What is agents-observe AGENTS.md?

A live dashboard for watching Claude Code agent sessions, including the events produced while an agent works.

Use it to inspect a current session, view its statistics, check server health, or read recent logs. It runs locally with Docker and opens at port 4981.

It makes an agent’s activity visible and provides commands for checking, starting, stopping, restarting, and troubleshooting the dashboard server.

How simple10/agents-observe configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to simple10/agents-observe. 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/simple10/agents-observe/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/simple10/agents-observe

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/simple10/agents-observe/agents-md/github.svg)](https://agentmods.dev/instructions/simple10/agents-observe/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/simple10/agents-observe/agents-md"><img src="https://agentmods.dev/badge/instructions/simple10/agents-observe/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/simple10/agents-observe/agents-md"><img src="https://agentmods.dev/badge/instructions/simple10/agents-observe/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 835 This file is loaded in full into every session.

When invoked 835 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.

Model	Per session	Once invoked
Fable 5.1	$0.00835	$0.00835
Opus 5.5	$0.00334	$0.00334
Sonnet 5.5	$0.00167	$0.00167
Haiku 4.5	$0.00084	$0.00084

Measured 2mo ago against content hash 3b453d248f16, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agents-observe 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 2mo 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents Observe

Real-time observability dashboard for Claude Code agents. Captures every hook event and streams it to a live dashboard.

Install as Plugin

claude plugin marketplace add simple10/agents-observe
claude plugin install agents-observe

Restart Claude Code. The server auto-starts as a Docker container and the dashboard is at http://localhost:4981.

Skills

Command	Description
`/observe view`	Open the current session in the dashboard
`/observe stats`	Open the current session's stats modal
`/observe`	Open the dashboard
`/observe status`	Server health and config
`/observe start`	Start the server
`/observe stop`	Stop the server
`/observe restart`	Restart the server
`/observe logs`	Show recent container logs
`/observe debug`	Diagnose server issues

Clone & Run

Requires just, Node.js, and Docker.

git clone https://github.com/simple10/agents-observe.git
cd agents-observe
just install   # install dependencies
just start     # start server via Docker

Dashboard: http://localhost:4981

For dev mode with hot reload: just dev (client at http://localhost:5174, API at http://localhost:4981).

Troubleshooting

Problem	Fix
Server not running	Run `/observe start` or restart Claude Code
Docker not running	Start Docker Desktop, then `/observe start`
Port conflict	Set `AGENTS_OBSERVE_SERVER_PORT=<port>` in `.env`
Need diagnostics	Run `/observe debug`
Database issues	Run `just db-reset`

Development

Before developing features or modifying code, read docs/DEVELOPMENT.md. It covers architecture, project structure, commands (just dev, just test, etc.), environment variables, worktree setup, code style, and testing.

Key points:

Use just dev for hot-reload development
Run just check before every commit — runs all tests + formatting
Use just commands for all dev tasks (not npm directly) — see just --list
Worktrees need a .env with unique ports (see DEVELOPMENT.md § Worktrees)
All env vars are centralized in hooks/scripts/lib/config.mjs — never read process.env elsewhere
TypeScript throughout, kebab-case file names

Read the full file on GitHub · 93 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.

2mo ago First seen · 93 lines · 835 tokens per session scan A 3b453d248f16

Subscribe to this mod's changes

agents-observe AGENTS.md is an instructions file published in the GitHub repository simple10/agents-observe (714 stars, last pushed 2mo ago), licensed MIT. It adds 835 tokens to every session, about $0.0033 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.

Building agents

agents-observe AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agents-observe AGENTS.mdsimple10/agents-observe	Instructions file	714	2mo ago	MIT	A	835	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agents-observe: Instructions file for Codex