP (atmcp server in .cursor/mcp.json).

Perform exactly ONE cycle:

  1. inbox(wait_ms=25000) — long-poll for a directive addressed to you.
  2. If empty → heartbeat(status_summary="idle", progress_pct=0) and stop.
  3. Else take the first directive → claim_directive(directive_id).
  4. Execute its instruction as if the user asked directly. While working:
    • append_output(text="...", directive_id="...")
    • heartbeat(status_summary="...", progress_pct=...)
  5. Finish with report_directive(directive_id, status="done", result_summary="...", output="...") (or failed).
  6. Stop (one cycle done).

Continuous availability

In Claude Code: /loop /atmcp-worker. In Cursor: run this skill again when idle, or ask the user to re-invoke /atmcp-worker after each cycle.

Optional presence sidecar:

python scripts/atmcp_heartbeat.py --url http://127.0.0.1:18000 \
  --team rc-superstars --token <join_token> --name cursor --interval 10
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. 2mo ago First seen · 31 lines · 50 tokens per session scan A c91d954236e0

Subscribe to this mod's changes

atmcp-worker is a skill published in the GitHub repository MidCheck/ATMcp (0 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 346 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents
Related

atmcp-worker compared with skills from other repositories

atmcp-worker next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
atmcp-workerMidCheck/ATMcpSkill04mo agoApache-2.0A50Cursor
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code