Borrowing it
Nothing to install: this file belongs to jeffton/batty. 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/jeffton/batty/main/AGENTS.mdgit clone --depth 1 https://github.com/jeffton/battyWrote 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/jeffton/batty/agents-md)<a href="https://agentmods.dev/instructions/jeffton/batty/agents-md"><img src="https://agentmods.dev/badge/instructions/jeffton/batty/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/jeffton/batty/agents-md"><img src="https://agentmods.dev/badge/instructions/jeffton/batty/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 | $0.00664 | $0.00664 |
| Opus 5.5 | $0.00266 | $0.00266 |
| Sonnet 5.5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade B, and why
batty AGENTS.md scanned grade B with 1 finding 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Install the selected test-only Chromium and WebKit revisions before the full test suite; on Linux run `sudo -n bash scripts/setup-browser-isolation.sh --test` for pinned Chromium and `sudo -n bash scripts/setup-browser-i How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development and deployment
Pull changes before starting work. Preserve concurrent changes.
Before pushing, validate the source:
pnpm check
pnpm test:all
bash scripts/deploy.test.sh
bash scripts/deploy-privileges.test.sh
pnpm build
node scripts/verify-startup.mjs
node scripts/verify-offline.mjs
Run Linux deployment regression checks on Linux. Get an independent review and address findings before pushing. During development, pnpm test runs the non-browser groups; it does not replace the full pre-push gate. On Arch, use pnpm test:all:isolated for that gate: it runs every group with WebKit in the pinned Ubuntu container. pnpm test:webkit runs the browser groups only; see the isolated WebKit setup in docs/operations.md.
Installations deploy validated commits. Deployment installs locked dependencies, builds and verifies service health and the expected build ID; do not rerun source checks, test suites or fixture-based offline tests there. The offline browser gate belongs before push.
Native cloud-browser viewing (H.264 capture/streaming) is intentionally Linux-only. macOS and Windows deployments must not add support, port it, or introduce a fallback unless the user explicitly requests that work. This restriction does not apply to ordinary headless browser tools, which remain cross-platform.
Browser dependency maintenance
Check current stable Patchright and Playwright releases together on every dependency review. Select Playwright Core using Patchright's upstream Playwright release and verify their installed browsers.json revisions agree; package version numbers need not match. Missing release notes or a GitHub release page alone do not justify a hold: inspect upstream commits/PRs, registry publication provenance and published package diffs, and document the actual changes and compatibility. Keep release-age and explicit migration holds. Dated reviews in docs/dependencies.md record past decisions, not ongoing holds. Reassess any hold against current releases rather than carrying it forward.
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.
- today Changed · +1 lines · +73 tokens per session scan A → B eacbc46487cf
- 5d ago Changed · +48 tokens per session 17c5ecda83d4
- 9d ago Changed · +2 lines · +124 tokens per session c6fff29b5045
- 10d ago Changed · +38 tokens per session 6491931eebfa
- 16d ago Changed · +6 lines · +149 tokens per session 3de987cfc63a
- 20d ago Changed · +2 lines · +60 tokens per session 3e1c00f4f09c
- 21d ago Changed · +1 lines · +9 tokens per session f0391d511cb4
- 26d ago Changed · -58 lines · -731 tokens per session bc230ce74505
- 1mo ago Changed · +1 lines · +86 tokens per session a62a1b2bf4a8
- 2mo ago First seen · 77 lines · 808 tokens per session scan A 7ccd343d3597
batty AGENTS.md is an instructions file published in the GitHub repository jeffton/batty (41 stars, last pushed today), licensed MIT. It adds 664 tokens to every session, about $0.0027 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
batty AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| batty AGENTS.mdjeffton/batty | Instructions file | 41 | today | MIT | B | 664 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |