agent-development

A set of rules for creating coding-agent files with YAML metadata followed by the agent's instructions. YAML is a simple format for labelled settings such as a name, model, and available tools.

In plain words
What is it for?
Use it when adding or reviewing agents for development, security, testing, DeFi, standards, or blockchain tooling.
Why use it?
It keeps agent files consistent, discoverable, and specific about their role and required expertise.

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/ccashwell/evm-cortex/agent-development
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex

Made for: Cursor.

Per session 330 This file is loaded in full into every session.
When invoked 330 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 $0.00330 $0.00330
Opus 5 $0.00165 $0.00165
Sonnet 5 $0.00066 $0.00066
Haiku 4.5 $0.00033 $0.00033

Measured 2d ago against content hash 10e0eab0f63e, 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 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/agent-development.mdc · 40 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
model: opus or sonnet
tools: [Read, Write, Bash, Grep, Glob]
---

Followed by the agent's system prompt in Markdown.

Naming Conventions

  • Filename: kebab-case.md (e.g., gas-optimizer.md)
  • Name field: same as filename without extension
  • Description: starts with domain-specific role

Agent Categories

  • Core Dev: solidity-architect, solidity-engineer, gas-optimizer, contract-deployer
  • Security: audit-orchestrator, depth-state-trace, depth-token-flow, depth-edge-case, depth-external
  • Testing: foundry-tester, invariant-tester, formal-verifier, fuzzer, poc-writer
  • DeFi: defi-architect, amm-expert, lending-expert, oracle-expert
  • Tooling: foundry-expert, openzeppelin-expert, slither-analyst
  • Standards: eip-expert, erc-implementer, upgrade-planner, governance-designer

Quality Rules

  • Every agent must have deep Ethereum/Solidity expertise
  • Include specific tool references (Foundry, Slither, Cast)
  • Include actionable methodology, not just knowledge
  • Reference specific EIPs, ERCs, and standards
  • Cross-reference relevant skills
  • Use "onchain" not "on-chain"

Consider these rules if they affect your changes.

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 · 40 lines · 330 tokens per session scan A 10e0eab0f63e

Subscribe to this mod's changes

agent-development is a cursor rule published in the GitHub repository ccashwell/evm-cortex (127 stars, last pushed 22d ago), licensed MIT. It adds 330 tokens to every session, about $0.0016 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 2026-08-30.