agentmods.dev

AI4L: Instructions file for Gemini CLI

GEMINI.md

AI4L GEMINI.md is an instructions file for Gemini CLI from forever-healthy/AI4L. It costs 687 tokens per session, scanned A, a copy of AI4L CLAUDE.md, MIT.

A project instruction file for Gemini CLI, the command-line tool for working with code. It defines project terms, time rules, shared paths, and limits on which files the agent may change.

In plain words
What is it for?
It is for setting project-wide rules, explaining abbreviations, locating shared prompts and temporary files, and controlling file edits.
Why use it?
It keeps the agent's work consistent across sessions and helps prevent changes outside approved folders.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions subagents.

This is forever-healthy/AI4L's own configuration. It tells Gemini CLI how to work on AI4L itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AI4L configures →

not rated 38repo 11d ago A scan 687 tokens copy · 100% MIT
View source ↗ forever-healthy/AI4L forever-healthy.org
Reuse

Borrowing it

Nothing to install: this file belongs to forever-healthy/AI4L. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/forever-healthy/AI4L/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/forever-healthy/AI4L

Made for: Gemini CLI.

Wrote 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.

agentmods badge for AI4L GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/forever-healthy/ai4l/gemini-md.svg)](https://agentmods.dev/instructions/forever-healthy/ai4l/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/forever-healthy/ai4l/gemini-md"><img src="https://agentmods.dev/badge/instructions/forever-healthy/ai4l/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 687 This file is loaded in full into every session.
When invoked 687 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00687 $0.00687
Opus 5 $0.00344 $0.00344
Sonnet 5 $0.00137 $0.00137
Haiku 4.5 $0.00069 $0.00069

Measured 3d ago against content hash 08f4d67117bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

AI4L 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 3d 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.

Origin

This is a copy

100% identical to AI4L CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

GEMINI.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Version 1.3.21 Forever Healthy

Project Instructions

Session related

  • For interactive conversations, follow "prompts/PERSONA.md"

Glossary

  • "ER" stands for evidence review

  • "ER.md" refers to the .md file of an ER

  • "QA" stands for quality assurance audit

  • "QA.md" refers to the .md file of a QA

Timestamps

  • When generating timestamps (for filenames, headers, etc.), always obtain the current date/time by running date in the shell. Never use the model's internal clock, as it may differ from the local timezone.

Globals for Skills and @Agents

  • [ai4l_prompt] = "prompts/AI4L.md"

  • [creation_dir] = "creation/"

  • [tmp_dir] = "creation/tmp/"

  • [trash_dir] = "creation/trash/"

  • [max_audits] = 20

  • [needed_passes] = 1

Hard Rule

  • NEVER modify any files outside of [creation_dir], [tmp_dir], or [trash_dir] without explicit user permission. This includes, but is not limited to, files in the root directory, configuration files, and any other files not in the listed directories.

When Calling @Agents

  • ALWAYS call the @agent exactly as specified in the prompt
  • DO NOT modify the prompts for the @agent or the way to call them; pass the prompt as it is.
  • DO NOT modify the arguments you pass to the @agent; pass them as they are.

MCP Servers

When calling d-pubmed (pubmed_fetch_articles), always pass 'pmids' as a proper JSON array of strings, never as a comma-separated string or single value

When verifying ClinicalTrials.gov URLs, use mcp__d-clinicaltrialsgov__clinicaltrials_get_study_record first. If the NCT ID resolves, that is the verification; only if it does not resolve, fall back to the chain below.

When verifying URLs, use the mcp__d-browser__* tools (browser_navigate + browser_snapshot). If d-browser is blocked or unavailable, fall back to mcp__d-fetch__fetch. If that also fails, fall back to d-proxy-1 and then d-proxy-2 — bot-wall-defeating retrieval tiers; use whichever page-retrieval tool that server offers. Do not use the built-in WebFetch tool.

Read the full file on GitHub · 67 lines

Changes

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.

  1. 3d ago First seen · 67 lines · 687 tokens per session scan A 08f4d67117bb

Subscribe to this mod's changes

AI4L GEMINI.md is an instructions file published in the GitHub repository forever-healthy/AI4L (38 stars, last pushed 11d ago), licensed MIT. It adds 687 tokens to every session, about $0.0034 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to AI4L CLAUDE.md, differing in 0 lines, and is treated as a copy.

Memory and contextevidencehealthlongevitypeptidesrejuvenationtherapeutics
Related

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

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.

github/spec-kit · 7,104 tokens