create-update-agent

A workflow for creating and editing custom AI agents in Cursor, an editor with built-in coding agents. It stores agent definitions in Cursor’s modes.json file and project documents in an ai folder.

In plain words
What is it for?
Use it to create or update agents, review existing agent settings, clarify requested changes, and save user stories or other project documents.
Why use it?
It provides a consistent way to manage agents while preventing custom agents from deleting agent files or folders.

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/usrrname/cursorrules/create-update-agent
Clone the repo
git clone --depth 1 https://github.com/usrrname/cursorrules

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 909 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 $0.00909
Opus 5 $0.00000 $0.00454
Sonnet 5 $0.00000 $0.00182
Haiku 4.5 $0.00000 $0.00091

Measured yesterday against content hash ae061f6b7e47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-update-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 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/core/create-update-agent.mdc · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critical Rules

  • All agents will be referred to as a team in prompts and the one with the best abilities for the task will volunteer to perform it.
  • Understand existing agents in .cursor/modes.json
  • Follows the format specified in .cursor/templates/mode-format.md
  • Adds or updates agent information in .cursor/modes.json
  • If updating an agent, clarify which aspects of an agent require updating or modification
  • Custom agents can NEVER delete files or folders in .cursor/
  • Custom agents can NEVER delete other agents.
  • Agents should create user stories, documents and other markdown project artifacts in the ./ai/** folder. If it doesn't already exist, it should be created.
  • If an agent was invoked by name, the system should infer that subsequent requests are directed at the same agent.
  • If there is an agent with capabilities better suited for a task, ask the user if they would like to delegate the requested activty to a different agent before executing the user's request.

Examples

AI: I'll help you create a new Cursor agent called SageDaddy based on Senshi from Dungeon Meshi. Let me first check the current modes.json and format requirements.

[AI reads .cursor/modes.json and docs/mode-format.md]

Here's what I propose for this new agent:

Name: SageDaddy Description: Software Architect - SageDaddy Model: claude-3.7-sonnet Persona: Adorably grumpy, quietly confident, logical, resourceful, calm and empathetic.

Would you like me to proceed with adding this agent? I'll need to update both the modes.json file and the custom-agents.md documentation.

User: Yes, please add him with access to all cursor tools and Tavily for research.

[AI updates both .cursor/modes.json and .cursor/templates/custom-agents.md with the new agent]

Read the full file on GitHub · 103 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. yesterday First seen · 103 lines · 0 tokens per session scan A ae061f6b7e47

Subscribe to this mod's changes

create-update-agent is a cursor rule published in the GitHub repository usrrname/cursorrules (10 stars, last pushed 4mo ago), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 909 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 2026-08-31.