What is saga-core CLAUDE.md?

Project instructions for AI coding agents working on SAGA, a backend that imports documents, extracts information, indexes them for search, and exposes APIs and an MCP server.

They are for guiding changes in the SAGA repository, including typed Python development, tests, document ingestion, search, APIs, workers, and infrastructure.

They give an agent the project's structure, technologies, commands, and coding expectations before it changes code.

How mlauf-labs/saga-core configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mlauf-labs/saga-core. 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/mlauf-labs/saga-core/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mlauf-labs/saga-core

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/mlauf-labs/saga-core/claude-md.svg)](https://agentmods.dev/instructions/mlauf-labs/saga-core/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mlauf-labs/saga-core/claude-md"><img src="https://agentmods.dev/badge/instructions/mlauf-labs/saga-core/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,528 This file is loaded in full into every session.

When invoked 1,528 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	$0.01528	$0.01528
Opus 5	$0.00764	$0.00764
Sonnet 5	$0.00306	$0.00306
Haiku 4.5	$0.00153	$0.00153

Measured 8d ago against content hash cb81467e0e6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

saga-core 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 8d 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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude / AI coding agents working in SAGA (Self-organizing Archive for Generative Agents) — the core backend. Read this before making any change. Keep changes small, focused, typed, tested, and consistent with the conventions below.

Project overview

SAGA ingests documents, converts them to Markdown (Docling/Kreuzberg over HTTP), enriches them with LLM-extracted metadata, indexes them in OpenSearch (a keyword document index

a vector index of chunks), stores originals in MinIO, keeps Postgres as the system of record, and serves hybrid search to agents via an MCP server and a REST API. Ingestion runs asynchronously on an ARQ worker. See docs/requirements/.

Tech stack & requirements

Python 3.12+, fully typed (uv run mypy strict must pass).
FastAPI (REST) · ARQ (async worker) · MCP server.
Infra: PostgreSQL · MinIO · OpenSearch · Redis · Docling/Kreuzberg · Ollama/OpenAI/Azure.
uv for dependency & env management. Depends on the saidex structured-output library (PyPI).

Repository layout

src/saga/
  core/         config, logging, errors, domain models
  api/          FastAPI app, auth, routes
  mcp/          MCP server + tools
  pipeline/     ARQ worker tasks: convert → analyse → chunk → embed → index
  converters/   Docling/Kreuzberg clients + routing
  llm/          LLM provider adapters + prompt loader
  embeddings/   embedding provider adapters
  storage/      OpenSearch + MinIO adapters
  chunking/     markdown + token splitter
config/         YAML config (config, converters, providers, logging)
prompts/        LLM prompts + MCP tool descriptions (Markdown)
docs/           requirements, architecture, planning
tests/          unit tests (mirror the src layout)
docker/         Dockerfile

Common commands

uv sync                       # install deps
uv run ruff check . --fix     # lint + autofix
uv run ruff format .          # format
uv run mypy                   # strict type check
uv run pytest                 # tests
docker compose up -d          # full stack

uv run saga-api               # REST API on :8000
uv run saga-worker            # ARQ worker
uv run saga-mcp               # MCP server on :8100

Read the full file on GitHub · 134 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.

8d ago First seen · 134 lines · 1,528 tokens per session scan A cb81467e0e6e

Subscribe to this mod's changes

saga-core CLAUDE.md is an instructions file published in the GitHub repository mlauf-labs/saga-core (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,528 tokens to every session, about $0.0076 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

saga-core: Instructions file for Claude Code