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/alexjsmith0115/synapps/claude-mdgit clone --depth 1 https://github.com/alexjsmith0115/synappsWrote 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/alexjsmith0115/synapps/claude-md)<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>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 | $0.04533 | $0.04533 |
| Opus 5 | $0.02266 | $0.02266 |
| Sonnet 5 | $0.00907 | $0.00907 |
| Haiku 4.5 | $0.00453 | $0.00453 |
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.
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.
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.
- 3d ago First seen · 267 lines · 4,533 tokens per session scan A aaee9efb6ece
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.
Other instructions, from other repositories
agent-lsp CLAUDE.md
Instructions for blackwell-systems/agent-lsp, a project described as: MCP server that orchestrates language servers into agent-native workflows. 65 tools, 30 CI-verified languages.
ariadne AGENTS.md
AGENTS.md instructions for CRJFisher/ariadne, covering guidelines, project layout / intention tree, refactoring ethos, documentation style: canonical and self-contained and scope.
ariadne CLAUDE.md
Claude Code instructions for CRJFisher/ariadne, covering guidelines, goals, project layout / intention tree, refactoring ethos and processing pipeline.
kin GEMINI.md
Gemini CLI instructions for firelock-ai/kin, covering kin: read the repository from the graph, pick the tool by what you know, trust the envelope, not the emptiness, if the tools have no graph and a working order.
kin AGENTS.md
AGENTS.md instructions for firelock-ai/kin, covering agents.md, this repo's role, the inner loop, non-obvious behaviours and landing.
kivgraph AGENTS.md
AGENTS.md instructions for Luqueee/kivgraph, covering instrucciones de desarrollo de kivgraph, mapa de instrucciones, identidad del proyecto, qué pregunta contesta cada tool de kivgraph and la puerta delante de grep.