synapps CLAUDE.md

synapps CLAUDE.md is an instructions file for coding agents from alexjsmith0115/synapps. It costs 4,533 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude Code, an AI coding assistant, covering the project’s commands, tests, design rules, and software setup.

In plain words
What is it for?
Use it when working on the synapps project, including running unit or integration tests and handling bug fixes.
Why use it?
It gives the coding assistant project-specific guidance so it can verify changes and follow the repository’s conventions.

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/alexjsmith0115/synapps/claude-md
Clone the repo
git clone --depth 1 https://github.com/alexjsmith0115/synapps

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 synapps CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alexjsmith0115/synapps/claude-md.svg)](https://agentmods.dev/instructions/alexjsmith0115/synapps/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alexjsmith0115/synapps/claude-md"><img src="https://agentmods.dev/badge/instructions/alexjsmith0115/synapps/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,533 This file is loaded in full into every session.
When invoked 4,533 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 $0.04533 $0.04533
Opus 5 $0.02266 $0.02266
Sonnet 5 $0.00907 $0.00907
Haiku 4.5 $0.00453 $0.00453

Measured 3d ago against content hash aaee9efb6ece, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

synapps 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 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.

CLAUDE.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT

  • Never assume the user is correct. Trust but verify all statements, using the code as a source of truth. When in doubt, ask the user for clarification.
  • Design all classes and functions with testability in mind. Use Dependency Injection liberally.
  • Keep classes and functions small, clear, and with a singular purpose (SRP).
  • Use comments sparingly. Comments should only exist to clarify a design choice/decision, not to explain what the code is doing. (WHY not WHAT)
  • Make sure all unit and integration tests pass before considering a task complete.
  • Every bugfix must include a regression test that would have caught the bug.

Common Commands

# Activate venv (always required before running Python commands)
source .venv/bin/activate

# Unit tests (no external dependencies, ~1.7s)
pytest tests/unit/ -v

# Integration tests (requires Memgraph on localhost:7687 and .NET SDK)
docker compose up -d  # start Memgraph + Memgraph Lab (Lab UI at http://localhost:3000; in-memory — data lost on restart, tests always re-index from scratch)
pytest tests/integration/test_mcp_tools.py -v -m integration      # MCP tool integration(C#) tests
pytest tests/integration/test_mcp_tools_typescript.py -v -m integration # Typescript integration tests (MCP)
pytest tests/integration/test_mcp_tools_python.py -v -m integration # Python integration tests (MCP)

pytest tests/integration/test_cli_commands.py -v -m integration   # CLI command integration tests
pytest tests/integration/test_cli_commands_python.py -v -m integration   # Python CLI command integration tests
pytest tests/integration/test_cli_commands_typescript.py -v -m integration   # typescript CLI command integration tests

Project

Synapps

Synapps is a code intelligence MCP server that indexes multi-language codebases (C#, TypeScript, Python, Java) using tree-sitter and Language Server Protocol, stores symbols and relationships in a Memgraph graph database, and exposes semantic query tools (find callers, trace call chains, analyze change impact) for AI coding agents and developers via both MCP and CLI.

Read the full file on GitHub · 267 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 First seen · 267 lines · 4,533 tokens per session scan A aaee9efb6ece

Subscribe to this mod's changes

synapps CLAUDE.md is an instructions file published in the GitHub repository alexjsmith0115/synapps (1 stars, last pushed 4mo ago), licensed MIT. It adds 4,533 tokens to every session, about $0.0227 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.