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/destrayon/connapse/claude-mdgit clone --depth 1 https://github.com/Destrayon/ConnapseWrote 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/destrayon/connapse/claude-md)<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>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 | $0.01834 | $0.01834 |
| Opus 5 | $0.00917 | $0.00917 |
| Sonnet 5 | $0.00367 | $0.00367 |
| Haiku 4.5 | $0.00183 | $0.00183 |
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.
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.StorageConnapseIdentityDbContext(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)
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 · 168 lines · 1,834 tokens per session scan A 26744894599e
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.
Other instructions, from other repositories
BlazorBindings.Maui AGENTS.md
AGENTS.md instructions for Dreamescaper/BlazorBindings.Maui, covering mobile guidelines, platform, razor and component conventions and blazor bindings generation.
coco-search CLAUDE.md
Claude Code instructions for VioletCranberry/coco-search, covering project instructions, project overview, tool routing (mandatory), development setup and prerequisites: docker, uv (python package manager).
ClawMem CLAUDE.md
Instructions for yoloshii/ClawMem: Claude Code reads CLAUDE.md natively (not AGENTS.md), so this file imports the root SSOT.
grove CLAUDE.md
Claude Code instructions for jmilinovich/grove, covering grove, architecture rules, running locally, code conventions and what not to do.
OpenNotebookLM AGENTS.md
AGENTS.md instructions for tom1030507/OpenNotebookLM, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
data-olympus AGENTS.md
Instructions for knaisoma/data-olympus, covering data olympus, project overview, architecture, development workflow and code standards.