Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/marcodiniz/ag-local-bridge/gemini-mdgit clone --depth 1 https://github.com/marcodiniz/ag-local-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/marcodiniz/ag-local-bridge/gemini-md)<a href="https://agentmods.dev/instructions/marcodiniz/ag-local-bridge/gemini-md"><img src="https://agentmods.dev/badge/instructions/marcodiniz/ag-local-bridge/gemini-md.svg" alt="Measured on agentmods" 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 | $0.04236 | $0.04236 |
| Opus 5 | $0.02118 | $0.02118 |
| Sonnet 5 | $0.00847 | $0.00847 |
| Haiku 4.5 | $0.00424 | $0.00424 |
Grade A, and why
ag-local-bridge GEMINI.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 yesterday.
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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-local-bridge — AI Agent Instructions
This file is loaded automatically by AI coding assistants (Gemini, Claude, Cursor, etc.) and defines the conventions that must be followed when making changes to this project.
Critical: Before Every Commit
Always run all three checks in order before staging any changes:
npm run format # 1. Auto-fix formatting (Prettier)
npm run lint # 2. Check for lint errors (ESLint)
npm test # 3. Run all tests (node:test)
Or as a single pipeline:
npm run format && npm run lint && npm test
Never skip formatting. The CI runs
format:checkand will fail if files aren't formatted.npm run formatis non-destructive and safe to run at any time.
All Available Scripts
| Command | What it does |
|---|---|
npm test |
Run all tests with Node's built-in test runner |
npm run lint |
ESLint over src/ and test/ |
npm run lint:fix |
ESLint with auto-fix |
npm run format |
Prettier write (auto-fixes all files) |
npm run format:check |
Prettier check only (what CI runs) |
npm run dev:deploy |
Deploy source to local Antigravity extension (Windows/PowerShell) |
Code Style
Enforced by Prettier (.prettierrc) and ESLint (eslint.config.js).
Key rules:
- Single quotes, trailing commas, semicolons
- 2-space indent, 120-char print width, LF line endings
no-unused-vars→ warn (prefix with_to suppress:_unused)eqeqeq→ error (always use===)- All files must be
'use strict';at the top
Unused imports in new files will produce lint warnings — remove them before committing.
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.
- yesterday Changed · +9 lines · +375 tokens per session f03cc2a99e38
- 5d ago First seen · 281 lines · 3,861 tokens per session scan A 845339fbd27c
ag-local-bridge GEMINI.md is an instructions file published in the GitHub repository marcodiniz/ag-local-bridge (49 stars, last pushed yesterday), licensed MIT. It adds 4,236 tokens to every session, about $0.0212 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 2026-08-30.
Other instructions, from other repositories
CLIProxyAPI AGENTS.md
AGENTS.md instructions for router-for-me/CLIProxyAPI, covering agents.md, repository, commands, config and architecture.
antigravity-claude-proxy CLAUDE.md
Instructions for badrisnarayanan/antigravity-claude-proxy, covering claude.md, commands and non-obvious things.
ClaudeBar CLAUDE.md
Claude Code instructions for tddworks/ClaudeBar, covering claude.md, project overview, build & test commands, quick start and install tuist (if not installed).
imagine-mcp AGENTS.md
AGENTS.md instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.
antigravity-companion AGENTS.md
Instructions for matasarei/antigravity-companion, covering agents.md, what this is, repository layout, core principles and where to make common changes.
antigravity-cloud-run AGENTS.md
Instructions for ykdojo/antigravity-cloud-run, covering antigravity on cloud run, testing end to end, multiple sessions, mounting local projects and research sessions.