Connapse CLAUDE.md

Connapse CLAUDE.md is an instructions file for coding agents from Destrayon/Connapse. It costs 1,834 tokens per session, scanned A, original, MIT.

A project guide for Connapse, a .NET web application that uses PostgreSQL for data and MinIO for object storage. It documents build, run, Docker, and test commands.

In plain words
What is it for?
Building the application, running it locally or with Docker, starting PostgreSQL and MinIO, and selecting particular tests or test categories.
Why use it?
It shows developers how to start the required services and how to run unit and integration tests in the expected way.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/destrayon/connapse/claude-md
Clone the repo
git clone --depth 1 https://github.com/Destrayon/Connapse

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 Connapse CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/destrayon/connapse/claude-md.svg)](https://agentmods.dev/instructions/destrayon/connapse/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/destrayon/connapse/claude-md"><img src="https://agentmods.dev/badge/instructions/destrayon/connapse/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,834 This file is loaded in full into every session.
When invoked 1,834 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01834 $0.01834
Opus 5 $0.00917 $0.00917
Sonnet 5 $0.00367 $0.00367
Haiku 4.5 $0.00183 $0.00183

Measured 4d ago against content hash 26744894599e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Connapse 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 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.

CLAUDE.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build & Run

# Build
dotnet build

# Run web app (requires backing services)
dotnet run --project src/Connapse.Web

# Start backing services (PostgreSQL + MinIO, ports exposed to host)
docker compose -f docker-compose.yml -f docker-compose.dev.yml up -d

# Full stack via Docker
docker compose up -d

Tests

# All tests
dotnet test

# Unit tests only (no Docker required)
dotnet test --filter "Category=Unit"

# Integration tests (needs Docker for Testcontainers)
dotnet test --filter "Category=Integration"

# Single test class
dotnet test --filter "FullyQualifiedName~Connapse.Core.Tests.CloudScope.CloudScopeServiceTests"

# Single test method
dotnet test --filter "FullyQualifiedName~ClassName.MethodName_Scenario_ExpectedResult"
  • xUnit framework, FluentAssertions (.Should()), NSubstitute for mocking
  • Integration tests share a single PostgreSQL+MinIO container pair via SharedWebAppFixture (collection-based)
  • Tag tests: [Trait("Category", "Unit")] or [Trait("Category", "Integration")]
  • Test naming: MethodName_Scenario_ExpectedResult

Database Migrations

Two separate EF Core migration histories:

  • KnowledgeDbContext (Storage): dotnet ef migrations add Name --project src/Connapse.Storage
  • ConnapseIdentityDbContext (Identity): dotnet ef migrations add Name --project src/Connapse.Identity

Migrations run automatically on app startup.

Architecture

Connapse.Web          (Blazor Server + Minimal API endpoints + MCP server)
├── Connapse.Identity (Auth: OAuth 2.1/JWT/PAT/cookie, cloud identity, audit)
├── Connapse.Ingestion(Parsers, chunking strategies, background worker)
├── Connapse.Search   (Vector, keyword, hybrid search + reranking)
├── Connapse.Storage  (PostgreSQL/pgvector, EF Core, connectors, embedding/LLM providers)
├── Connapse.Agents   (Agent orchestration)
└── Connapse.Core     (Domain models, interfaces, settings records — zero dependencies)

Read the full file on GitHub · 168 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. 4d ago First seen · 168 lines · 1,834 tokens per session scan A 26744894599e

Subscribe to this mod's changes

Connapse CLAUDE.md is an instructions file published in the GitHub repository Destrayon/Connapse (16 stars, last pushed today), licensed MIT. It adds 1,834 tokens to every session, about $0.0092 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 2026-08-30.