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/andersonlemesc/oryntra/agents-mdgit clone --depth 1 https://github.com/andersonlemesc/OryntraWrote 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/andersonlemesc/oryntra/agents-md)<a href="https://agentmods.dev/instructions/andersonlemesc/oryntra/agents-md"><img src="https://agentmods.dev/badge/instructions/andersonlemesc/oryntra/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 | $0.03696 | $0.03696 |
| Opus 5 | $0.01848 | $0.01848 |
| Sonnet 5 | $0.00739 | $0.00739 |
| Haiku 4.5 | $0.00370 | $0.00370 |
Grade A, and why
Oryntra 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 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.
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Regras de projeto pra agentes de IA (Claude Code, Cursor, Copilot). Leitura obrigatória antes de qualquer tarefa.
Produto
Oryntra — plataforma open-source de agentes LLM pra Chatwoot. Painel Laravel/Filament + runtime Python/LangGraph. Multi-tenant via workspace_id. Detalhes completos em README.md.
Stack fixada
- Laravel 13 + PHP 8.3
- Filament 3 (admin painel + multi-tenancy)
- Fortify (auth: 2FA, recovery codes, password confirmation)
- Shield (roles/permissions Filament)
- Horizon + Redis (queues)
- Reverb (WebSocket real-time)
- Pail + Telescope (observabilidade dev)
- Spatie ActivityLog (audit)
- Pest (testes Laravel)
- Pint + Larastan level 8 + Rector (code quality)
- Postgres + pgvector (banco + embeddings)
- MinIO (S3-compatible storage)
- Python 3.12 + FastAPI + LangGraph (runtime de agente, privado)
- uv (gerenciador Python), ruff + mypy (Python quality), pytest
- Docker Compose (dev e prod)
Estrutura do monorepo
/ # raiz: docs, docker, configs
├── laravel/ # app Laravel
├── agent-python/ # serviço Python privado
├── docker/ # Dockerfiles e configs
├── docs/ # docs, ADRs, runbooks, OpenAPI
└── .github/ # CI workflows
Comandos comuns
docker compose up -d # subir stack
docker compose exec laravel-app php artisan migrate
docker compose exec laravel-app php artisan make:filament-user
docker compose exec laravel-app php artisan pail # tail logs
docker compose exec laravel-app ./vendor/bin/pest
docker compose exec laravel-app ./vendor/bin/pint
docker compose exec laravel-app ./vendor/bin/phpstan analyse
docker compose exec agent-python pytest
docker compose exec agent-python ruff check .
docker compose exec agent-python mypy src/
Regras de arquitetura (críticas)
- Python nunca exposto publicamente. Acessível só pela rede interna Docker via
http://agent-python:8000. Toda chamada exige headerX-Internal-Token. workspace_idem toda query de negócio. Sem exceção. Tabela semworkspace_id= bug de tenancy.- Tokens criptografados. API tokens Chatwoot, chaves LLM, recovery codes — sempre cast
encrypted. - Idempotência por
chatwoot_message_id. Webhooks repetidos não geram resposta duplicada. - Lock por
conversation_id. Duas respostas simultâneas pra mesma conversa = bug. - Embeddings só no Python. Laravel nunca chama API de embedding direto.
- BYOK (Bring Your Own Key). Workspace cadastra própria chave OpenAI/Anthropic/Gemini. Plataforma não cobra LLM.
thread_iddo LangGraph composto:workspace:{ws_id}:account:{account_id}:conversation:{conv_id}.
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 · 319 lines · 3,696 tokens per session scan A 79322cbfd2f6
Oryntra AGENTS.md is an instructions file published in the GitHub repository andersonlemesc/Oryntra (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,696 tokens to every session, about $0.0185 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
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).
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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.