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 skills/john-wilmes/claude-agentic-coding-playbook/create-projectnpx skills add john-wilmes/claude-agentic-coding-playbook --skill create-projectgit clone --depth 1 https://github.com/john-wilmes/claude-agentic-coding-playbookWrote 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/skills/john-wilmes/claude-agentic-coding-playbook/create-project)<a href="https://agentmods.dev/skills/john-wilmes/claude-agentic-coding-playbook/create-project"><img src="https://agentmods.dev/badge/skills/john-wilmes/claude-agentic-coding-playbook/create-project.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 5.1 | $0.00069 | $0.01358 |
| Opus 5 | $0.00034 | $0.00679 |
| Sonnet 5 | $0.00014 | $0.00272 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
create-project 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 5d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Project
Scaffold a new project following all global CLAUDE.md conventions.
Input
$ARGUMENTS= project name (required, kebab-case)
If no arguments provided, ask the user for a project name.
Steps
1. Determine install root
Run the install-root discovery helper:
INSTALL_ROOT=$(bash ~/.claude/scripts/skills/find-install-root.sh)
2. Gather requirements
Ask the user (single AskUserQuestion call):
- Project type: Node/TypeScript, Python, static site, or other
- Description: one-line summary for package.json and GitHub
3. Create directory
<INSTALL_ROOT>/<project-name>/
Fail if directory already exists.
4. Initialize git
cd <INSTALL_ROOT>/<project-name> && git init
5. Create .gitignore
Minimum entries per global CLAUDE.md Repository Hygiene rules:
node_modules/,dist/,.env*,*.log,.DS_Store,Thumbs.db
Add language-specific entries based on project type (e.g., __pycache__/ for Python, .next/ for Next.js).
6. Create project CLAUDE.md
Read the template at <INSTALL_ROOT>/.claude/templates/project-CLAUDE.md if available, otherwise use the built-in template.
Must include:
- Project name and one-line description
- Quality gate commands (type-check, lint, test) appropriate to the project type
- Language and framework conventions
- Architecture notes section (even if initially empty)
- Build and dependency instructions
7. Create AGENTS.md
Generate an AGENTS.md file at the project root. This is a cross-tool convention (60k+ repos) that tells any AI coding assistant how to build, test, and lint the project.
Populate sections from the quality gate commands chosen in step 6:
# AGENTS.md
## Build
<build command from quality gates, or "No build step configured.">
## Test
<test command from quality gates, e.g. "npm test">
## Lint
<lint command from quality gates, e.g. "npx eslint .">
## General
- Follow existing code style and naming conventions.
- Write tests for new functionality.
- Do not commit credentials or secrets.
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.
- 5d ago First seen · 170 lines · 69 tokens per session scan A e3039f702922
create-project is a skill published in the GitHub repository john-wilmes/claude-agentic-coding-playbook (4 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 1,358 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
typescript-best-practices
Enforces TypeScript best practices and modern patterns.
rust-skills
Comprehensive Rust coding guidelines with 265 rules across 26 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, concurrency, unsafe code, API design, memory optimization, performance, numeric safety, conversions, serde, pattern matching, macros…
harness-init
Bootstrap a target repo via /harness-init — ground, read, judge, confirm, apply. The IDEAgent itself reads, judges, and writes the root-truth files after one confirmation, without requiring Node/npm/npx/tsx.
pipeline-quality-audit
Audit and improve media or AI-generation pipelines whose command may succeed while the delivered output is unusable. Use direct output evidence, attempt automatic repair/retry/fallback, quarantine bad attempts for diagnosis, and stop only when no valid deliverable can be produced.
project-ai-docs-steward
Audit and improve a target repo's AI entry documentation (AGENTS.md, CLAUDE.md, steering, .cursor rules). Use after /harness-init or when AI context drifts. Generic harness protocol skill — parameterize paths to the open workspace.
doc-governance
Audit and converge a repository's human documentation using the governance model proven in practice: single source of truth, lifecycle-tiered docs (current truth / lessons / validation), project content kept out of pipeline docs, dead docs deleted instead of archived, and honest evidence labels. Use when docs feel…