Borrowing it
Nothing to install: this file belongs to duckduckgo/apple-browsers. 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/duckduckgo/apple-browsers/main/AGENTS.mdgit clone --depth 1 https://github.com/duckduckgo/apple-browsersWrote 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/duckduckgo/apple-browsers/agents-md)<a href="https://agentmods.dev/instructions/duckduckgo/apple-browsers/agents-md"><img src="https://agentmods.dev/badge/instructions/duckduckgo/apple-browsers/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/duckduckgo/apple-browsers/agents-md"><img src="https://agentmods.dev/badge/instructions/duckduckgo/apple-browsers/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 | $0.00309 | $0.00309 |
| Opus 5.5 | $0.00124 | $0.00124 |
| Sonnet 5.5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
apple-browsers 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 1mo 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
DuckDuckGo Apple browsers
Loaded into every agent session. Add a line only when agents demonstrably get
something wrong and nothing catches it during the task. Procedures live in
.claude/skills/; personal preferences live in your user-level config.
- Before finishing, run
mint run swiftlint lint --strict --force-excludeon the files you changed. CI uses--strict, so any warning, including the file-header check, fails the PR;--force-excludeskips files CI doesn't lint, such asPackage.swift. - Every new Swift Testing
@Testneeds.timeLimit(.minutes(1)), which requires@available(iOS 16, macOS 13, *). - Adding, moving or deleting files in the Xcode projects: use the
ddg-xcode-add-fileskill. - Adding or changing a pixel or wide event: use the
ddg-add-pixelskill. - Tests that depend on the remote Privacy Configuration arrange each flag state explicitly and assert the app's behavior in that state, including flags changing while the app runs. They never assert what the live configuration currently contains.
- Pull requests: fill in
.github/PULL_REQUEST_TEMPLATE.md. If theSnapshotReferencessubmodule changed, run./scripts/open-snapshot-submodule-pr.shfirst and add the PR link it prints to the description.
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.
- 1mo ago Changed · -9 lines · -140 tokens per session 40e0039c919e
- 2mo ago Changed · +6 lines · +101 tokens per session 1f1cae9e9454
- 2mo ago First seen · 27 lines · 348 tokens per session scan A 46989f204620
apple-browsers AGENTS.md is an instructions file published in the GitHub repository duckduckgo/apple-browsers (270 stars, last pushed today), licensed Apache-2.0. It adds 309 tokens to every session, about $0.0012 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 2026-09-01.
apple-browsers AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apple-browsers AGENTS.mdduckduckgo/apple-browsers | Instructions file | 270 | today | Apache-2.0 | A | 309 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | 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 | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |