zenAgent AGENTS.md

Repository instructions for coding agents working on Zen Agent, a project that controls a browser the user is actively using.

In plain words
What is it for?
They guide agents on repository commands, file layout, TypeScript style, browser-tab discovery, stable tab identification, and the separation between browser automation and setup tools.
Why use it?
They prevent automated changes from unexpectedly switching windows, tabs, or browser spaces, and require the agent to handle uncertainty explicitly.

Instructions file for CodexOpenCode

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/fschrhunt/zenagent/agents-md
Clone the repo
git clone --depth 1 https://github.com/fschrhunt/zenAgent

Made for: Codex, OpenCode.

Per session 1,276 This file is loaded in full into every session.
When invoked 1,276 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.

ModelPer sessionOnce invoked
Fable 5 $0.01276 $0.01276
Opus 5 $0.00638 $0.00638
Sonnet 5 $0.00255 $0.00255
Haiku 4.5 $0.00128 $0.00128

Measured 2d ago against content hash 0b366a96c5c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

zenAgent 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 · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Working rules for coding agents in this repository. Read .context/todo.md for what to build next and docs/adr/0001-browser-transport.md for why the architecture is what it is.

The product invariants come first

Zen Agent drives a browser the user is actively working in. These are not preferences; a change that breaks one of them is a bug even if every test passes:

  • Never focus a Zen window, select a tab, or switch the visible Space as a side effect. browsingContext.activate and tabs.update({active: true}) are the two calls that violate this most easily. The spike keeps activate around only as a positive control.
  • Look before you open. Discover windows, Spaces, and tabs before deciding to create one.
  • Address tabs by stable ID, never by whichever tab happens to be active.
  • Keep browser policy in one shared daemon. MCP is the browser automation surface; the CLI is limited to setup, configuration, and diagnostics.
  • Fail loudly on ambiguity. Return an explicit ambiguity or unsupported-capability error rather than falling back to something that might disturb the browser.
  • Model what you do not know. Use the Observation<T> three-way known/unknown/unsupported from src/browser/model.ts instead of inventing a value. Selected and focused state is observable only when the privileged transport reports the corresponding named capability; otherwise it must remain an Observation of unknown or unsupported.
  • Keep page content out of logs by default — URLs, titles, form values, cookies, and tokens included.

Commands

npm run check          # format:check, lint, typecheck, test, build — the CI gate
npm test               # vitest, no browser required
npm run dev -- --help  # run the CLI from source via tsx
npm run build          # tsc to dist/

npm run check is exactly what CI runs. Run it before opening a pull request.

Read the full file on GitHub · 113 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. 2d ago First seen · 113 lines · 1,276 tokens per session scan A 0b366a96c5c4

Subscribe to this mod's changes

zenAgent AGENTS.md is an instructions file published in the GitHub repository fschrhunt/zenAgent (0 stars, last pushed 23d ago), licensed MIT. It adds 1,276 tokens to every session, about $0.0064 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.

Related

Other instructions, from other repositories

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

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 · 7,104 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 · 5,182 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 · 4,345 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

next.js 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