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.
npx agentmods add instructions/browserbase/stagehand/agents-mdgit clone --depth 1 https://github.com/browserbase/stagehandWhat 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 | $0.00160 | $0.00160 |
| Opus 5 | $0.00080 | $0.00080 |
| Sonnet 5 | $0.00032 | $0.00032 |
| Haiku 4.5 | $0.00016 | $0.00016 |
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.
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 andShave identical trees. Record the child’s current commit, rungit merge --no-edit S^andgit merge --no-edit -s ours S, then usegit diffto confirm that the child’s files did not change and inspectgit diff --merge-base S HEADas the final PR diff before pushing. Stop if either diff contains unexpected 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.
- yesterday First seen · 7 lines · 160 tokens per session scan A 4cdb1c7e1370
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.
Other instructions, from other repositories
fortress AGENTS.md
AGENTS.md instructions for tiliondev/fortress, covering fortress — agent setup guide, ... drive it (section 2) .., 3. persona (optional) — override any fingerprint surface, rules an agent must follow and verify authenticity.
Claude CLAUDE.md
Claude Code instructions for johanolofsson72/Claude, covering claude.md, critical rules (read first), execution mode, autonomous mode (non-interactive) and anti-stall rule.
awesome-ai-apps AGENTS.md
Instructions for Arindam200/awesome-ai-apps, covering agents.md, repository overview, project categories, common development commands and running individual projects.
playwriter AGENTS.md
Instructions for remorses/playwriter, covering backward compatibility, architecture, development, running mcp locally and running cli locally.
graphiti AGENTS.md
Instructions for getzep/graphiti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
autocontext CLAUDE.md
Instructions for greyhaven-ai/autocontext, covering claude.md, project overview, repository layout, commands and setup.