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 rules/myelixlabs/synapse-mcp/synapsegit clone --depth 1 https://github.com/myelixlabs/synapse-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/rules/myelixlabs/synapse-mcp/synapse)<a href="https://agentmods.dev/rules/myelixlabs/synapse-mcp/synapse"><img src="https://agentmods.dev/badge/rules/myelixlabs/synapse-mcp/synapse.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 | $0.00323 | $0.00323 |
| Opus 5 | $0.00161 | $0.00161 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
synapse 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 2d 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.
What it actually says
Synapse MCP — Graph-First Workflow
You have access to Synapse MCP, a persistent AST code-knowledge graph of this codebase. Follow these rules to make the most of it.
Discovery
- Use
ask_synapsefor ALL codebase questions first — before grepping, before reading files. - For "can I delete X?" or "is X still used?", include
inputs.chunk_idorinputs.symbolwith arity. - If
ask_synapsereturnscompletion_state: "tool_call_required", follow the first safenext_tool_callsentry.
Writing Code
- Use
write_safelyfor ALL file modifications. It simulates the edit in memory, verifies callers, and auto-rolls back on failure. - Never use standard file write tools for code edits.
write_safelyexists specifically to prevent broken files.
Debugging
- When pasting a stack trace, use
resolve_stackto map frames to AST chunks and get root-cause analysis. - Use
review_diffbefore committing — it ranks blast radius, broken contracts, and tests to run.
Memory
- Synapse persists summaries across sessions. When you learn something about the codebase, write it to the knowledge cache so future sessions benefit.
Fallback
- Only fall back to shell grep/file reads if Synapse returns no safe route or the task is explicitly non-codebase.
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.
- 2d ago First seen · 29 lines · 323 tokens per session scan A a773c08fb06e
synapse is a cursor rule published in the GitHub repository myelixlabs/synapse-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 323 tokens to every session, about $0.0016 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 cursor rules, from other repositories
cursorrules
Use AGENTS.md as the single authoritative behavior file.
cloud_agent
Sourcebot is a self-hosted tool that helps humans and agents understand your codebase.
style
Sourcebot is a self-hosted tool that helps humans and agents understand your codebase.
codestory
CodeStory local grounding. Use repo evidence before source claims.
rig
Rig MCP usage guide — when to use which tool.
open-kioku
Use when navigating a codebase, searching for symbols, tracing definitions, analyzing change impact, or planning refactors. Requires the repository to be indexed with ok index . first.