Borrowing it
Nothing to install: this file belongs to starling-browser/starling. 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/starling-browser/starling/main/CLAUDE.mdgit clone --depth 1 https://github.com/starling-browser/starlingWrote 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/starling-browser/starling/claude-md)<a href="https://agentmods.dev/instructions/starling-browser/starling/claude-md"><img src="https://agentmods.dev/badge/instructions/starling-browser/starling/claude-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/starling-browser/starling/claude-md"><img src="https://agentmods.dev/badge/instructions/starling-browser/starling/claude-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 | $0.00329 | $0.00329 |
| Opus 5.5 | $0.00132 | $0.00132 |
| Sonnet 5.5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
starling CLAUDE.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 2mo 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.
What it actually says
Agent instructions
The repository's agent rules of engagement live in AGENTS.md — read it first.
The C# performance policy is the source of truth in AGENTS.md under "Coding standards — performance policy for C# code". It applies to all code in this repo. Follow it for every change.
Comments and doc comments: Use them sparingly. A comment should explain a decision local to the scope of the code when that decision isn't clear from the code itself. Skip comments that restate what the code already says. Keep them local too — never send the reader three layers up or into another system, and do not narrate a problem you hit (no "fixes the issue where..."). See AGENTS.md under "Coding standards" for the full rule.
Braces: Always use braces for conditionals, loops, and other block statements, even when the body is a single line.
Testing a demo site: when asked to test, verify, or check a demo site (the
fixtures in testdata/sites/...), always load it through the running Aspire
harness at http://localhost:8088/<name>/, never by rendering the files from
disk (file://, a loopback, or an in-process stub). Rendering from disk hides
real serving failures — most notably the sites YARP container not running when
Docker is down. See AGENTS.md under "Getting traces & telemetry from Aspire" for
the rule and the quick checks when a site will not load.
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.
- 2mo ago First seen · 26 lines · 329 tokens per session scan A 682208d27f73
starling CLAUDE.md is an instructions file published in the GitHub repository starling-browser/starling (64 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 329 tokens to every session, about $0.0013 per session on Opus 5.5. 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.
starling CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| starling CLAUDE.mdstarling-browser/starling | Instructions file | 64 | 4mo ago | Apache-2.0 | A | 329 | Claude Code |
| plan-forge dapr.instructions.mdsrnichols/plan-forge | Instructions file | 6 | 2d ago | MIT | A | 4,975 | GitHub Copilot |
| plan-forge database.instructions.mdsrnichols/plan-forge | Instructions file | 6 | 2d ago | MIT | A | 1,890 | GitHub Copilot |
| plan-forge naming.instructions.mdsrnichols/plan-forge | Instructions file | 6 | 2d ago | MIT | A | 1,453 | GitHub Copilot |
| plan-forge caching.instructions.mdsrnichols/plan-forge | Instructions file | 6 | 2d ago | MIT | A | 733 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |