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/bengous/claude-code-plugins/skill-creatorgit clone --depth 1 https://github.com/bengous/claude-code-pluginsWhat 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 | $0.00006 | $0.00278 |
| Opus 5 | $0.00003 | $0.00139 |
| Sonnet 5 | $0.00001 | $0.00056 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
skill-creator 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 yesterday.
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.
What it actually says
Skill Creator
A comprehensive guide for creating effective Claude Code skills, with utilities for initialization, validation, and packaging.
What This Plugin Provides
- Complete skill creation guide: Best practices, patterns, and conventions
- Reference documentation: Output patterns and workflow examples
- Utility commands: Initialize, validate, and package skills
Available Commands
/skill-creator- Load the full skill creation guide (this command)/skill-creator:init <name> [--path <dir>]- Initialize a new skill/skill-creator:validate <path>- Validate skill structure/skill-creator:package <path> [--output <dir>]- Package a skill
Your Task
Read and present the complete skill creation guide to the user:
Read the file: ${CLAUDE_PLUGIN_ROOT}/SKILL.md
This file contains comprehensive documentation on:
- Skill creation best practices
- Structural conventions
- Output patterns and formatting
- Workflow examples
- Quality guidelines
- Common pitfalls and how to avoid them
After reading SKILL.md, summarize the key sections and let the user know they can ask questions about any specific aspect of skill creation.
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.
- yesterday First seen · 42 lines · 6 tokens per session scan A 27edc69a045d
skill-creator is a command published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 6 tokens to every session and 278 once invoked, about $0.0000 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 commands, from other repositories
pwf-commit-changes
Commit uncommitted changes across all workspace repos, tagging commits with ticket numbers from pasted issue text. Spawns one parallel subagent per repo — each analyzes every changed file, groups them by ticket, and makes multiple focused commits independently.
enforce_standards
CRITICAL: Before running the code standards enforcer, we must prepare the stack properly and abort if there are merge conflicts.
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
triage
Triage Linear issue with comprehensive analysis.
verify
Adversarial spec-vs-implementation verification for a completed task. Dispatches the spec-mentor subagent with fresh context (no anchoring bias), parses its verdict (PASS / DRIFT / NEEDS-MARTY), and updates the verification queue. The v7.4.0 architectural replacement for a dedicated "mentor session.".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.