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.
git clone --depth 1 https://github.com/dykyi-roman/awesome-claude-codeWrote 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/dykyi-roman/awesome-claude-code/generate-claude-component)<a href="https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/generate-claude-component"><img src="https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/generate-claude-component.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 | $0.00029 | $0.02274 |
| Opus 5 | $0.00015 | $0.01137 |
| Sonnet 5 | $0.00006 | $0.00455 |
| Haiku 4.5 | $0.00003 | $0.00227 |
Grade A, and why
generate-claude-component 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 4d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Creator
You are a master of creating Claude Code components.
Input Parsing
Parse $ARGUMENTS to extract component type and optional meta-instructions:
Format: [component-type] [-- <meta-instructions>]
Examples:
- /acc:generate-claude-component
- /acc:generate-claude-component command
- /acc:generate-claude-component agent -- for DDD auditing
- /acc:generate-claude-component skill -- generates Value Objects
- /acc:generate-claude-component ? -- I want to auto-format code
- /acc:generate-claude-component ? -- need a security audit
- /acc:generate-claude-component hook -- validate PHP syntax before Write tool
- /acc:generate-claude-component rule -- domain layer must be pure
- /acc:generate-claude-component plugin -- package DDD tools for distribution
Parsing rules:
- Split
$ARGUMENTSby--(space-dash-dash-space) - First part = component type (optional: command/agent/skill/hook/rule/plugin/?)
- Second part = meta-instructions (optional, hints about purpose)
Discovery mode (?):
If first part is ?, enter discovery mode:
- Analyze meta-instructions to understand user's goal
- Recommend best component type with reasoning
- Show plan before proceeding
If component type provided (not ?), skip Step 0-1 and go directly to Step 2.
If meta-instructions provided, use them to guide questions in Step 2.
Process
Step 0: Discovery Mode (if ? provided)
If user passed ? as component type:
-
Analyze the goal from meta-instructions:
- What problem needs solving?
- Is it automation, audit, generation, or workflow?
- Does it need separate context (agent) or just instructions (skill)?
- Should it trigger automatically (hook) or manually (command)?
- Is it project-wide instruction (rule) or distributable package (plugin)?
-
Recommend component type with reasoning:
Goal Pattern Recommended Reason "automatically when..." / "on save" / "before commit" Hook Triggered by events, zero context cost "check/audit/validate/analyze" Command + Agent Complex analysis needs separate context "generate/create/write" Command + Agent + Skills Generation workflow "instructions/reference/knowledge" Skill Reusable knowledge "simple workflow/quick action" Command Single saved prompt "always follow these rules" / "project standard" Rule Always in system prompt "share with team" / "distribute" / "package" Plugin Namespaced, installable "external API/tool integration" MCP config Standardized protocol
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.
- 4d ago First seen · 245 lines · 0 tokens per session scan A 85bdda7ccc8d
generate-claude-component is a command published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 23d ago), licensed MIT. It adds 29 tokens to every session and 2,274 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 2026-09-03.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.