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/juanmidev1/synapse-code-mcp/claude-mdgit clone --depth 1 https://github.com/Juanmidev1/synapse-code-mcpWrote 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/juanmidev1/synapse-code-mcp/claude-md)<a href="https://agentmods.dev/instructions/juanmidev1/synapse-code-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/juanmidev1/synapse-code-mcp/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 | $0.01213 | $0.01213 |
| Opus 5 | $0.00607 | $0.00607 |
| Sonnet 5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
synapse-code-mcp 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synapse MCP — Developer Guide
What this project is
Synapse MCP is a TypeScript MCP (Model Context Protocol) server that exposes a local code repository to AI assistants. It runs as a background process communicating over stdio using JSON-RPC. The AI "pulls" context rather than receiving manual file pastes.
Repository layout
src/index.ts— CLI entry point, argument parsing, boots the serversrc/server.ts— Creates the MCP server, registers all 3 toolssrc/tools/— One file per MCP tool (thin handler layer, no business logic)src/core/fs/— File system operations (tree building, ignore resolution, file reading)src/core/search/— Search facade + ripgrep/native adapterssrc/core/analysis/— Dependency graph analysis (ts-morph for TS, regex heuristics for others)src/config/— Config loading, merging, Zod validationsrc/utils/— Logger (pino), path helpers with path-traversal protection, typed errorssrc/types/— Shared TypeScript interfacestests/unit/— Unit tests per moduletests/fixtures/— Minimal fake projects used by integration tests
Essential commands
npm run dev— Run in watch mode (tsx, no compile step needed)npm run build— Compile TypeScript todist/npm test— Run all tests with Vitestnpm run typecheck— Type-check without emittingnpm run lint— ESLint check
Architecture constraints (enforce strictly)
- Tool handlers in
src/tools/MUST NOT contain business logic. They only validate inputs, callcore/modules, and format the MCP response. src/core/modules MUST NOT import fromsrc/tools/orsrc/server.ts.- Config is passed as a parameter, never imported as a global singleton.
pathUtils.resolveAndValidate()must be called before EVERY file system read operation — it throwsPathEscapeErrorif the resolved path escapes the project root (path traversal protection).
Key design decisions
- stdio transport: No HTTP. The MCP client spawns Synapse as a child process. Communication is over stdin/stdout using MCP JSON-RPC framing.
- ripgrep fallback:
searcher.tstriesrgfirst (dramatically faster), falls back to pure-Node regex scan.rgis never a hard dependency. - ts-morph for TS analysis: Wraps the TypeScript compiler API for deep analysis of TypeScript/JavaScript. Only relative imports (
./foo,../bar) are followed in the dependency graph — path aliases (@/components/Foo) are not yet resolved. ignorepackage: The only reliable JS implementation of git's gitignore spec — handles negation patterns, anchored patterns, nested.gitignorefiles.- Depth-limited dependency graph:
maxDependencyDepth(default 2) prevents runaway recursion on large monorepos. - Immutable config: Parsed once at startup, passed as frozen object. No hot-reload in v1.
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 · 80 lines · 1,213 tokens per session scan A 846417287fe9
synapse-code-mcp CLAUDE.md is an instructions file published in the GitHub repository Juanmidev1/synapse-code-mcp (3 stars, last pushed 4d ago), licensed MIT. It adds 1,213 tokens to every session, about $0.0061 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.