john-wilmes

Claude Agentic Coding Playbook — AI skill for Claude Code

AI community intermediate

Evidence-based practices for LLM-assisted development -- hooks, skills, scripts, and a best-practices guide with 58 citations.

How to install Claude Agentic Coding Playbook

This entry records only its repository, not the path inside it, so there is no exact command to give. Open john-wilmes/claude-agentic-coding-playbook and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Agentic Coding Playbook does

Evidence-based practices for LLM-assisted software development. Built for [Claude Code](https://claude.com/claude-code). The principles in [best-practices.md](docs/best-practices.md) are conceptually portable, but all hooks, skills, and scripts target Claude Code specifically.

Alternatives in AI

Rust Skills — Rust Developer AI Assistance System — Meta-Problem-Driven Knowledge Indexing 893 ★
Maestro Companion — Quick execution for small tasks — minimal run lifecycle (start + done) with evidence recording 530 ★
Agentic SEO Skill — An LLM-first SEO analysis skill for Antigravity, Codex, Claude with 16 specialized sub-skills, 10 specialist a 419 ★

README

[](https://github.com/john-wilmes/claude-agentic-coding-playbook/actions/workflows/test-install.yml)

Agentic Coding Playbook

Why This Exists

AI-assisted code contains 1.7x more issues than human-written code and introduces 10x more security findings in enterprise settings. Developer productivity gains range from -19% (experienced OSS developers) to +55% (controlled tasks) depending on task type, tool, and developer experience. The practices in this playbook are designed to capture the upside while mitigating the documented risks.

Key findings from the research:

Metric	Value	Source
AI code issues vs human code	1.7x more	CodeRabbit (470 PRs)
Security findings in AI-assisted teams	10x increase	Apiiro (Fortune 50)
Prompt injection success rate	94%	PMC controlled study
AI code review defect detection	44-82%	Greptile, Macroscope benchmarks
Fresh session vs exhausted session cost	~10x cheaper	Anthropic
Model routing savings (Haiku vs Opus)	5-20x	Anthropic pricing
Prompt cache hit savings	90%	Anthropic
Teams with AI review seeing quality gains	81% vs 55%	Qodo

Full details with citations: [docs/best-practices.md](docs/best-practices.md)

How This Works

Most Claude Code setups rely on CLAUDE.md instructions alone. Instructions are advisory — compliance ranges from ~50-90% in our testing (published research reports lower rates for complex instruction sets). This playbook takes a different approach:

...