agent-selection-guide

agent-selection-guide is an agent for Claude Code from daffy0208/ai-dev-standards. It costs 0 tokens per session (2,513 once invoked), scanned A, original, MIT.

A decision guide for choosing among specialized coding agents. It matches common development tasks with agents suited to exploration, project management, code review, design systems, security, or general implementation.

In plain words
What is it for?
Use it when exploring an unfamiliar codebase, managing a complex project, coordinating agents, reviewing code, checking security, or implementing features and fixes.
Why use it?
It removes the guesswork of deciding which agent to use for a task. This is useful when a project offers many agent types with different purposes.

Agent for Claude Code

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 agents/daffy0208/ai-dev-standards/agent-selection-guide
Clone the repo
git clone --depth 1 https://github.com/daffy0208/ai-dev-standards

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-selection-guide

README.md
[![agentmods](https://agentmods.dev/badge/agents/daffy0208/ai-dev-standards/agent-selection-guide.svg)](https://agentmods.dev/agents/daffy0208/ai-dev-standards/agent-selection-guide)
Your own site
<a href="https://agentmods.dev/agents/daffy0208/ai-dev-standards/agent-selection-guide"><img src="https://agentmods.dev/badge/agents/daffy0208/ai-dev-standards/agent-selection-guide.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 2,513 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 $0.02513
Opus 5 $0.00000 $0.01256
Sonnet 5 $0.00000 $0.00503
Haiku 4.5 $0.00000 $0.00251

Measured 3d ago against content hash d96cb78a1a46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-selection-guide 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 3d 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/agents/agent-selection-guide.md · 444 lines

How it starts

The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Selection Guide

Decision tree and practical guidance for choosing the right agent for your task.


Quick Decision Tree

START: What do you need to do?

├─ Configure Claude Code settings?
│  └─→ USE: Setup Agents (statusline-setup or output-style-setup)
│
├─ Explore new/unfamiliar codebase?
│  ├─ Quick overview needed? → USE: Explore Agent (Quick mode)
│  ├─ Balanced understanding? → USE: Explore Agent (Medium mode)
│  └─ Deep analysis needed? → USE: Explore Agent (Very Thorough mode)
│
├─ Manage complex project?
│  └─→ USE: Archon-Manager Agent
│
├─ Coordinate multiple agents?
│  └─→ USE: Multi-Agent Architect
│
├─ Orchestrate entire project lifecycle?
│  └─→ USE: Framework-Orchestrator Agent
│
├─ Automated code review needed?
│  └─→ USE: Codex-Review-Workflow Agent
│
├─ Build/maintain design system?
│  └─→ USE: Design-System Architect
│
├─ Security architecture/audit?
│  └─→ USE: Security-Architect
│
└─ Everything else? (implementation, bug fixes, features)
   └─→ USE: General-Purpose Agent (default)

Detailed Selection Criteria

1. By Task Type

Exploration Tasks

  • New codebase → Explore Agent (Quick/Medium)
  • Architecture analysis → Explore Agent (Very Thorough)
  • Pattern discovery → Explore Agent (Medium)
  • Pre-refactoring → Explore Agent (Very Thorough)

Implementation Tasks

  • Feature development → General-Purpose Agent
  • Bug fixes → General-Purpose Agent
  • Refactoring → General-Purpose Agent
  • Testing → General-Purpose Agent + testing-strategist

Management Tasks

  • Project management → Archon-Manager
  • Task coordination → Archon-Manager
  • Knowledge management → Archon-Manager + knowledge-base-manager

Orchestration Tasks

  • Multi-agent coordination → Multi-Agent Architect
  • Framework coordination → Framework-Orchestrator
  • Complex workflows → Framework-Orchestrator + Multi-Agent Architect

Quality Tasks

  • Code review → Codex-Review-Workflow
  • Security audit → Security-Architect
  • Quality assurance → Codex-Review-Workflow + quality-assurance

Read the full file on GitHub · 444 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. 3d ago First seen · 444 lines · 0 tokens per session scan A d96cb78a1a46

Subscribe to this mod's changes

agent-selection-guide is an agent published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,513 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.