Borrowing it
Nothing to install: this file belongs to saajunaid/caddis-plugin. 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/saajunaid/caddis-plugin/main/.github/instructions/browser-first.instructions.mdgit clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/browser-first)<a href="https://agentmods.dev/instructions/saajunaid/caddis-plugin/browser-first"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/browser-first/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/saajunaid/caddis-plugin/browser-first"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/browser-first.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 | $0.00520 | $0.00520 |
| Opus 5.5 | $0.00208 | $0.00208 |
| Sonnet 5.5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
caddis-plugin browser-first.instructions.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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser-First Rule for Direct Integrated-Browser Requests
When the user explicitly asks to use the integrated browser or asks for a simple action on an already-open browser page, treat it as a direct browser task.
Trigger examples
- "click this button in the integrated browser"
- "use the already-open browser page"
- "type into this field and tell me what happens"
- "report the visible status text"
- "check what changed on screen"
Mandatory behavior
- Use the native browser tools immediately on the existing page.
- Perform the requested action directly in the browser.
- Report the visible result briefly.
- Stop unless the user asked for more.
What "native browser tools" means
The web capability (VS Code integrated browser tool). Concretely:
- Navigating to a URL
- Clicking elements by selector or label
- Reading visible text / DOM state
- Taking screenshots
- Filling form fields
These are synchronous, in-process actions on the open browser panel. They do NOT include: running Playwright scripts, launching headless Chrome via terminal, or calling any MCP tool.
Do NOT do these first
- Read source files or inspect HTML
- Run
get_errors - Run terminal commands
- Search the workspace
- Load or use Playwright
- Produce a checklist, diagnostic wrapper, or long progress narrative
Fallback rule — explicit Playwright handoff
Only escalate to Playwright or other automation if:
- The
webnative tool is unavailable in your current session - The native tool fails after one retry
- The task requires multi-step automation that native tools cannot perform (e.g. multi-page flow, network interception, cross-origin iframe)
When escalating, load the relevant skill before writing any Playwright code:
Load .github/skills/workflow/playwright/SKILL.md (if it exists) or
Load .github/skills/webapp/webapp-testing/SKILL.md
State clearly in your response that you are falling back because the native web tool failed/is unavailable.
Example
If the user says:
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 First seen · 68 lines · 520 tokens per session scan A 99f1cc608590
caddis-plugin browser-first.instructions.md is an instructions file published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 520 tokens to every session, about $0.0021 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.