creating-kiro-agents

Guidance for creating Kiro agents, which are specialized AI development assistants, using JSON configuration files. It covers their prompts, tools, permissions, resources, and hooks.

In plain words
What is it for?
Setting up Kiro agents for specific development jobs, including their configuration locations, allowed tools, paths, and shell commands.
Why use it?
It helps keep each assistant focused and limits it to the files and commands it actually needs.

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/pr-pm/prpm/creating-kiro-agents
Clone the repo
git clone --depth 1 https://github.com/pr-pm/prpm

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,026 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.02026
Opus 5 $0.00000 $0.01013
Sonnet 5 $0.00000 $0.00405
Haiku 4.5 $0.00000 $0.00203

Measured 2d ago against content hash bd5d54a8ad8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

creating-kiro-agents scanned grade A with 1 finding 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

### ❌ Don't: Grant All Tools

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.cursor/rules/creating-kiro-agents.mdc · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kiro Agent Development

Patterns for creating specialized Kiro AI agents with proper configuration, tools, and security.

Agent File Structure

{
  "name": "agent-name",
  "description": "One-line purpose",
  "prompt": "System instructions",
  "tools": ["fs_read", "fs_write"],
  "toolsSettings": {},
  "resources": [],
  "mcpServers": {},
  "hooks": {}
}

Location:

  • Project: .kiro/agents/<name>.json
  • Global: ~/.kiro/agents/<name>.json

Core Principles

1. Specialization

✅ Create focused agents: backend-api-specialist ❌ Avoid generic agents: general-helper

2. Least Privilege

Only grant necessary tools and paths.

{
  "toolsSettings": {
    "fs_write": {
      "allowedPaths": ["src/api/**", "tests/api/**"]
    },
    "execute_bash": {
      "allowedCommands": ["npm test", "npm run build"]
    }
  }
}

3. Clear Prompts

Be specific about domain, focus areas, and standards.

{
  "prompt": "Backend API expert specializing in Express.js and MongoDB.\n\n## Focus\n- RESTful API design\n- Security (input validation, auth)\n- Error handling\n- Query optimization\n\n## Standards\n- Always use async/await\n- Implement proper logging\n- Validate all inputs"
}

Common Patterns

Backend Specialist

{
  "name": "backend-dev",
  "description": "Node.js/Express API development with MongoDB",
  "prompt": "Backend development expert. Focus on API design, database optimization, and security.\n\n## Core Principles\n- RESTful conventions\n- Input validation\n- Error handling\n- Query optimization",
  "tools": ["fs_read", "fs_write", "execute_bash"],
  "toolsSettings": {
    "fs_write": {
      "allowedPaths": ["src/api/**", "src/routes/**", "src/models/**"]
    }
  }
}

Code Reviewer

{
  "name": "code-reviewer",
  "description": "Reviews code against team standards",
  "prompt": "You review code for:\n- Quality and readability\n- Security issues\n- Performance problems\n- Standard compliance\n\nProvide constructive feedback with examples.",
  "tools": ["fs_read"],
  "resources": ["file://.kiro/steering/review-checklist.md"]
}

Read the full file on GitHub · 337 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. 2d ago First seen · 337 lines · 0 tokens per session scan A bd5d54a8ad8c

Subscribe to this mod's changes

creating-kiro-agents is a cursor rule published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,026 tokens. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.