agentmods.dev

systems-manager AGENTS.md

Repository instructions for Knuckles-Team’s systems-manager project, documenting its Python stack, architecture, diagrams, and required commands.

In plain words
What is it for?
Use them when working on the project’s agent, MCP server, storage-health checks, credentials, skills, or related system-management components.
Why use it?
They give a coding agent the project’s expected structure and working rules, reducing mistakes when changing or running the code.

Instructions file for CodexOpenCode

3 4d ago A scan 4,612 tokens copy · 86% MIT
View the source file Knuckles-Team/systems-manager
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/knuckles-team/systems-manager/agents-md
Clone the repo
git clone --depth 1 https://github.com/Knuckles-Team/systems-manager

Made for: Codex, OpenCode.

Per session 4,612 This file is loaded in full into every session.
When invoked 4,612 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.04612 $0.04612
Opus 5 $0.02306 $0.02306
Sonnet 5 $0.00922 $0.00922
Haiku 4.5 $0.00461 $0.00461

Measured 2d ago against content hash 2a12f1786764, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

systems-manager 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 2d 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.

Origin

This is a copy

86% identical to servicenow-api AGENTS.md — 97 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Claude Code loads this file via CLAUDE.md (@AGENTS.md import) — the two stay in sync. Edit this file, not CLAUDE.md.

Tech Stack & Architecture

  • Language/Version: Python 3.11–3.14
  • Core Libraries: agent-utilities, fastmcp, pydantic-ai, psutil, distro
  • Key principles: Functional patterns, Pydantic for data validation, asynchronous tool execution.
  • Architecture:
    • mcp_server.py: Main MCP server entry point and tool registration.
    • agent.py: Pydantic AI agent definition and logic.
    • storage_health.py: Physical-disk + BMC drive-fault health (CONCEPT:SM-OS.governance.sys-8/1.5) — SMART (incl. RAID megaraid passthrough), BMC/IPMI drive-slot faults, RAID PD state, correlated; runs over the manager seam (local or remote host).
    • bmc_credentials.py: consumes an exact runtime credential projection resolved by AgentConfig from an external secret reference.
    • skills/: Directory containing modular agent skills (if applicable).

Architecture Diagram

graph TD
    User([User/A2A]) --> Server[A2A Server / FastAPI]
    Server --> Agent[Pydantic AI Agent]
    Agent --> MCP[MCP Server / FastMCP]
    MCP --> Client[API Client / Wrapper]
    MCP --> Storage[sm_storage_health — SM-OS.governance.sys-8/1.5]
    Storage --> Mgr[manager.run_command — local or remote]
    Storage --> SMART([smartctl / megaraid])
    Storage --> BMC([fan-manager IPMI / ipmitool])
    Storage -.OOB credential projection.-> Config([AgentConfig secret reference])
    Client --> ExternalAPI([External Service API])

Workflow Diagram

sequenceDiagram
    participant U as User
    participant S as Server
    participant A as Agent
    participant M as MCP Tools
    participant SM as Systems Manager
    participant PM as Package Manager
    participant SYS as System APIs

    U->>S: Request
    S->>A: Process Query
    A->>M: Invoke Tool
    M->>SM: Execute System Operation
    SM->>PM: Package Management
    SM->>SYS: System APIs
    PM-->>SM: Package Result
    SYS-->>SM: System Result
    SM-->>M: Operation Result
    M-->>A: Tool Result
    A-->>S: Final Response
    S-->>U: Output

Read the full file on GitHub · 374 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. 2d ago First seen · 374 lines · 4,612 tokens per session scan A 2a12f1786764

Subscribe to this mod's changes

systems-manager AGENTS.md is an instructions file published in the GitHub repository Knuckles-Team/systems-manager (3 stars, last pushed 4d ago), licensed MIT. It adds 4,612 tokens to every session, about $0.0231 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to servicenow-api AGENTS.md, differing in 97 lines, and is treated as a copy.

applicationsinstalloperating-systemsystem-managerutilities
Related

Other instructions, from other repositories

github-azure-agentic-journeys AGENTS.md

Instructions for DanWahlin/github-azure-agentic-journeys, covering agents and skills, journeys, prerequisites, agent & skill system and available agents.

DanWahlin/github-azure-agentic-journeys · 2,944 tokens

hoenn AGENTS.md

AGENTS.md instructions for alyraffauf/hoenn, covering work in hoenn, check a change, deploy deliberately and keep secrets out of git.

alyraffauf/hoenn · 384 tokens

FounderOS CLAUDE.md

Instructions for ARCASSystems/FounderOS, covering founder os - claude code plugin, what this is, positioning non-negotiables, quick start and updates.

ARCASSystems/FounderOS · 9,025 tokens

FounderOS AGENTS.md

Instructions for ARCASSystems/FounderOS, covering founderos - agent instructions, read first, joining the operator's team, writing and commits and built by.

ARCASSystems/FounderOS · 1,186 tokens

FounderOS GEMINI.md

Instructions for ARCASSystems/FounderOS, covering founderos - gemini cli context, read first, gemini-specific operating notes, writing and commits and built by.

ARCASSystems/FounderOS · 859 tokens

tools CLAUDE.md

Claude Code instructions for smmariquit/tools, covering phtools project guidelines, 0. core directives, auto-updating knowledge, caveman mode (token compression) and official live data sources.

smmariquit/tools · 1,838 tokens