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 skills/aaronsb/claude-code-config/wormholenpx skills add aaronsb/claude-code-config --skill wormholegit clone --depth 1 https://github.com/aaronsb/claude-code-configWrote 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/aaronsb/claude-code-config/wormhole)<a href="https://agentmods.dev/skills/aaronsb/claude-code-config/wormhole"><img src="https://agentmods.dev/badge/skills/aaronsb/claude-code-config/wormhole.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 | $0.00054 | $0.01265 |
| Opus 5 | $0.00027 | $0.00633 |
| Sonnet 5 | $0.00011 | $0.00253 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade B, and why
wormhole scanned grade B with 1 finding 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Arch Linux | `sudo pacman -S magic-wormhole` | How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Magic Wormhole File Transfer
Secure, simple transfers between computers using magic-wormhole codes.
When to Suggest Wormhole
| Scenario | Tool |
|---|---|
| Ad-hoc transfer between two machines, no prior setup | wormhole |
| Recurring transfers, SSH already configured | scp, rsync |
| Transfer within same machine or LAN with shared filesystem | cp, rsync |
| Transfer to/from cloud storage | provider CLI (aws s3, gsutil, etc.) |
Step 0: Check Installation
command -v wormhole 2>/dev/null && echo "installed" || echo "missing"
If missing, detect the platform and install:
uname -s # Darwin = macOS, Linux = check distro
cat /etc/os-release 2>/dev/null | grep -E '^(ID|ID_LIKE)='
| Platform | Command |
|---|---|
| Arch Linux | sudo pacman -S magic-wormhole |
| macOS (Homebrew) | brew install magic-wormhole |
| Debian / Ubuntu | sudo apt install magic-wormhole |
| Fedora | sudo dnf install magic-wormhole |
| pip (fallback) | pip install magic-wormhole |
Use AskUserQuestion to confirm the install method before running it. Stop the skill flow until installation succeeds.
Step 1: Determine Mode
There are two modes depending on who is running the skill:
- Interactive — a human is in the loop. Use
AskUserQuestionfor choices, plain text for free-form values (codes, text content). - Automated — a subagent is running this. All parameters (path, code, destination) must be provided in the prompt. No elicitation, no blocking waits for human input.
If you are a subagent, skip all AskUserQuestion calls and use the parameters from your task prompt directly.
Step 2: Ask What They Want To Do
Interactive: Use AskUserQuestion:
- Send a file — transfer a file to another machine
- Send a directory — transfer an entire directory (sent as zip)
- Send text — send a short text snippet
- Receive — receive an incoming transfer using a wormhole code
Automated: The operation, path/code, and destination must be specified in the task prompt.
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.
- 3d ago First seen · 147 lines · 54 tokens per session scan B cab1f7f1367c
wormhole is a skill published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 1,265 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
achieving-cmmc-level-2-compliance
Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when…
task-planning-arch
计算任务 gap 并产出下一步可执行子任务 List[TaskSpec];gap 已闭返回空数组。对齐 arch 场景(架构师名册/技术栈概览/双视角分析)确定式分解——按根目标交付物集合 + donechildren 查表(参照 task-planning storage 特例,非自由 LLM 分解)。.
task-search
在框架预查的候选 bot 集里决出执行者(who)与协作方式(how),返回 4 态 SearchResult(HITSINGLE/HITGROUP/HITMULTIBOTS/MISS)。对齐案例剧本确定式映射。.
escalation-governance
Assess whether to escalate models. Use when evaluating reasoning depth.
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
silicon-throne
硅基圣座总控核心，以神谕式统御把零散任务压成 末将-first 之文明工程.