stagehand AGENTS.md

Repository instructions for browser automation projects, including rules for handling stacked pull requests. A stacked pull request is built on another pull request, so changes must be merged in the right order.

In plain words
What is it for?
Use it when updating stacked pull requests, merging a parent into its child, resolving related conflicts and checking that the resulting file trees and diffs are expected.
Why use it?
It prevents parent and child pull requests from drifting apart after a parent is merged. The rules also require checking that the child still contains the correct final files before it is pushed.

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/browserbase/stagehand/agents-md
Clone the repo
git clone --depth 1 https://github.com/browserbase/stagehand

Made for: Codex, OpenCode.

Per session 160 This file is loaded in full into every session.
When invoked 160 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 $0.00160 $0.00160
Opus 5 $0.00080 $0.00080
Sonnet 5 $0.00032 $0.00032
Haiku 4.5 $0.00016 $0.00016

Measured yesterday against content hash 4cdb1c7e1370, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stagehand 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 yesterday.

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 · 7 lines

What it actually says

  • For stacked PRs, target each PR at its immediate predecessor; when a parent changes, merge it into its immediate child and resolve conflicts normally.
  • After a parent is squash-merged as S, ensure its child contains the parent’s final tip and verify that tip and S have identical trees. Record the child’s current commit, run git merge --no-edit S^ and git merge --no-edit -s ours S, then use git diff to confirm that the child’s files did not change and inspect git diff --merge-base S HEAD as the final PR diff before pushing. Stop if either diff contains unexpected changes.
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. yesterday First seen · 7 lines · 160 tokens per session scan A 4cdb1c7e1370

Subscribe to this mod's changes

stagehand AGENTS.md is an instructions file published in the GitHub repository browserbase/stagehand (24,098 stars, last pushed yesterday), licensed MIT. It adds 160 tokens to every session, about $0.0008 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.