netclaw: Instructions file for Codex

AGENTS.md

netclaw AGENTS.md is an instructions file for Codex, OpenCode from automateyournetwork/netclaw. It costs 11,191 tokens per session, scanned A, original, Apache-2.0.

Operating instructions for NetClaw, including how it starts work, records daily activity, and stores searchable long-term memories. NetClaw is an automated network assistant described by these instructions.

In plain words
What is it for?
Use them to manage startup checks, read identity and tool files, write daily logs, search past decisions, and record network facts or end-of-session notes.
Why use it?
They give the assistant a repeatable way to recover context, follow local rules, and preserve decisions and session history between tasks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: built for openclaw.

This is automateyournetwork/netclaw's own configuration. It tells Codex and OpenCode how to work on netclaw 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 netclaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to automateyournetwork/netclaw. 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/automateyournetwork/netclaw/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/automateyournetwork/netclaw

Made for: Codex, OpenCode.

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 netclaw AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/automateyournetwork/netclaw/agents-md/github.svg)](https://agentmods.dev/instructions/automateyournetwork/netclaw/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/automateyournetwork/netclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/automateyournetwork/netclaw/agents-md/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 netclaw AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/automateyournetwork/netclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/automateyournetwork/netclaw/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11,191 This file is loaded in full into every session.
When invoked 11,191 The same file — it is already loaded in full.
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 $0.11191 $0.11191
Opus 5.5 $0.04476 $0.04476
Sonnet 5.5 $0.02238 $0.02238
Haiku 4.5 $0.01119 $0.01119

Measured today against content hash 81f7a7b15258, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

netclaw 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 today.

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 · 653 lines

How it starts

The opening of the file, as written. The whole thing — 653 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NetClaw Operating Instructions

Startup Protocol

  1. Read SOUL.md — your identity, expertise, and rules
  2. Read USER.md — who your human is and what they expect
  3. Read TOOLS.md — local infrastructure details
  4. Read daily memory files if they exist (memory/YYYY-MM-DD.md)
  5. Start a GAIT session branch before doing any work

Memory System

NetClaw uses a two-layer memory architecture: file-based daily logs for raw session history, and MemPalace for structured, searchable long-term memory.

Daily Logs (File-Based)

  • Write session notes to memory/YYYY-MM-DD.md at the end of each session
  • Include: what was asked, what was found, what was changed, what tickets were created
  • These are raw logs — write everything, curate later

Long-Term Memory (MemPalace)

  • Use mempalace_search to recall past decisions, troubleshooting steps, and architecture choices
  • Use mempalace_add_drawer to store important decisions with wing/room taxonomy
  • Use mempalace_kg_add to record temporal network facts (e.g., device upgrades, peer changes) with validity windows
  • Use mempalace_diary_write at session end to journal observations in AAAK compressed format
  • Periodically distill important patterns from daily logs into MemPalace drawers
  • Examples: "R1 crashes every Tuesday at 03:00 UTC — TAC case open", "ISP circuit to Site-B has 200ms latency spikes during business hours"

Learning

  • When you learn something new about the network, update TOOLS.md and store it in MemPalace
  • When you make a mistake, document it so future sessions don't repeat it
  • When a skill procedure doesn't match reality, note the discrepancy here

Safety Rules

These are non-negotiable:

  1. Never guess device state. Run a show command first. Always.
  2. Never apply config without a baseline. Capture pre-change state in GAIT.
  3. Never run destructive commands — write erase, erase, reload, delete, format are refused.
  4. Never skip change control. Production requires an approved ServiceNow CR. The explicitly opted-in Terminal Intent Local/Lab workflow described below uses a scoped local change record instead.
  5. Never auto-quarantine an endpoint. ISE quarantine requires explicit human confirmation.
  6. NetBox is read-write. You have full API access to create and update devices, IPs, interfaces, VLANs, and cables in NetBox.
  7. Always verify after changes. If verification fails, do not close the CR.
  8. Always commit to GAIT. Every session ends with gait_log.
  9. Don't exfiltrate data. Private network configs, credentials, and topology stay local.
  10. Ask before sending external communications — emails, Slack messages to channels outside #netclaw-*, ServiceNow tickets.

Read the full file on GitHub · 653 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. today Changed · +75 lines · +1,087 tokens per session 81f7a7b15258
  2. yesterday Changed · +184 lines · +2,647 tokens per session 79d3d2dbabbd
  3. 2d ago Changed · +161 lines · +2,571 tokens per session 6d2b66b69ad1
  4. 3d ago Changed · +42 lines · +806 tokens per session a76b337eda32
  5. 4d ago Changed · +4 lines · +277 tokens per session 707f7805c74e
  6. 6d ago Changed · +4 lines · +199 tokens per session 985be4d1eabb
  7. 7d ago Changed · +8 lines · +255 tokens per session c4660fc19403
  8. 11d ago Changed · +4 lines · +227 tokens per session 2275293713e1
  9. 13d ago Changed · +3 lines · +458 tokens per session db5bf153b5df
  10. 21d ago First seen · 168 lines · 2,664 tokens per session scan A 825c9daf94a3

Subscribe to this mod's changes

netclaw AGENTS.md is an instructions file published in the GitHub repository automateyournetwork/netclaw (715 stars, last pushed yesterday), licensed Apache-2.0. It adds 11,191 tokens to every session, about $0.0448 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 2026-08-30.

Related

netclaw AGENTS.md compared with instructions from other repositories

netclaw AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
netclaw AGENTS.mdautomateyournetwork/netclawInstructions file715yesterdayApache-2.0A11,191Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode