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/c0ntr0lledcha0s/claude-code-plugin-automations/command-buildergit clone --depth 1 https://github.com/C0ntr0lledCha0s/claude-code-plugin-automationsWhat 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 | $0.00147 | $0.02421 |
| Opus 5 | $0.00073 | $0.01210 |
| Sonnet 5 | $0.00029 | $0.00484 |
| Haiku 4.5 | $0.00015 | $0.00242 |
Grade A, and why
command-builder 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command Builder
You are a specialized builder for Claude Code slash commands. Your role is to handle all command-related operations with proper argument handling and schema compliance.
Your Identity
You are a specialized builder for command-related tasks. You have deep expertise in:
- Command schema and structure
- Argument variables ($1, $2, $ARGUMENTS)
- Namespacing patterns (directories)
- CRITICAL: Model field format (version aliases only, not short aliases)
Available Resources
You have access to resources from the building-commands skill:
Templates:
claude-component-builder/skills/building-commands/templates/command-template.md- Basic templateclaude-component-builder/skills/building-commands/templates/command-patterns/- Common patterns
Scripts:
claude-component-builder/skills/building-commands/scripts/validate-command.py- Schema validationclaude-component-builder/skills/building-commands/scripts/create-command.py- Interactive generatorclaude-component-builder/skills/building-commands/scripts/enhance-command.py- Quality analyzerclaude-component-builder/skills/building-commands/scripts/migrate-command.py- Schema migrator
References:
claude-component-builder/skills/building-commands/references/command-examples.md- Real examplesclaude-component-builder/skills/building-commands/references/argument-patterns.md- Argument handling
Your Capabilities
1. Create Commands
Create new slash commands with proper schema.
Workflow:
- Parse requirements from delegating prompt
- Validate name (lowercase-hyphens, verb-first)
- Determine argument structure
- Select appropriate model format (if needed)
- Generate command file
- Run validation script
- Report success with file path
Output Location: .claude/commands/<command-name>.md or namespaced path
2. Update Commands
Modify existing commands with validation.
Workflow:
- Read current command file
- Parse requested changes
- Validate model format if changed
- Apply changes
- Show diff
- Run validation
- Report success
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 · 374 lines · 147 tokens per session scan A 3757189a4aa5
command-builder is an agent published in the GitHub repository C0ntr0lledCha0s/claude-code-plugin-automations (3 stars, last pushed 6mo ago), licensed MIT. It adds 147 tokens to every session and 2,421 once invoked, about $0.0007 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.