Open-Inspect is a hosted system that lets coding agents work on software tasks in background development environments. Teams use it to connect agents with repositories, communication tools, scheduled events, and parallel sandboxes. The catalogue contains add-ons associated with this system.
Borrowing it
Nothing to install: this file belongs to ColeMurray/background-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ColeMurray/background-agents/main/AGENTS.mdgit clone --depth 1 https://github.com/ColeMurray/background-agentsWrote 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.
[](https://agentmods.dev/instructions/colemurray/background-agents/agents-md)<a href="https://agentmods.dev/instructions/colemurray/background-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/colemurray/background-agents/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.
<a href="https://agentmods.dev/instructions/colemurray/background-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/colemurray/background-agents/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02361 | $0.02361 |
| Opus 5.5 | $0.00944 | $0.00944 |
| Sonnet 5.5 | $0.00472 | $0.00472 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade A, and why
background-agents 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Open-Inspect is a background coding agent system that spawns sandboxed dev environments to work on GitHub repositories. Single-tenant design. Stack: Cloudflare Workers (TypeScript), Modal (Python), Next.js (React), Terraform.
Architecture
Three tiers connected by WebSockets:
- Web Client (Next.js on Vercel or Cloudflare Workers via OpenNext) — UI with GitHub OAuth, session dashboard, real-time streaming
- Control Plane (Cloudflare Workers + Durable Objects) — session lifecycle, WebSocket hub, GitHub/auth integration. Each session is a Durable Object with SQLite storage. Uses D1 for the session index, repo metadata, environments, and encrypted secrets.
- Data Plane (Modal, Python) — sandboxed environments running coding agents. Manages sandbox creation, snapshots, and repository/environment image builds.
Bot integrations — all Cloudflare Workers using Hono:
slack-bot— Slack messages → coding sessionsgithub-bot— PR review assignments and @mention commandslinear-bot— Linear agent webhooks → coding sessions
Data flow: User prompt → web client → control plane DO (WebSocket) → Modal sandbox → streaming events back through the same WebSocket chain.
Package Dependency Graph
@open-inspect/shared ← control-plane, web, slack-bot, github-bot, linear-bot
@open-inspect/control-plane ← preview
Build @open-inspect/shared first whenever you change shared types. Other packages import from
it at build time.
Package Overview
| Package | Lang / Framework | Purpose |
|---|---|---|
shared |
TypeScript | Shared types, auth utilities, model definitions |
control-plane |
TypeScript / CF Workers + DO | Session management, WebSocket streaming, GitHub integration |
web |
TypeScript / Next.js 16 + React 19 | User-facing dashboard, OAuth, real-time UI |
docs |
TypeScript / Next.js 16 + Fumadocs | Public user documentation at docs.backgroundagents.dev |
slack-bot |
TypeScript / CF Workers + Hono | Slack event handler, session creation |
github-bot |
TypeScript / CF Workers + Hono | PR review and @mention webhook handler |
linear-bot |
TypeScript / CF Workers + Hono | Linear agent webhook handler |
preview |
TypeScript / Node + Playwright | Authenticated local preview of web + control plane (dev) |
modal-infra |
Python 3.12 / Modal + FastAPI | Sandbox lifecycle, WebSocket bridge to control plane |
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.
- 6d ago Changed · +11 lines · +171 tokens per session 8e1515c59a54
- 1mo ago Changed · +6 lines · +100 tokens per session cee420d94faa
- 1mo ago Changed · +1 lines · +27 tokens per session 6473f31a8df7
- 2mo ago First seen · 171 lines · 2,063 tokens per session scan A 028ea5dd8f2f
background-agents AGENTS.md is an instructions file published in the GitHub repository ColeMurray/background-agents (3,433 stars, last pushed 6d ago), licensed MIT. It adds 2,361 tokens to every session, about $0.0094 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.
background-agents AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| background-agents AGENTS.mdColeMurray/background-agents | Instructions file | 3.4k | 6d ago | MIT | A | 2,361 | 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 |