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/fengkx/beancount-lsp/project-structuregit clone --depth 1 https://github.com/fengkx/beancount-lspWhat 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 | $0.00389 | $0.00389 |
| Opus 5 | $0.00195 | $0.00195 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
project-structure 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 yesterday.
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
Intro: This project is a monorepo managed by pnpm. It is a Language Server Protocol(LSP) implementation of Beancount (A plain text accounting Language).
The project contains two part one lsp-server and lsp-client. server is a Language Server implemented LSP Spec. client is a VSCode Extension which connect to the server.
LSP Server:
In the Language Server, we use web-tree-sitter and tree-sitter-beancount to parse the beancount files. And provide the ability to retrieve symbols from symbol index (defined in packages/lsp-server/src/common/features/symbol-index.ts). It can provide language server features like diagnostic and syntax highlight, code navigateion stuffs(go to definition / references).
All tree-sitter queries are locationed in packages/lsp-server/src/common/language/queries.
LSP features should follow the Feautre interface defined in packages/lsp-server/src/common/features/types.ts like all the existed one inside packages/lsp-server/src/common/features folder.
LSP Client:
Clients communicate with server throgh LSP or JSON RPC with custom messages defined in packages/shared/src/messages.ts. Other than being a LanguageClient, it also provide LLM toolss. Tools interface should fullfiled ToolImpl defined in packages/lsp-client/src/common/llm/tools/tool.ts
Tips:
- things like parsing, calculations work should be done in server side and communicate throght LSP
- Reuse existed parsing and symbol index process when possible. Improve the existed one rather than create a new one
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.
- yesterday First seen · 23 lines · 389 tokens per session scan A 359a1d517b0b
project-structure is a cursor rule published in the GitHub repository fengkx/beancount-lsp (48 stars, last pushed 3d ago), licensed MIT. It adds 389 tokens to every session, about $0.0019 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 2026-09-01.
Other cursor rules, from other repositories
cursorrules
Agent settings configuring version, languages.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.