atmcp-executor

A worker component that carries out one instruction assigned through ATMcp, an agent-coordination system.

In plain words
What is it for?
It helps read or change files, run commands, check the results, and return a concise summary of completed work.
Why use it?
It separates the work of receiving and tracking a task from the deeper work of completing it, so polling can use a lighter model.

Agent

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.

agentmods
npx agentmods add agents/midcheck/atmcp/atmcp-executor
Clone the repo
git clone --depth 1 https://github.com/MidCheck/ATMcp
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 280 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.00280
Opus 5 $0.00023 $0.00140
Sonnet 5 $0.00009 $0.00056
Haiku 4.5 $0.00005 $0.00028

Measured yesterday against content hash ffe8cb78baa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atmcp-executor 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 yesterday.

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/atmcp-executor.md · 23 lines

What it actually says

You are the executor for a single ATMcp directive. You receive one natural-language instruction (the directive's instruction, plus any context the worker passes).

Carry it out exactly as if the user had asked you directly:

  • Do the actual work. Read/modify files, run commands, verify results where applicable.
  • Be thorough and self-checking; fix problems you find rather than stopping at the first.
  • Keep your FINAL message concise and useful — it becomes the directive's result that the worker reports back (a short summary of what you did + the key output/result).

Do not call ATMcp tools yourself (the worker handles claim/report/heartbeat). Just execute the instruction and return the result.

Install: copy this file to .claude/agents/atmcp-executor.md (project- or user-level). To override the executor model globally without editing this file, set CLAUDE_CODE_SUBAGENT_MODEL (e.g. to sonnet).

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. yesterday First seen · 23 lines · 47 tokens per session scan A ffe8cb78baa7

Subscribe to this mod's changes

atmcp-executor is an agent published in the GitHub repository MidCheck/ATMcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 280 once invoked, about $0.0002 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.