Borrowing it
Nothing to install: this file belongs to invictumhr/ai-invictum-browser-bridge. 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/invictumhr/ai-invictum-browser-bridge/main/AGENTS.mdgit clone --depth 1 https://github.com/invictumhr/ai-invictum-browser-bridgeWrote 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/invictumhr/ai-invictum-browser-bridge/agents-md)<a href="https://agentmods.dev/instructions/invictumhr/ai-invictum-browser-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/invictumhr/ai-invictum-browser-bridge/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/invictumhr/ai-invictum-browser-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/invictumhr/ai-invictum-browser-bridge/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 | $0.01054 | $0.01054 |
| Opus 5 | $0.00527 | $0.00527 |
| Sonnet 5 | $0.00211 | $0.00211 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
ai-invictum-browser-bridge 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 8d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invictum Browser Bridge agent instructions
The phrases use IBB, use IBG, use Invictum Browser Bridge, and
use Invictum Browser Gate all mean the same thing. Croatian equivalents such
as koristi IBB, koristi IBG, koristi Invictum Browser Bridge, and
koristi Invictum Browser Gate are recognized aliases. Read the entire
AGENT_TRIGGER.md before the first browser action.
Before developing, starting, diagnosing, or using the Bridge, read the entire AGENT_USAGE.md.
Read the specialized guide that applies to the task:
- Login, HTTP Basic Auth, and native JavaScript dialogs: AUTH_AND_DIALOGS.md.
- Local file upload: docs/FILE_UPLOAD.md. Use only
browser.set_file_input_files; never attempt to setFileListthrough JavaScript or a coordinate click. - Classic WordPress Appearance > Menus:
docs/WORDPRESS_MENUS.md. Use typed
browser.get_wordpress_menuandbrowser.edit_wordpress_menu; do not reorganize menus with coordinate dragging or raw JavaScript. - WordPress admin list tables, notices, Gutenberg, and Classic Editor: docs/WORDPRESS_ADMIN.md. Prefer typed WordPress actions and authoritative editor models.
- Figma browser design files: docs/FIGMA.md. Run the typed healthcheck first, treat the rendered layer tree as virtualized/partial, and use screenshots for the WebGL canvas.
- Advanced DOM/CSS work, custom widgets, event listeners, event capture, and raw-JavaScript fallback: docs/ADVANCED_BROWSER_TOOLS.md. Always prefer a typed action; raw JavaScript is an explicitly authorized R3 last resort.
- Viewport, element, region, and full-page screenshots plus tutorial annotations: docs/SCREENSHOTS_AND_ANNOTATIONS.md.
- Programmatic console, metadata-only network capture, mobile emulation, advanced gestures, and PDF export: docs/ADVANCED_AGENT_CAPABILITIES.md.
- WHM/cPanel and other xterm-compatible browser terminals: docs/TERMINAL_AUTOMATION.md. Use only the typed terminal actions; buffer reads are R2 and every text/key input is R3. Never retry uncertain terminal input automatically.
- MCP dry runs, idempotency, structured confirmation/elicitation, post-action context, strict stale relocation, conditional batching, and set-of-marks screenshots: docs/MCP_AGENT_ERGONOMICS.md.
- Clean page text, natural-language element discovery, history navigation, same-origin page API calls, and policy-preserving batches: docs/AGENT_PRODUCTIVITY_ACTIONS.md.
AGENT_USAGE.md is authoritative for:
- MCP, CLI, Agent SDK, and local control API usage;
- automatic Bridge startup and recovery;
- Native Messaging connectivity checks;
- runtime capabilities reported by
system.capabilities; - Chrome Site access and restricted pages;
- automatic background-tab behavior and per-tab agent identity;
- the bounded background-first readiness rule: wait 20 seconds, activate once only for a genuinely focus-gated renderer, then restore prior user focus when safe;
- prefilled login, ephemeral HTTP Basic Auth, and native dialogs;
- explicitly authorized local file upload without path leakage in audit logs;
- typed WordPress menu/admin/editor workflows;
- typed Figma document/layer/property inspection and safe selection;
- advanced inspection, event capture, DOM/CSS mutation, and raw-JS fallback;
- metadata-only network diagnostics, synthetic gestures, and PDF export;
- explicitly authorized, bounded browser-terminal detection, readback, trusted input, waits, and recovery;
- screenshots, annotations, and coordinate fallback;
- the required
reserve -> work -> browser.unlock_tablifecycle; - policy, audit, and security boundaries;
- unit, integration, and real-Chrome verification.
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.
- 8d ago First seen · 83 lines · 1,054 tokens per session scan A 4ab3e441d76e
ai-invictum-browser-bridge AGENTS.md is an instructions file published in the GitHub repository invictumhr/ai-invictum-browser-bridge (0 stars, last pushed 12d ago), licensed MIT. It adds 1,054 tokens to every session, about $0.0053 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 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.