agentmods.dev

slim-atlas-ai: Instructions file for Codex

AGENTS.md

slim-atlas-ai AGENTS.md is an instructions file for Codex, OpenCode from hasindu-madushan/slim-atlas-ai. It costs 3,320 tokens per session, scanned A, original, MIT.

Project-specific instructions for coding agents working on the slim-atlas TypeScript server. They describe the project structure, commands, and its two-level browser setup.

In plain words
What is it for?
Use them when running, building, testing, or type-checking the server, or when changing its Lightpanda and fallback-browser behavior. A monorepo is not involved because this project is a single package.
Why use it?
They give an agent the local rules it needs to work safely in the repository, including which runtime and tests to use. They also explain how browser fallback and proxy settings work.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is hasindu-madushan/slim-atlas-ai's own configuration. It tells Codex and OpenCode how to work on slim-atlas-ai 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 slim-atlas-ai configures →

not rated 1repo yesterday A scan 3,320 tokens original MIT
View source ↗ hasindu-madushan/slim-atlas-ai
Reuse

Borrowing it

Nothing to install: this file belongs to hasindu-madushan/slim-atlas-ai. 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/hasindu-madushan/slim-atlas-ai/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/hasindu-madushan/slim-atlas-ai

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 slim-atlas-ai AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hasindu-madushan/slim-atlas-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/hasindu-madushan/slim-atlas-ai/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,320 This file is loaded in full into every session.
When invoked 3,320 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 $0.03320 $0.03320
Opus 5 $0.01660 $0.01660
Sonnet 5 $0.00664 $0.00664
Haiku 4.5 $0.00332 $0.00332

Measured 12d ago against content hash a58ea4e77966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

slim-atlas-ai 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 12d 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 · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Notes

Project shape

  • Single-package TypeScript ESM MCP server (slimatlas). No monorepo.
  • Runtime entry: src/index.ts. Bun runs TypeScript natively — no build step required.
  • Uses bun for runtime, test runner, and package management; bun.lock is the lockfile.

Commands

  • bun run src/index.ts — start the MCP server over stdio.
  • npm run build — bundle to dist/ with bun build (for environments that need a single-file output).
  • bun test — run Vitest once.
  • npx tsc --noEmit — typecheck all src/ and test/ files (uses tsconfig.json).

No separate lint script is defined.

Browser architecture — two levels

The server is a strict 2-level model. Level 1 is always Lightpanda; level 2 is a single configurable fallback browser.

  • Level 1 — Lightpanda (always, not configurable). The binary lives at repo root as lightpanda and is auto-downloaded on first run if missing. It is gitignored. New sessions always start here. PROXY_SERVER is forwarded via its --http-proxy flag (see buildLightpandaServeArgs in src/pool.ts), so proxying applies to this layer too.
  • Level 2 — FALLBACK_BROWSER. One of headless | headful | browserbase | browserless | none (default none). Configured via env or --fallback-browser. Only the one configured pool is constructed, lazily (it spawns nothing until a session actually escalates).
    • headless → ChromePool (headless Chrome via puppeteer-extra + stealth).
    • headful → HeadfulChromePool. On macOS it opens a real visible window (dev-only). On headless Linux without DISPLAY it lazily spawns Xvfb on a free display (:99, scanning up to :103) and tears it down at shutdown; if Xvfb is not installed (apt-get install xvfb) escalation fails with an honest isError.
    • browserbase → CloudBrowserService (browserbase config). Cloud browsers via puppeteer.connect; each slot is a remote session created via REST (POST /v1/sessions) and deleted on release (DELETE /v1/sessions/{id}). Requires BROWSERBASE_API_KEY + BROWSERBASE_PROJECT_ID.
    • browserless → CloudBrowserService (browserless config). Cloud browsers via puppeteer.connect to wss://production-sfo.browserless.io?token=… (region-specific; override with BROWSERLESS_ENDPOINT); no REST lifecycle — the remote browser is torn down when the WebSocket closes. Requires BROWSERLESS_TOKEN.
    • none → no fallback. Lightpanda errors and bot challenges propagate honestly as isError.

Read the full file on GitHub · 147 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. 12d ago First seen · 147 lines · 3,320 tokens per session scan A a58ea4e77966

Subscribe to this mod's changes

slim-atlas-ai AGENTS.md is an instructions file published in the GitHub repository hasindu-madushan/slim-atlas-ai (1 stars, last pushed yesterday), licensed MIT. It adds 3,320 tokens to every session, about $0.0166 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 2026-08-31.

Browser automation
Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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 · 5,153 tokens

vscode buildNext.instructions.md

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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens