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 skills add Pixel-Process-UG/superkit-agents --skill using-toolkitgit clone --depth 1 https://github.com/Pixel-Process-UG/superkit-agentsWrote 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/skills/pixel-process-ug/superkit-agents/using-toolkit)<a href="https://agentmods.dev/skills/pixel-process-ug/superkit-agents/using-toolkit"><img src="https://agentmods.dev/badge/skills/pixel-process-ug/superkit-agents/using-toolkit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pixel-process-ug/superkit-agents/using-toolkit"><img src="https://agentmods.dev/badge/skills/pixel-process-ug/superkit-agents/using-toolkit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.03207 |
| Opus 5.5 | $0.00018 | $0.01283 |
| Sonnet 5.5 | $0.00009 | $0.00641 |
| Haiku 4.5 | $0.00005 | $0.00321 |
Grade A, and why
using-toolkit 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 1mo 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. This is not optional. You cannot rationalize your way out of this.
Overview
Master catalog and dispatch system for all 64 toolkit skills. Ensures proper skill identification at conversation start.
How to Access Skills
In Claude Code: Use the Skill tool. When you invoke a skill, its content is loaded and presented to you — follow it directly. Never use the Read tool on skill files.
Phase 1: Skill Identification
Before ANY action: scan catalog, identify ALL matching skills (even 1% relevance), invoke via Skill tool.
Phase 2: Skill Prioritization
Invoke in order: (1) Process (brainstorming, planning) → (2) Specialist (frontend, backend, architect) → (3) Quality (TDD, review) → (4) Docs → (5) Design → (6) Ops → (7) Terminal (verification).
Phase 3: Skill Execution
Rigid skills: Follow exactly. Flexible skills: Adapt to context. Always invoke verification-before-completion before claiming done.
Available Skills (64 Total)
Core Skills (6)
| Skill | When to Use |
|---|---|
using-toolkit |
Session start — establishes skill usage |
self-learning |
Starting work on unfamiliar projects, or when corrected |
resilient-execution |
When an approach fails — ensures retry with alternatives |
circuit-breaker |
Autonomous loops, repeated operations, stagnation detection |
auto-improvement |
Self-improving system, tracks effectiveness, learns from errors |
verification-before-completion |
Before claiming ANY task is complete |
Process & Workflow Skills (9)
| Skill | When to Use |
|---|---|
planning |
Before ANY implementation — forces structured planning |
brainstorming |
Before creative work — exploring ideas, features, designs |
task-management |
Breaking work into tracked steps during implementation |
executing-plans |
Executing approved plan documents step by step |
subagent-driven-development |
Multi-task execution with two-stage review gates |
dispatching-parallel-agents |
Running multiple independent tasks concurrently |
autonomous-loop |
Ralph-style iterative autonomous development loops |
ralph-status |
End of every autonomous loop iteration — structured progress reporting |
task-decomposition |
Hierarchical task breakdown, dependency mapping, parallelization |
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.
- 1mo ago First seen · 268 lines · 45 tokens per session scan A 4571ce01143f
using-toolkit is a skill published in the GitHub repository Pixel-Process-UG/superkit-agents (3 stars, last pushed 7mo ago), licensed MIT. It adds 45 tokens to every session and 3,207 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
create-slack-app
Use when a developer wants to create, scaffold, or bootstrap a new Slack app or agent from scratch with the Slack CLI. Covers prerequisites, authentication, choosing a workspace to install into, and creating a project from a Bolt (JS or Python) template locally. Trigger on "create a Slack app", "new Bolt app", "start…
subagent-driven-development
A development workflow in which a fresh coding agent implements each independent task, another review checks that task, and a final review examines the complete set of changes.
music
A tool for creating and working with music using Mureka, an AI music service. It handles new songs, instrumental tracks, remixes, extensions, and audio analysis.