agent-categories

agent-categories is an agent for Claude Code from thapaliyabikendra/ai-artifacts. It costs 0 tokens per session (1,069 once invoked), scanned A, original, Apache-2.0.

A guide for sorting coding agents—automated helpers that plan, review, build, or specialise—into role-based folders.

In plain words
What is it for?
Use it to classify agents as architects, reviewers, engineers, or specialists based on the work they perform.
Why use it?
It makes a collection of agents easier to organise and helps determine where a new agent belongs.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to classify agents as architects, reviewers, engineers, or specialists based on the work they perform.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thapaliyabikendra/ai-artifacts/agent-categories
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.

Clone the repo
git clone --depth 1 https://github.com/thapaliyabikendra/ai-artifacts

Made for: Claude Code.

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-categories

README.md
[![agentmods](https://agentmods.dev/badge/agents/thapaliyabikendra/ai-artifacts/agent-categories.svg)](https://agentmods.dev/agents/thapaliyabikendra/ai-artifacts/agent-categories)
Your own site
<a href="https://agentmods.dev/agents/thapaliyabikendra/ai-artifacts/agent-categories"><img src="https://agentmods.dev/badge/agents/thapaliyabikendra/ai-artifacts/agent-categories.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,069 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.01069
Opus 5 $0.00000 $0.00535
Sonnet 5 $0.00000 $0.00214
Haiku 4.5 $0.00000 $0.00107

Measured 8d ago against content hash 0bb46e7d2a73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-categories 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 8d 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.

.claude/skills/claude-artifact-creator/references/agents/agent-categories.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Categories

Agents are organized by role (what they ARE) into the following categories.

Category Overview

Category Purpose Examples
architects/ Design systems, plan implementations backend-architect, business-analyst
reviewers/ Analyze and critique abp-code-reviewer, react-code-reviewer, security-engineer, qa-engineer
engineers/ Build and implement abp-developer, react-developer, devops-engineer
specialists/ Deep domain expertise debugger

Decision Tree: Where Does My Agent Go?

Is it primarily about designing/planning? → architects/
Is it primarily about reviewing/critiquing? → reviewers/
Is it primarily about building/implementing? → engineers/
Does it have deep domain expertise? → specialists/

Category Details

Architects (architects/)

Purpose: Design systems, create specifications, make architecture decisions.

Characteristics:

  • Focus on design over implementation
  • Create documentation (TSD, ADRs, schemas)
  • Make technology and pattern decisions
  • Plan before building

Typical Tools: Read, Write, Glob, Grep

Examples:

  • backend-architect - API design, database schemas
  • product-architect - BRDs, user stories, acceptance criteria
  • frontend-architect - Component architecture, state management

Reviewers (reviewers/)

Purpose: Analyze, audit, and critique code or systems.

Characteristics:

  • Read-only operations (typically)
  • Produce findings and recommendations
  • Don't implement fixes directly
  • Focus on quality and compliance

Typical Tools: Read, Glob, Grep

Examples:

  • abp-code-reviewer - Backend code quality, ABP patterns
  • react-code-reviewer - Frontend code quality, React patterns
  • security-engineer - Security audits, STRIDE, OWASP
  • qa-engineer - Test coverage, quality validation

Engineers (engineers/)

Purpose: Build and implement features, write code.

Characteristics:

  • Write and edit code
  • Follow specifications from architects
  • Run builds and tests
  • May auto-approve edits

Read the full file on GitHub · 167 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. 8d ago First seen · 167 lines · 0 tokens per session scan A 0bb46e7d2a73

Subscribe to this mod's changes

agent-categories is an agent published in the GitHub repository thapaliyabikendra/ai-artifacts (24 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,069 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.

Related

Other agents, from other repositories