usage-examples

A collection of examples showing which coding agents to use for common development work. It includes onboarding a new repository, investigating bugs, implementing features, reviewing code, and planning migrations.

In plain words
What is it for?
Use it as a reference for exploring an unfamiliar project, refactoring, security audits, performance work, documentation, architecture analysis, and code-review preparation.
Why use it?
It gives developers concrete prompts and expected results when they are unsure how to divide a task between agents.

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/usage-examples
Clone the repo
git clone --depth 1 https://github.com/daffy0208/ai-dev-standards

Made for: Claude Code.

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 3,201 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 $0.03201
Opus 5 $0.00000 $0.01600
Sonnet 5 $0.00000 $0.00640
Haiku 4.5 $0.00000 $0.00320

Measured 2d ago against content hash c66f18bc306f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

usage-examples 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.

.claude/agents/usage-examples.md · 703 lines

How it starts

The opening of the file, as written. The whole thing — 703 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Usage Examples

Practical examples showing how to use different agents for common development tasks.

Table of Contents

  1. New Repository Onboarding
  2. Bug Investigation
  3. Feature Implementation
  4. Refactoring
  5. Security Audit
  6. Performance Optimization
  7. Documentation Generation
  8. Architecture Analysis
  9. Migration Planning
  10. Code Review Preparation

New Repository Onboarding

Scenario

You've just cloned a new React/Node.js project and need to understand it quickly.

Approach

Phase 1: Quick Overview (5 minutes)

Agent: Explore (Quick)
Task: "Give me an overview of this project - what it does,
       tech stack, and main entry points"

Expected Output:
- Project purpose
- Tech stack (React, Node, PostgreSQL)
- Entry points (index.tsx, server.ts)
- Directory structure

Phase 2: Deep Dive on Key Areas (30 minutes)

Agent: Explore (Medium)
Task: "Explore the authentication system - how users log in,
       session management, and authorization checks"

Expected Output:
- Auth flow diagram
- Components involved
- API endpoints
- Security measures

Phase 3: Get Started (Ongoing)

Agent: General-Purpose
Task: "Set up my local development environment following
       the project conventions"

Actions:
- Install dependencies
- Configure environment
- Run tests
- Start dev server

Bug Investigation

Scenario

Users report authentication failing with special characters in passwords.

Approach

Phase 1: Locate Code (5 minutes)

Agent: General-Purpose
Task: "Find all code related to password validation and
       authentication, especially where user input is processed"

Tools Used:
- Grep for "password", "validation", "auth"
- Read auth-related files

Read the full file on GitHub · 703 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 · 703 lines · 0 tokens per session scan A c66f18bc306f

Subscribe to this mod's changes

usage-examples 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 3,201 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.