project

A short description of mini-SWE-agent, an AI software engineering agent that solves GitHub issues and similar programming tasks. It outlines the project’s main folders and its use of interchangeable components.

In plain words
What is it for?
Use it as a high-level reference for locating agents, execution environments, model interfaces, and run scripts. It also explains that each use case selects an agent, environment, and model.
Why use it?
It gives newcomers a quick orientation to the repository before they work in it. This reduces the need to infer the project structure from scattered files.

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/benchflow-ai/agents/project
Clone the repo
git clone --depth 1 https://github.com/benchflow-ai/agents

Made for: Cursor.

Per session 175 This file is loaded in full into every session.
When invoked 175 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00175 $0.00175
Opus 5 $0.00088 $0.00088
Sonnet 5 $0.00035 $0.00035
Haiku 4.5 $0.00017 $0.00017

Measured yesterday against content hash fa161efe6593, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project 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.

Origin

This is a copy

100% identical to project — 0 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.

acp/mini-swe-code/.cursor/rules/project.mdc · 22 lines

What it actually says

mini-SWE-agent overview

  • mini-SWE-agent implements an AI software engineering agent that solves github issues and similar programming challenges
  • The idea of this project is to write the simplest, smallest, most readable agent.

The project is structured as

minisweagent/__init__  # Protocols/interfaces for all base classes
minisweagent/agents  # Agent control flow & loop
minisweagent/environments  # Executing agent actions
minisweagent/models  # LM interfaces
minisweagent/run  # Run scripts that serve as an entry point
  • The project embraces polymorphism: Every individual class should be simple, but we offer alternatives
  • Every use case should start with a run script, that picks one agent, environment, and model class to run
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. yesterday First seen · 22 lines · 175 tokens per session scan A fa161efe6593

Subscribe to this mod's changes

project is a cursor rule published in the GitHub repository benchflow-ai/agents (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 175 tokens to every session, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to project, differing in 0 lines, and is treated as a copy.