beanz-agent

Coding rules for beanz, a Rust project that measures cognitive debt in AI coding sessions. They cover development workflow, naming, communication, public interfaces, and when to run checks or tests.

In plain words
What is it for?
Developing features, fixing bugs, adding tests, and reviewing architecture in the beanz Rust project. They also guide use of Cargo checks and tests and prevent unrequested commits or unrelated refactors.
Why use it?
They set boundaries for making changes and require uncertainty, new dependencies, and unfinished work to be reported clearly. This helps keep changes focused and maintainable.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/daveepope/beanz/beanz-agent
Clone the repo
git clone --depth 1 https://github.com/daveepope/beanz

Made for: Cursor.

Per session 1,286 This file is loaded in full into every session.
When invoked 1,286 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01286 $0.01286
Opus 5 $0.00643 $0.00643
Sonnet 5 $0.00257 $0.00257
Haiku 4.5 $0.00129 $0.00129

Measured 2d ago against content hash 106d65f4128c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

beanz-agent 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.

.cursor/rules/beanz-agent.mdc · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

beanz — agent instructions

General programming workflows

  • beanz is a Rust-only Cargo project (cognitive debt scoring for AI coding sessions). Use idiomatic Rust unless stated otherwise.
  • No drive-by refactors or unrelated files; no new markdown/docs unless the user asks (e.g. READMEs).
  • Use cargo check for fast feedback during iteration; run cargo test (and cargo build --release when relevant) before considering work done.
  • Always report to the developer if you are adding any new third-party crates.
  • Never stray away from the plan set out by the developer.
  • Function as an informative AI coding agent to assist the developer with features, bugs, test coverage, and architecture.
  • Stay within the bounds of the task set out to you.
  • If you are not confident in your answers, say so — honesty is critical.
  • Do not commit unless the developer explicitly asks. Ask first before creating a commit; leave changes for the developer to review and commit when they have not asked.

AI communication

  • Keep replies concise and consistent in tone and structure.
  • Be clear; ask direct questions when something is ambiguous. Do not waffle, hedge with filler, or pad with generic advice.
  • If you are not sure of an answer, say so plainly and work with the developer to close the knowledge gap (what you need checked, what options depend on unknowns, what to read or run next).

Naming conventions (strict)

  • Do not use the words mock, manager, integration test, utility, helper, or sink as substrings in beanz-authored identifiers or API symbols, or in string literals you choose (e.g. not SessionManager, build_helper). Applies to types, functions, methods, fields, locals, modules, and exposed config keys. Prefer neutral names such as setup_*, build_*, with_*, prepare_*.
  • This applies to the entire codebase, not only pub items.

Public API and abstractions

Read the full file on GitHub · 68 lines

Changes

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.

  1. 2d ago First seen · 68 lines · 1,286 tokens per session scan A 106d65f4128c

Subscribe to this mod's changes

beanz-agent is a cursor rule published in the GitHub repository daveepope/beanz (5 stars, last pushed 4d ago), licensed MIT. It adds 1,286 tokens to every session, about $0.0064 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.