Claude Code Templates is a command-line tool and catalogue for configuring Anthropic’s Claude Code with agents, commands, settings, hooks, integrations, skills, and project templates. Developers use it to browse and install reusable components for their coding workflows. The catalogue includes many of these Claude Code components.
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 commands/davila7/claude-code-templates/create-blog-articlegit clone --depth 1 https://github.com/davila7/claude-code-templatesWrote 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/commands/davila7/claude-code-templates/create-blog-article)<a href="https://agentmods.dev/commands/davila7/claude-code-templates/create-blog-article"><img src="https://agentmods.dev/badge/commands/davila7/claude-code-templates/create-blog-article.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 | $0.00017 | $0.03913 |
| Opus 5 | $0.00009 | $0.01956 |
| Sonnet 5 | $0.00003 | $0.00783 |
| Haiku 4.5 | $0.00002 | $0.00391 |
Grade A, and why
create-blog-article 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 — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Blog Article for Claude Code Component
You will create a complete, SEO-optimized blog article for a Claude Code component.
Component Path Argument
Component path provided: $ARGUMENTS
Expected format examples:
development-team/frontend-developer(for agents)supabase(for MCPs)productivity/nowait(for skills)
Step 1: Identify Component Type and Read Component File
Based on the path structure, determine the component type:
- If path has
/, could be an agent, MCP, command, skill, or hook in a folder - Single word could be MCP, command, or skill
Read the component file:
- Agents:
cli-tool/components/agents/$ARGUMENTS.md(e.g.,development-team/frontend-developer.md) - MCPs:
cli-tool/components/mcps/$ARGUMENTS.json(e.g.,devtools/context7.json) - Skills:
cli-tool/components/skills/$ARGUMENTS/SKILL.md - Commands:
cli-tool/components/commands/$ARGUMENTS.md(e.g.,setup/ci-cd-pipeline.md) - Hooks:
cli-tool/components/hooks/$ARGUMENTS.md
CRITICAL: Use find or grep to locate the actual file path first, then extract folder/name structure.
Extract from the component file:
name: Component namedescription: Component descriptiontools: Available tools (for agents)- Key capabilities and focus areas from the content
Step 2: Generate Component-Specific Blog ID and Names
From the component path, create:
-
Blog ID: Convert path to blog-friendly ID
- Example:
development-team/frontend-developer→frontend-developer-agent - Example:
supabase→supabase-mcp - Example:
productivity/nowait→nowait-skill
- Example:
-
Component Name: Human-readable name
- Example:
frontend-developer→Frontend Developer - Example:
supabase→Supabase
- Example:
-
Component Type: Uppercase type
- AGENT, MCP, SKILL, COMMAND, HOOK
Step 3: Generate Cover Image FIRST
CRITICAL: Generate the cover image BEFORE creating the HTML file.
Use the Python script to generate the image:
python3 scripts/generate_blog_images.py
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 · 432 lines · 17 tokens per session scan A 0b13fabe0c6d
create-blog-article is a command published in the GitHub repository davila7/claude-code-templates (30,520 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 3,913 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
research-verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
validate-pr-description
Use when validating a PR title and description for conventional commit format, issue linking keywords, and template compliance before submission.
adv-gemini-research
Deep research query via Gemini with Google Search grounding.
brain-archive
Migrate stale completed threads + old sessions to WORKSPACEBRAINARCHIVE.md.