agentmods.dev

ubuteco_api: Instructions file for Codex

AGENTS.md

ubuteco_api AGENTS.md is an instructions file for Codex, OpenCode from Sartori-RIA/ubuteco_api. It costs 1,264 tokens per session, scanned A, original, MIT.

Repository instructions for ubuteco_api, a Ruby on Rails API that uses PostgreSQL, Redis, background jobs, search, and real-time communication. They explain which frontend is active and what project documents to read before coding.

In plain words
What is it for?
Use them before implementing API changes, choosing a work plan, checking project-specific guidance, or preparing changes for review.
Why use it?
They help an agent follow the project’s architecture, avoid the abandoned frontend, and use the required planning and branching process.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is Sartori-RIA/ubuteco_api's own configuration. It tells Codex and OpenCode how to work on ubuteco_api 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 ubuteco_api configures →

not rated 10repo changed 3d ago A scan 1,264 tokens original MIT
View source ↗ Sartori-RIA/ubuteco_api
Reuse

Borrowing it

Nothing to install: this file belongs to Sartori-RIA/ubuteco_api. 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/Sartori-RIA/ubuteco_api/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Sartori-RIA/ubuteco_api

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.

agentmods badge for ubuteco_api AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sartori-ria/ubuteco_api/agents-md/github.svg)](https://agentmods.dev/instructions/sartori-ria/ubuteco_api/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sartori-ria/ubuteco_api/agents-md"><img src="https://agentmods.dev/badge/instructions/sartori-ria/ubuteco_api/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.

agentmods 80×15 button for ubuteco_api AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sartori-ria/ubuteco_api/agents-md"><img src="https://agentmods.dev/badge/instructions/sartori-ria/ubuteco_api/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,264 This file is loaded in full into every session.
When invoked 1,264 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01264 $0.01264
Opus 5.5 $0.00506 $0.00506
Sonnet 5.5 $0.00253 $0.00253
Haiku 4.5 $0.00126 $0.00126

Measured 3d ago against content hash e895edfaa915, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ubuteco_api 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.

AGENTS.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — ubuteco_api

Instructions for AI assistants working in this repository.

Also: CLAUDE.md (Claude Code) · .github/copilot-instructions.md (GitHub Copilot) — both point here.

Stack

  • Ruby 4 / Rails 8.1 API-only
  • PostgreSQL, Redis, Sidekiq, Searchkick + OpenSearch, AnyCable
  • Auth: Devise + JWT (allowlisted_jwts)
  • Authorization: CanCanCan
  • Money: money-rails (amounts as cents + ISO currency columns)

Active frontend

ubuteco-react is the only active UI. Angular ubuteco_spa is abandoned — do not port or reference it.

Before you code

  1. Read docs/plans/README.md — pick one plan, check status and dependencies.
  2. Read docs/workflow-plans-and-git.md — small commits, update plan before PR (canonical for all agents; not only Cursor).
  3. Read docs/context/common-ai-pitfalls.md — frequent agent mistakes in this repo.
  4. Small API bugs / polish: docs/backlog/README.md — promote to a plan if scope grows.
  5. Read docs/context/architecture.md for tenant model and request flow.
  6. Read domain context for your plan area — see Key paths.
  7. Read docs/dev-setup.md for ports and local commands.

Branching

  • Implementation (code): one plan = one branch — feature/<plan-slug> (e.g. feature/locale-and-currency). Do not mix unrelated plans on the same branch.
  • Plan docs (docs/plans/, status checkboxes, new plan files): commit directly on master — no feature branch or PR required.
  • Backlog docs (docs/backlog/): commit directly on master when text-only.
  • Other docs-only (context, ADRs, dev-setup): also fine on master, or docs/<topic> if you prefer a short-lived branch.

Plans, commits & PRs

Read docs/workflow-plans-and-git.md before opening a PR.

Read the full file on GitHub · 87 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 Changed · +2 lines · +25 tokens per session e895edfaa915
  2. 2mo ago First seen · 85 lines · 1,239 tokens per session scan A 166a2b0397f9

Subscribe to this mod's changes

ubuteco_api AGENTS.md is an instructions file published in the GitHub repository Sartori-RIA/ubuteco_api (10 stars, last pushed 3d ago), licensed MIT. It adds 1,264 tokens to every session, about $0.0051 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 2026-08-31.

Related

ubuteco_api AGENTS.md compared with instructions from other repositories

ubuteco_api AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ubuteco_api AGENTS.mdSartori-RIA/ubuteco_apiInstructions file103d agoMITA1,264Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode