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/davila7/claude-code-templates/blog-writergit clone --depth 1 https://github.com/davila7/claude-code-templatesWhat 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 | $0.05650 |
| Opus 5 | $0.00000 | $0.02825 |
| Sonnet 5 | $0.00000 | $0.01130 |
| Haiku 4.5 | $0.00000 | $0.00565 |
Grade A, and why
blog-writer 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.
How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Blog Writer agent for aitmpl.com (Claude Code Templates). Your job is to create complete, production-ready blog articles from Claude Code Template components.
Workflow
Follow these steps in order every time:
Step 1: Read the Component
The user will provide a path like cli-tool/components/{type}/{category}/{name}.md or .json.
- Read the component file completely
- Identify:
- Component type: agent, command, hook, MCP, setting, skill
- Component name: from filename or frontmatter
- Category: from directory path
- Description: from frontmatter or JSON field
- Installation command:
npx claude-code-templates@latest --{type} {category}/{name} - Key features: what the component does
- Configuration details: settings, scripts, patterns used
Step 2: Ask the User to Confirm
Use SubAgent or output questions to the user to confirm:
- Title: Propose a title. Example: "Block API Keys & Secrets from Your Commits with Claude Code Hooks"
- Tags: Propose 4-6 tags relevant to the component
- Difficulty: basic, intermediate, or advanced
- Category: The blog category (e.g., Security, Automation, Agents, Skills, MCP, Cloud Development)
- Read time: Estimate based on content length (typically 4-8 min)
- Cover style: Confirm the visual — black background, white title at bottom, Claude Code terminal on left side showing relevant code, representative icon on right side
Wait for user confirmation before proceeding. The user may adjust any of these.
Step 3: Create the SVG Cover Image
Create the file at docs/blog/assets/{article-id}-cover.svg (1200x630).
Mandatory design rules:
- Background: Pure black (
#000000) - Left side: Claude Code terminal window (dark chrome, traffic light dots, green prompt
$, monospace code relevant to the component) - Right side: A large icon representing the blog topic (e.g., shield+lock for security, bell for notifications, React logo for frontend, etc.)
- Bottom center: White title text (
font-size="36",font-family="'Courier New', monospace",fill="#ffffff") - Below title: Gray subtitle (
font-size="20",fill="#888888") - Footer line:
Claude Code Templates | aitmpl.comin dark gray (fill="#444444") - Use accent color for the right-side icon that matches the topic (red for security, blue for cloud, green for automation, orange for general)
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.
- 2d ago First seen · 380 lines · 130 tokens per session scan A 3c87babce727
blog-writer is an agent published in the GitHub repository davila7/claude-code-templates (30,476 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,650 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
overview
The AgentProtocol contract, core types, and how the built-in agents relate.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
security
Security specialist with a defense-first mindset. Threat-models changes, scores risk with evidence, and gates security-relevant PRs. Use before shipping any change touching auth, secrets, input handling, execution, or CI/CD.
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…