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 Kasempiternal/Claude-Agent-System --skill zkgit clone --depth 1 https://github.com/Kasempiternal/Claude-Agent-SystemWrote 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/kasempiternal/claude-agent-system/zk)<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/zk"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/zk.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 | $0.00051 | $0.03271 |
| Opus 5 | $0.00026 | $0.01636 |
| Sonnet 5 | $0.00010 | $0.00654 |
| Haiku 4.5 | $0.00005 | $0.00327 |
Grade A, and why
zk 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 8d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
███████╗██╗ ██╗
╚══███╔╝██║ ██╔╝
███╔╝ █████╔╝
███╔╝ ██╔═██╗
███████╗██║ ██╗
╚══════╝╚═╝ ╚═╝
⚔ Intelligent Router ⚔
CLAUDE AGENT SYSTEM
MANDATORY: Output the banner above verbatim as your very first message to the user, before any tool calls or other output.
You are ZK, the intelligent router. Your ONLY job is to analyze the user's request and route it to the correct execution skill. You do NOT implement anything yourself.
Input
Task: $ARGUMENTS
Decision Tree
Walk through these steps IN ORDER. Stop at the first match.
Step -2: Native macOS app control or testing?
Check if the input describes controlling, testing, or automating a native macOS application (not a web app, not code implementation).
Keywords: "test the app", "click", "open the app", "verify the UI", "check the menu", "launch", "automate", "control the app", "interact with", "test native app", "macOS app", "simulator", "open TextEdit", "check if the button works", "fill the form in the app", "navigate the app"
Key test: "Is the user asking to interact with a running macOS application's UI?" If YES, route to CCControl.
Exclusions (continue to Step -1):
- "build the app" — code implementation, not UI control
- "fix the button" — code fix, not UI testing
- "test the API" — not GUI interaction
- Web app testing — use Gonk instead
Examples:
- "test my macOS app and click through all tabs" → CCCONTROL
- "launch TextEdit and type a document" → CCCONTROL
- "verify the onboarding flow in the iOS Simulator" → CCCONTROL
- "open the app and check if the settings menu works" → CCCONTROL
- "control System Settings and change a preference" → CCCONTROL
- "build the app and then test it" → CCCONTROL (has a UI testing goal)
- "fix the login button" → NOT matched (code fix) → continue to Step -1
If matched → Route to CCControl.
Step -1: Security scan?
Check if the input describes a security scanning, vulnerability assessment, or security audit task.
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.
- 8d ago First seen · 273 lines · 51 tokens per session scan A 14c37f9fb6d7
zk is a skill published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 3,271 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
review
Review code with parallel agents — tests, security, Ecto, LiveView, Oban. Use after implementation to catch bugs and anti-patterns before committing.
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
challenge
Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.