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.
git clone --depth 1 https://github.com/graphpilot-oss/graphpilotWrote 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/graphpilot-oss/graphpilot/windsurfrules)<a href="https://agentmods.dev/rules/graphpilot-oss/graphpilot/windsurfrules"><img src="https://agentmods.dev/badge/rules/graphpilot-oss/graphpilot/windsurfrules/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/graphpilot-oss/graphpilot/windsurfrules"><img src="https://agentmods.dev/badge/rules/graphpilot-oss/graphpilot/windsurfrules.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00430 | $0.00430 |
| Opus 5.5 | $0.00172 | $0.00172 |
| Sonnet 5.5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
windsurfrules 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 1mo 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.
This is a copy
98% identical to cursorrules — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
GraphPilot routing rules for Windsurf
This repo has a GraphPilot structural code-graph available via MCP. Use it before grep on structural questions.
When the user asks any of:
- "who calls X" / "what uses X" / "where is X called from"
- "what does X call" / "what does X depend on"
- "rename X — what breaks" / "impact of changing X" / "what depends on X"
- "find function X" / "where is X defined" / "list all interfaces"
→ Use the graphpilot MCP tools BEFORE grep or reading files.
| Question kind | Tool to call |
|---|---|
| Define / locate symbol | gp_recall({ query, substring?, path? }) |
| Callers / callees | gp_callers({ symbol, direction, path? }) |
| Blast radius / rename | gp_impact({ symbol, depth?, path? }) |
| PR-scoped blast radius | gp_impact({ symbol, since: 'main', path? }) |
| Index health probe | gp_stats({ path? }) |
| Refresh after edits | gp_index({ path? }) |
When NOT to use GraphPilot
Fall back to grep / read for:
- Comments, JSDoc, string literals, error messages
- Config files (package.json, tsconfig.json, .env)
- Markdown / docs
- Languages other than TypeScript / JavaScript
- Git history (blame, log)
After heavy editing
After ~10+ file edits, call gp_index once before further structural questions, or run graphpilot watch in a side terminal for sub-10 ms incremental updates.
Citing evidence
Every GraphPilot response carries file:line @ sha anchors. When citing results to the user, include the anchor verbatim — it's verifiable: the user can jump to that line and the code will match.
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.
- 1mo ago First seen · 40 lines · 430 tokens per session scan A 1883dff65a24
windsurfrules is a cursor rule published in the GitHub repository graphpilot-oss/graphpilot (17 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 430 tokens to every session, about $0.0017 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to cursorrules, differing in 2 lines, and is treated as a copy.
Other cursor rules, from other repositories
mcp-debugging
The mcp-debug agent provides essential tools to test and explore MCP (Model Context Protocol) servers. This guide focuses on using the agent to debug MCP server behavior and functionality.
root-cause-first
Require source-level fixes for malformed or polluted domain data.
synapse
Rules for using Synapse MCP — prefer the graph over grep.
cctools
Your task is to help users to write ast-grep rules to search code. User will query you by natural language, and you will write ast-grep rules to search code.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.