specify-rules

A set of automatically generated development rules for the Busibox project, a local language-model platform. It records the technologies and project guidelines gathered from existing feature plans.

In plain words
What is it for?
Use it when implementing Busibox features that depend on its listed Python, database, storage, queue, networking, or agent-management tools.
Why use it?
It gives coding agents a shared reference for the project's technology choices and development expectations.

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/jazzmind/busibox/specify-rules
Clone the repo
git clone --depth 1 https://github.com/jazzmind/busibox

Made for: Cursor.

Per session 608 This file is loaded in full into every session.
When invoked 608 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 $0.00608 $0.00608
Opus 5 $0.00304 $0.00304
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 2d ago against content hash 702d84f53714, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specify-rules 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/specify-rules.mdc · 34 lines

What it actually says

busibox Development Guidelines

Auto-generated from all feature plans. Last updated: 2025-10-14

Active Technologies

  • (001-create-an-initial)
  • Bash 5.x (scripts), Ansible 2.14+ (configuration management), NGINX 1.18+ (reverse proxy) (002-deploy-app-servers)
  • Python 3.11+ + FastAPI 0.104+, pymilvus 2.6+ (BM25 function support), redis-py 5.0+, boto3 (MinIO S3), psycopg 3.1+ (PostgreSQL async) (004-updated-data-service)
  • PostgreSQL 15+ (metadata, status), Milvus 2.6+ (vectors with BM25), MinIO (S3-compatible file storage), Redis 7.0+ (Streams for job queue) (004-updated-data-service)
  • Python 3.11+ + FastAPI 0.115+, Pydantic AI 0.0.20+, SQLAlchemy 2.0+ (async), asyncpg, APScheduler 3.10+, python-jose (JWT), httpx, OpenTelemetry SDK, sse-starlette (005-i-want-to)
  • PostgreSQL 15+ (agent definitions, runs, tokens, workflows, scorers) (005-i-want-to)
  • Python 3.11+ (existing agent-server stack) + FastAPI, SQLAlchemy, Pydantic, LiteLLM, APScheduler (all already integrated) (006-busibox-agents-specs)
  • PostgreSQL 15+ with existing schema (agent_definitions, tool_definitions, workflow_definitions, eval_definitions, scheduled_runs, run_records) (006-busibox-agents-specs)

Project Structure

src/
tests/

Commands

Add commands for

Code Style

: Follow standard conventions

Recent Changes

  • 006-busibox-agents-specs: Added Python 3.11+ (existing agent-server stack) + FastAPI, SQLAlchemy, Pydantic, LiteLLM, APScheduler (all already integrated)
  • 005-i-want-to: Added Python 3.11+ + FastAPI 0.115+, Pydantic AI 0.0.20+, SQLAlchemy 2.0+ (async), asyncpg, APScheduler 3.10+, python-jose (JWT), httpx, OpenTelemetry SDK, sse-starlette
  • 004-updated-data-service: Added Python 3.11+ + FastAPI 0.104+, pymilvus 2.6+ (BM25 function support), redis-py 5.0+, boto3 (MinIO S3), psycopg 3.1+ (PostgreSQL async)
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 · 34 lines · 608 tokens per session scan A 702d84f53714

Subscribe to this mod's changes

specify-rules is a cursor rule published in the GitHub repository jazzmind/busibox (7 stars, last pushed 4d ago), licensed MIT. It adds 608 tokens to every session, about $0.0030 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.