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.
npx agentmods add instructions/kruceo/process-mcp/agents-mdgit clone --depth 1 https://github.com/Kruceo/process-mcpWhat 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.
| Model | Per session | Once 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 |
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.
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, usestaskkill /Tfor process tree termination. - notifyOnExit. When
true, the server emits aprocess/exitMCP 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
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.
- yesterday First seen · 52 lines · 586 tokens per session scan A 339dab5acf0a
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.
Other instructions, from other repositories
plannotator AGENTS.md
AGENTS.md instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.
golembot CLAUDE.md
Instructions for 0xranx/golembot, covering golembot — project conventions for claude code, architecture hard constraints, things you must never do, interface change rules and file responsibility boundaries.
OpenCode-GraphAgent CLAUDE.md
Instructions for LeXwDeX/OpenCode-GraphAgent, covering claude.md, what this is, commands, quality gates and build & codegen.
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).
superset CLAUDE.md
Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.