What is openarg_backend CLAUDE.md?

Project instructions for an OpenArg backend, a service that collects Argentine government data and answers questions about it. They describe its software stack, hexagonal architecture, background workers, and resilience rules.

Use them when modifying the API, database, data-scraping and embedding pipeline, Celery background jobs, authentication, configuration, or error handling.

They give coding agents the project context needed to change the backend without breaking its layers, data pipeline, or worker processing.

How colossus-lab/openarg_backend configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to colossus-lab/openarg_backend. 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/colossus-lab/openarg_backend/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/colossus-lab/openarg_backend

Made for: Claude Code.

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/colossus-lab/openarg_backend/claude-md/github.svg)](https://agentmods.dev/instructions/colossus-lab/openarg_backend/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/colossus-lab/openarg_backend/claude-md"><img src="https://agentmods.dev/badge/instructions/colossus-lab/openarg_backend/claude-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/colossus-lab/openarg_backend/claude-md"><img src="https://agentmods.dev/badge/instructions/colossus-lab/openarg_backend/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,787 This file is loaded in full into every session.

When invoked 5,787 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	$0.05787	$0.05787
Opus 5.5	$0.02315	$0.02315
Sonnet 5.5	$0.01157	$0.01157
Haiku 4.5	$0.00579	$0.00579

Measured 29d ago against content hash d8d80c182f41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openarg_backend CLAUDE.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 29d 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.

CLAUDE.md · 343 lines

How it starts

The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenArg Backend

Backend service for OpenArg — AI-powered analysis of Argentine government open data. It scrapes public data portals into PostgreSQL, embeds the catalogue, keeps curated marts and live connectors, and answers natural-language questions for the web chat (/api/v1/query/*), the public API (/api/v1/ask) and the public MCP (mcp_publico/, mcp.openarg.org). See README.md for the full picture.

Stack

Framework: FastAPI 0.115 + Uvicorn (async, UVLoop)
Database: PostgreSQL 16 + pgvector (HNSW indexing, 1024-dim embeddings) + PostGIS (migration 0025)
ORM: SQLAlchemy 2.0 (async) + Alembic migrations
DI: Dishka 1.6 (IoC container)
Workers: Celery 5.4 + Redis 7 (broker + cache + results)
Answer engines (chosen per turn with ANSWERS_ENGINE, code default legacy; application/answers/engine.py):
- agent: Claude Sonnet 4.6 on AWS Bedrock (BEDROCK_AGENT_MODEL) in a tool loop, through the Anthropic SDK (AsyncAnthropicBedrock). The agent has answered in prod since 2026-10-03.
- legacy: the LangGraph graph on Claude Haiku 4.5 on Bedrock (BEDROCK_LLM_MODEL) with Google Gemini (GEMINI_MODEL, default 2.5 Flash) as fallback. Haiku 4.5 is also the default model of the workers' LLM tasks.
Figure verifier: ANSWERS_VERIFY_MODE = off / shadow (default) / correct (application/answers/verification.py)
Embeddings: AWS Bedrock Cohere Embed Multilingual v3 (1024-dim)
AWS credentials: boto3's default chain (instance role on the servers); no keys required in .env
HTTP: HTTPX (async client)
Auth: shared service key (X-API-Key) + Google ID token for the frontend; oarg_sk_ user keys (Bearer) for the public API/MCP; X-Admin-Key for /admin
Rate Limiting: SlowAPI + Redis counters (monthly quotas in application/public_quota.py and application/web_quota.py)
Config: TOML files + Pydantic settings
Logging: structlog

Architecture (Hexagonal / Ports & Adapters)

Read the full file on GitHub · 343 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.

29d ago Changed · +74 lines · +2,150 tokens per session d8d80c182f41
2mo ago First seen · 269 lines · 3,637 tokens per session scan A d679bebba94f

Subscribe to this mod's changes

openarg_backend CLAUDE.md is an instructions file published in the GitHub repository colossus-lab/openarg_backend (150 stars, last pushed 3d ago), licensed MIT. It adds 5,787 tokens to every session, about $0.0231 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.

Backend and APIs

openarg_backend CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
openarg_backend CLAUDE.mdcolossus-lab/openarg_backend	Instructions file	150	3d ago	MIT	A	5,787	Claude Code
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

openarg_backend: Instructions file for Claude Code