What is giselle AGENTS.md?

Development guidance for Giselle, a system for designing and running AI workflows, with an emphasis on simple and maintainable code. It also describes the project's tools, architecture, and monorepo layout.

Use it when developing Giselle features, deciding whether a dependency or abstraction is needed, organising packages, validating inputs, or reviewing code for simplicity.

It helps developers avoid unnecessary dependencies, abstractions, dead code, and inconsistent patterns while changing the project.

How giselles-ai/giselle configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to giselles-ai/giselle. 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/giselles-ai/giselle/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/giselles-ai/giselle

Made for: Codex, OpenCode.

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/giselles-ai/giselle/agents-md/github.svg)](https://agentmods.dev/instructions/giselles-ai/giselle/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/giselles-ai/giselle/agents-md"><img src="https://agentmods.dev/badge/instructions/giselles-ai/giselle/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/giselles-ai/giselle/agents-md"><img src="https://agentmods.dev/badge/instructions/giselles-ai/giselle/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,829 This file is loaded in full into every session.

When invoked 2,829 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 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 5.1	$0.02829	$0.02829
Opus 5.5	$0.01132	$0.01132
Sonnet 5.5	$0.00566	$0.00566
Haiku 4.5	$0.00283	$0.00283

Measured 10d ago against content hash 91a03e22a464, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

giselle 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 10d 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

Copies of this mod

1 near-identical copy found in the catalogue:

giselle AGENTS.md — 100% identical, 62 lines differ

AGENTS.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Giselle Development Guide

Development Philosophy

Core Principle: Less is more

Keep every implementation as small and obvious as possible.

Guidelines

Simplicity first – Prefer the simplest data structures and APIs that work
Avoid needless abstractions – Refactor only when duplication hurts
Remove dead code early – pnpm tidy scans for unused files/deps and lets you delete them in one command
Minimize dependencies – Before adding a dependency, ask "Can we do this with what we already have?"
Consistency wins – Follow existing naming and file-layout patterns; if you must diverge, document why
Explicit over implicit – Favor clear, descriptive names and type annotations over clever tricks
Fail fast – Validate inputs, throw early, and surface actionable errors
Let the code speak – If you need a multi-paragraph comment, refactor until intent is obvious

Project Overview

Giselle is built to design and run AI workflows beyond prompt chains. Not a chat. Not a chain. A system you can run.

Key Features:

Visual editor
Instant execution
No infra headaches
Open source — focused on local use and self-hosting

Architecture

Monorepo Structure

Giselle uses a Turborepo monorepo with pnpm workspaces, organized into four main directories:

/workspace
├── apps/                    # Deployable applications
│   ├── studio.giselles.ai/  # Giselle Studio application
│   └── ui.giselles.ai/      # UI component showcase
├── packages/                # Published SDK packages (@giselles-ai/*)
├── internal-packages/       # Internal shared packages (@giselle-internal/*)
└── tools/                   # Development utilities

Package Layers

SDK Packages (packages/@giselles-ai/*):

protocol — Core domain types and schemas (Workspace, Node, Task, Generation)
giselle — Engine implementation (tasks, generations, triggers, integrations)
react — React hooks and components for client integration
nextjs — Next.js integration with route handlers
language-model — Language model abstractions and cost calculations
language-model-registry — Provider-specific model implementations
rag — RAG pipeline (chunking, embedding, querying)
github-tool — GitHub integration utilities

Read the full file on GitHub · 407 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.

10d ago Changed · -7 lines · -37 tokens per session 91a03e22a464
15d ago Changed · -41 lines · -551 tokens per session 322035d3157d
2mo ago First seen · 455 lines · 3,417 tokens per session scan A 2014a82fb07c

Subscribe to this mod's changes

giselle AGENTS.md is an instructions file published in the GitHub repository giselles-ai/giselle (559 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,829 tokens to every session, about $0.0113 per session on Opus 5.5. 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.

agent ai ai-agent genai generative-ai nextjs

giselle AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
giselle AGENTS.mdgiselles-ai/giselle	Instructions file	559	3d ago	Apache-2.0	A	2,829	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

giselle: Instructions file for Codex