agent-development

Development rules for creating and editing agent definitions, which are specialized AI roles written as Markdown files. They specify the file format, available tool declarations, naming, roles, and quality expectations.

In plain words
What is it for?
Use them when adding or changing agents for development, code review, testing, architecture, analysis, or other specialist work.
Why use it?
They prevent overlapping or unclear agent roles and ensure each agent has a predictable structure and purpose.

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/vibeeval/vibecosystem/agent-development
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 293 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00293
Opus 5 $0.00000 $0.00147
Sonnet 5 $0.00000 $0.00059
Haiku 4.5 $0.00000 $0.00029

Measured yesterday against content hash bf72891afd96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-development 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.

.cursor/rules/agent-development.mdc · 41 lines

What it actually says

Agent Development Rules

Agent File Format

Each agent is a Markdown file with YAML frontmatter:

---
name: agent-name
description: One-line description of what the agent does
tools: [Read, Write, Edit, Bash, Grep, Glob]
---

Followed by the agent's system prompt in Markdown.

Naming Conventions

  • Filename: kebab-case.md (e.g., code-reviewer.md)
  • Name field: same as filename without extension
  • Description: starts with a verb (e.g., "Reviews code for...")

Agent Categories

  • Core Dev: frontend-dev, backend-dev, kraken, spark, devops
  • Review & QA: code-reviewer, security-reviewer, verifier, qa-engineer
  • Domain Experts: graphql-expert, kubernetes-expert, ddd-expert
  • Architecture: architect, planner, clean-arch-expert
  • Testing: tdd-guide, e2e-runner, arbiter, mocksmith
  • Analysis: scout, sleuth, data-analyst, profiler

Quality Rules

  • Every agent must have a clear, specific purpose
  • Avoid overlapping responsibilities between agents
  • Keep system prompts focused and actionable
  • Include specific output format expectations
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 · 41 lines · 0 tokens per session scan A bf72891afd96

Subscribe to this mod's changes

agent-development is a cursor rule published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 293 tokens. 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 2026-08-30.