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/blueprint-master/blueprint-modular/agents-mdgit clone --depth 1 https://github.com/Blueprint-Master/blueprint-modularWrote 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/blueprint-master/blueprint-modular/agents-md)<a href="https://agentmods.dev/instructions/blueprint-master/blueprint-modular/agents-md"><img src="https://agentmods.dev/badge/instructions/blueprint-master/blueprint-modular/agents-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 | $0.04711 | $0.04711 |
| Opus 5 | $0.02355 | $0.02355 |
| Sonnet 5 | $0.00942 | $0.00942 |
| Haiku 4.5 | $0.00471 | $0.00471 |
Grade A, and why
blueprint-modular 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 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.
How it starts
The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Mode d'emploi pour agents autonomes opérant sur Blueprint Maker. Ce document est lu par Cursor Background Agents, GitHub Copilot Agent, Claude Code et tout autre agent LLM contribuant au code. Dernière révision : 19 mai 2026.
0. À lire en premier
Tu es un agent LLM appelé à modifier le code de Blueprint Maker ou de ses satellites. Avant toute action :
- Lis ce fichier en entier.
- Lis
PRINCIPLES.md(principes architecturaux non-négociables). - Lis
CONVENTIONS.md(règles techniques détaillées). - Identifie le repo dans lequel tu opères. Vérifie via :
test -f lib/design/designer-database.json && test -f lib/design/designer-resolver.ts && echo "REPO_OK_MAKER" || echo "CHECK_REPO"
- Si le check retourne
CHECK_REPO, arrête-toi et demande clarification à l'utilisateur avant toute modification.
Tout agent qui modifie du code sans avoir lu ces trois fichiers produit du bruit. La prise en charge d'une tâche commence par cette lecture.
1. Identité du projet
1.1 Ce que c'est
Blueprint Maker est un Process Intelligence Engine. Il transforme une intention en langage naturel en application full-stack déployable. Le pipeline est : NL prompt → LLM → AppSpec JSON → builders TypeScript déterministes → K-15 validation → HTTPS deployment
La promesse Blueprint repose sur la reproductibilité : pour un même AppSpec, la même application est produite. Le LLM intervient en amont pour produire l'AppSpec, puis tout est dérivé de manière déterministe.
1.2 Positionnement stratégique
Blueprint Maker n'est pas un générateur d'apps de plus. C'est une plateforme qui apprend comment les organisations conçoivent et adaptent leurs processus. Concurrents à terme : ServiceNow, SAP Signavio.
L'agent qui intervient sur le code doit garder en tête que chaque modification touche un produit positionné sur un marché entreprise exigeant. Pas de raccourci, pas de hack, pas de "ça marche pour l'instant".
1.3 Ecosystème
| Produit | Rôle | Repo |
|---|---|---|
| Maker | Génération d'apps depuis prompt | blueprint-maker |
| Modular | Bibliothèque UI bpm.* (@blueprint-modular/core) |
blueprint-modular |
| Mirror | Observation des processus déployés | (à venir) |
| Mind | Clustering de patterns | (à venir) |
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.
- 3d ago First seen · 479 lines · 4,711 tokens per session scan A d987ed5e52c2
blueprint-modular AGENTS.md is an instructions file published in the GitHub repository Blueprint-Master/blueprint-modular (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 4,711 tokens to every session, about $0.0236 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.
Other instructions, from other repositories
www-sacred AGENTS.md
Instructions for internet-development/www-sacred, covering agents.md, what this repo is, repo map, conventions and the fonts menu previews.
starwind-ui AGENTS.md
Instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
aicanvas CLAUDE.md
Claude Code instructions for uiNerd16/aicanvas, covering ai canvas — global rules, what this project is, how work is organized, secrets & credentials — this is an open-source repo and tech stack.
animal-island-ui AGENTS.md
AGENTS.md instructions for guokaigdg/animal-island-ui, covering agents.md — working in this repository, read first, by task, verification, content that must be kept in sync and ground rules.
ns-ui AGENTS.md
AGENTS.md instructions for nikolas-sapa/ns-ui, covering agents.md — working inside this repo, structure, autoplay — how a card demonstrates itself, descriptor schema and driver constraints (don't regress these).
animal-island-ui CLAUDE.md
Claude Code instructions for guokaigdg/animal-island-ui, a project described as: Animal Crossing-style React UI component library, inspired by Nintendo's game visuals Vue version available. Animal 风格的 React 组件库 灵感来源于任天堂《集合啦！动物森友会》 Vue 版同步发布.