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/firebase/firebase-tools/gemini-mdgit clone --depth 1 https://github.com/firebase/firebase-toolsWhat 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 | $0.00769 | $0.00769 |
| Opus 5 | $0.00385 | $0.00385 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
firebase-tools 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 2d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md
This file provides guidance to Gemini CLI or other coding agents when working with code in this repository. It focuses on key conventions and best practices. For a comprehensive guide on the development setup and contribution process, see CONTRIBUTING.md.
Essential Commands
# Build the project
npm run build
# Link the package - once this is run, you can manually test changes in your terminal
npm link
npm test # Full test suite with linting and compilation
npm run mocha:fast # Quick unit tests only
npx mocha {testfile} # Quick unit test for a specific file
# Linting and formatting
npm run lint # Check all code
npm run lint:changed-files # Lint changed files only (much faster)
npm run format # Auto-fix formatting issues
Best Practices
Code Quality & Utilities
- Look for existing utilities first: Before writing common helper functions (e.g., for logging, file system operations, promises, string manipulation), check
src/utils.tsto see if a suitable function already exists. - Use the central
logger(src/logger.ts); never useconsole.log()for user-facing output. - Throw
FirebaseError(src/error.ts) for expected, user-facing errors. If the error is due to a violation of a precondition (e.g. something that is null but should never be), specify a non-zero exit code. - API calls must use
apiv2.tsfor authenticated requests. - Reduce nesting as much as possible: Code should avoid unnecessarily deep nesting or long periods of nesting. Use early returns,
continue, andbreakstatements in functions and loops to handle edge cases early and keep main logic flat. Consider helper functions to encapsulate complex branching.
TypeScript
- Never use
anyorunknownas an escape hatch. Define proper interfaces/types or use type guards. - Use strict null checks and handle
undefined/nullexplicitly. - Prefer falsy checks over explicit boolean comparisons: Use
!somethinginstead ofsomething === falseunless you explicitly need to distinguish betweenfalseand other falsy values likeundefinedornull.
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.
- 2d ago First seen · 58 lines · 769 tokens per session scan A d4df1cda17ef
firebase-tools GEMINI.md is an instructions file published in the GitHub repository firebase/firebase-tools (4,463 stars, last pushed 3d ago), licensed MIT. It adds 769 tokens to every session, about $0.0038 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.