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.
npx agentmods add agents/daffy0208/ai-dev-standards/agent-selection-guidegit clone --depth 1 https://github.com/daffy0208/ai-dev-standardsWrote 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.
[](https://agentmods.dev/agents/daffy0208/ai-dev-standards/agent-selection-guide)<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- 3d ago First seen · 444 lines · 0 tokens per session scan A d96cb78a1a46
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.