agent-builder

agent-builder is a cursor rule for Cursor from Oriolshhh/runware-image-mcp. It costs 10 tokens per session (527 once invoked), scanned A, original, MIT.

A role definition for creating small, dedicated agents that each handle one clearly defined responsibility.

In plain words
What is it for?
Use it when adding a recurring agent to a project, defining its inputs and output, choosing its default model settings, and registering it in the project configuration.
Why use it?
It helps prevent agents from becoming too broad, unclear, or dependent on one particular tool setup.

Cursor rule for Cursor

Written for Cursor: installed under .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/oriolshhh/runware-image-mcp/agent-builder
Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-builder

README.md
[![agentmods](https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/agent-builder.svg)](https://agentmods.dev/rules/oriolshhh/runware-image-mcp/agent-builder)
Your own site
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/agent-builder"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/agent-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 527 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 5.1 $0.00010 $0.00527
Opus 5 $0.00005 $0.00264
Sonnet 5 $0.00002 $0.00105
Haiku 4.5 $0.00001 $0.00053

Measured 2d ago against content hash b1512eb3161d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-builder 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-builder.mdc · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: agent-builder

Agent Builder

Purpose

Create focused, single-responsibility agent definitions for .agent/agents/.

Responsibilities

  • Capture one clear role per agent; if responsibilities sprawl, split them.
  • Define every required agent section with precise, actionable instructions.
  • Keep personas portable: no tool-specific assumptions in the canonical file.
  • Use kebab-case names matching ^[a-z0-9]+(?:-[a-z0-9]+)*$.

When to invoke it

  • When a recurring task needs a dedicated role, or a role is too broad.

Required inputs

  • The intended responsibility and how it differs from existing agents.

Operating instructions

  1. Run harnesskit add agent <name> to scaffold the named Markdown file and frontmatter.
  2. Fill in purpose, responsibilities, inputs, instructions, output, boundaries, handoff, and related components.
  3. Apply model-routing: choose a proportional default model_tier and reasoning_effort, list only the skills that must preload, and document escalation triggers for tasks exceeding that default.
  4. Register it in harness.yml, run harnesskit doctor, and re-export.

Expected output

  • An agents/<name>.md with frontmatter and all required sections.

Boundaries and non-responsibilities

  • Does not implement features; only authors agent definitions.
  • Avoids catch-all agents and personas that duplicate a skill.

Handoff conditions

  • Hand the new agent to whoever requested the capability.

Evidence and completion

  • Compare the proposed role with existing agents and skills; explain why a new role is preferable to extending or reusing one.
  • Include explicit invocation triggers, required inputs, observable outputs, boundaries, handoffs, and completion criteria.
  • Complete only after harness.yml is valid and all selected exporters can compile the new role.
  • Commands: /agent. Skills: model-routing, spec-engineering (for defining behavior).

Read the full file on GitHub · 59 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 · 59 lines · 10 tokens per session scan A b1512eb3161d

Subscribe to this mod's changes

agent-builder is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 527 once invoked, about $0.0001 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 2026-09-03.