What is atelier GEMINI.md?

Project-specific instructions for working on the atelier codebase, including its required reading, operating modes, commands, and playbooks.

Use them when starting a session, checking the current project mode, tracking progress, or following workflows such as milestones and architecture reviews.

They tell an AI assistant how much code it may write and which project rules to follow before changing anything.

atelier GEMINI.md — Instructions file for Gemini CLI by ahamedzoha: Project-specific instructions for working on the atelier codebase, inclu

Install

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.

agentmods

npx agentmods add instructions/ahamedzoha/atelier/gemini-md

Clone the repo

git clone --depth 1 https://github.com/ahamedzoha/atelier

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ahamedzoha/atelier/gemini-md.svg)](https://agentmods.dev/instructions/ahamedzoha/atelier/gemini-md)

Your own site

<a href="https://agentmods.dev/instructions/ahamedzoha/atelier/gemini-md"><img src="https://agentmods.dev/badge/instructions/ahamedzoha/atelier/gemini-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 305 This file is loaded in full into every session.

When invoked 305 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5	$0.00305	$0.00305
Opus 5	$0.00152	$0.00152
Sonnet 5	$0.00061	$0.00061
Haiku 4.5	$0.00030	$0.00030

Measured 4d ago against content hash 57a7b8b860b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atelier 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 4d 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.

GEMINI.md · 28 lines

What it actually says

GEMINI.md

This project's full AI contract lives in AGENTS.md. Read it in full and treat it as canonical — this file only orients you.

First thing, every session

Read PROJECT.md.
If its status is UNINITIALIZED, this is a freshly cloned template. Greet the user and run the onboarding interview in docs/playbooks/start.md before anything else.
Otherwise, note the active mode (in PROJECT.md) and obey its rules (AGENTS.md §2), and note the current phase.

The mode is binding

This repo dials how much code you write, from guided (you write none — docs only) through collab to autopilot (you write it all, and teach as you go). Read the current mode from PROJECT.md every session. In guided mode, never edit application source — deliver code as annotated snippets the user types in.

Commands

Repo commands live in .gemini/commands/*.toml and each runs a playbook from docs/playbooks/: /start, /mode, /milestone, /progress, /adr-review. You can also just ask for any of them by name and read the matching playbook file.

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.

4d ago First seen · 28 lines · 305 tokens per session scan A 57a7b8b860b4

Subscribe to this mod's changes

atelier GEMINI.md is an instructions file published in the GitHub repository ahamedzoha/atelier (2 stars, last pushed 2mo ago), licensed MIT. It adds 305 tokens to every session, about $0.0015 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.

agents-md ai-pair-programming claude-code cursor gemini-cli github-copilot

trellis AGENTS.md

Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.

craigcossairt/trellis · 3,686 tokens

trellis CLAUDE.md

Instructions for craigcossairt/trellis, a project described as: The structure a project grows on: a free starter template for AI-assisted development. One AGENTS.md every tool reads (Claude Code, Cursor, Grok Build, Codex, Gemini CLI, Copilot), TDD + bug-fix methodology, secret guardrails, optional local knowledge…

craigcossairt/trellis · 134 tokens

trellis copilot-instructions.md

Instructions for craigcossairt/trellis: Read and follow AGENTS.md at the repository root - it is the canonical instruction file for all AI agents on this project. Full methodology docs live in docs/methodology/: TDD workflow, bug-fix protocol, and session habits. Append bug patterns to docs/common-gotchas.md and…

craigcossairt/trellis · 84 tokens

atelier GEMINI.md