What is monitor AGENTS.md?

Repository instructions for loading the correct AGENTS.md and CLAUDE.md files before changing code. These files contain rules for how an AI coding agent should work in each part of a repository.

It helps discover the repository’s root instructions, load deeper directory-specific instructions, resolve conflicts by scope, and apply the right guidance to single- or multi-file work.

It prevents the agent from missing rules that apply to a specific directory or from using the wrong instruction when files overlap.

monitor AGENTS.md — Instructions file by ntppool

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/ntppool/monitor/agents-md

Clone the repo

git clone --depth 1 https://github.com/ntppool/monitor

Made for: Codex, OpenCode.

Per session 530 This file is loaded in full into every session.

When invoked 530 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.

Model	Per session	Once invoked
Fable 5	$0.00530	$0.00530
Opus 5	$0.00265	$0.00265
Sonnet 5	$0.00106	$0.00106
Haiku 4.5	$0.00053	$0.00053

Measured 2d ago against content hash 338a0f17076c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

monitor 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.

AGENTS.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the shared agent entrypoint for tools that support AGENTS.md.

In this repository, the canonical per-directory agent instructions live in stacked CLAUDE.md files. Use this file to discover and apply those CLAUDE.md instructions correctly.

Instruction Loading

Always read the repository root CLAUDE.md first.
When working in a specific subtree, also read every CLAUDE.md on the directory path from the repo root down to the target directory.
Apply those files in order from general to specific. Example for work in apps/mirrors/cpan/primary/:
- <repo-root>/CLAUDE.md
- <repo-root>/apps/mirrors/CLAUDE.md
- <repo-root>/apps/mirrors/cpan/primary/CLAUDE.md

Scope And Precedence

Treat the root CLAUDE.md as repo-wide defaults.
Treat deeper CLAUDE.md files as additive and more specific to their subtree.
If two applicable CLAUDE.md files conflict, the deepest applicable file wins.
Apply subtree-specific guidance only within that subtree.

Multi-File Work

For a single-file task, load the CLAUDE.md stack for that file's directory.
For multi-file tasks spanning different subtrees, load the applicable stack for each file you inspect or modify.
Do not apply instructions from one subtree to unrelated sibling subtrees unless the root CLAUDE.md says to do so.
If the task starts as repo-wide exploration and no target path is known yet, begin with the root CLAUDE.md and load deeper files as the task narrows.

Canonical Files Only

Use files named exactly CLAUDE.md as the authoritative stacked instructions.
Ignore conflict copies, backups, and similarly named files such as CLAUDE.sync-conflict-*.md unless the user explicitly asks about them.

Tool Configuration

Tools that support custom context filenames should be configured to load AGENTS.md from the repository root.
If a tool also supports another agent file such as GEMINI.md, that file should either repeat these rules or defer to AGENTS.md, but CLAUDE.md remains the canonical source of per-directory instructions.

Read the full file on GitHub · 43 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.

2d ago First seen · 43 lines · 530 tokens per session scan A 338a0f17076c

Subscribe to this mod's changes

monitor AGENTS.md is an instructions file published in the GitHub repository ntppool/monitor (20 stars, last pushed 3mo ago), licensed MIT. It adds 530 tokens to every session, about $0.0027 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 2026-08-30.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

monitor AGENTS.md