process-mcp AGENTS.md

Development instructions for a local MCP server that manages background processes. MCP is a way for an agent to call tools, while background processes are commands that keep running after they start.

In plain words
What is it for?
Building or contributing to the process MCP server. They cover process control, capped logs, short IDs, termination behavior, notifications, Bun usage, and semantic commit versioning.
Why use it?
They explain how to start, stop, monitor, and query long-running commands without blocking the conversation, while keeping process IDs, logs, signals, and commits consistent.

Instructions file for CodexOpenCode

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 instructions/kruceo/process-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/Kruceo/process-mcp

Made for: Codex, OpenCode.

Per session 586 This file is loaded in full into every session.
When invoked 586 The same file — it is already loaded in full.
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 $0.00586 $0.00586
Opus 5 $0.00293 $0.00293
Sonnet 5 $0.00117 $0.00117
Haiku 4.5 $0.00059 $0.00059

Measured yesterday against content hash 339dab5acf0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

process-mcp AGENTS.md 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.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Process MCP Server

Local MCP server for managing background processes. Start, stop, monitor, and query long-running commands without blocking the conversation.

Key Decisions

  • Bun-first. Runtime is Bun. Node compatibility is nice-to-have, not a requirement.
  • MCP via stdio. No HTTP/SSE ports. The server communicates strictly via stdin/stdout.
  • IDs are short. nanoid(6) — ex: aB3xK9. No UUIDs.
  • Logs capped at 1000 lines. Circular buffer per process.
  • Signals: SIGTERM → SIGKILL. stop(id, false) sends SIGTERM, stop(id, true) sends SIGKILL. On Windows, uses taskkill /T for process tree termination.
  • notifyOnExit. When true, the server emits a process/exit MCP notification when the process terminates. No client currently resumes conversations from this, but the infrastructure is ready.
  • No clean architecture. Keep it simple, practical, and reliable.

Commit Conventions (Pipoca-Style)

We use semantic commits to drive automatic versioning via pipoca.

Tag Meaning Version Bump
fix: Bug fix, correction patch 0.0.x
style: Formatting, linting, no logic change patch 0.0.x
docs: Documentation updates patch 0.0.x
refactor: Code restructuring, no feature change patch 0.0.x
test: Adding or updating tests patch 0.0.x
feature: New functionality minor 0.x.0
update: Dependency updates, enhancements minor 0.x.0
release: Major milestone, breaking changes major x.0.0
chore: Maintenance, build, CI changes none

Examples

fix: handle SIGTERM gracefully on Windows
feature: add notifyOnExit parameter to start tool
docs: update README with installation steps
release: v1.0.0 stable API

Versioning

bunx pipoca update package.json   # calculate next version from commits
git tag v$(jq -r .version package.json)
git push origin main --tags

Read the full file on GitHub · 52 lines

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 · 52 lines · 586 tokens per session scan A 339dab5acf0a

Subscribe to this mod's changes

process-mcp AGENTS.md is an instructions file published in the GitHub repository Kruceo/process-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 586 tokens to every session, about $0.0029 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.