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/tatuke/agent-switch/transport-skillnpx skills add tatuke/agent-switch --skill transport-skillgit clone --depth 1 https://github.com/tatuke/agent-switchWrote 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/tatuke/agent-switch/transport-skill)<a href="https://agentmods.dev/skills/tatuke/agent-switch/transport-skill"><img src="https://agentmods.dev/badge/skills/tatuke/agent-switch/transport-skill.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 | $0.00021 | $0.01331 |
| Opus 5 | $0.00010 | $0.00665 |
| Sonnet 5 | $0.00004 | $0.00266 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
transport-skill 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transport Skill — Guided Configuration
Use this skill when you need to configure and execute an ASTP bundle transfer between two agent platforms.
Flow
Step 1: Source Agent
Ask the user:
"Which agent platform is the SOURCE for this transfer?" Options: opencode, claude-code, codex, gemini-cli, hermes, cursor, kiro, or custom name
Record the answer as sourceAgent.
Step 2: Target Agent
Ask the user:
"Which agent platform is the TARGET for this transfer?" Same options as Step 1.
Record as targetAgent.
Validate: source ≠ target (warn if same, ask user to confirm).
Step 3: Source Endpoint
Ask the user:
"Enter the source endpoint in user@host format (e.g., [email protected]):"
Validate: must contain exactly one @ separating user and host.
Ask: "Source SSH port? (default: 22)"
Step 4: Source Pack Path
Ask the user:
"Enter the path on the source host where the ASTP bundle is located (e.g., /home/alice/.astp-bundle/):"
Use your shell execution tool to check if the path exists (if source is local):
test -e <sourcePackPath> && echo "exists" || echo "not found"
If not found, warn the user and offer to retry.
Step 5: Target Endpoint
Same as Step 3, for the target host.
Step 6: Target Pack Path
Same as Step 4, for the target host.
Step 7: Connectivity Test
Use your shell execution tool to verify connectivity:
For local hosts: skip SSH test. For remote hosts:
ssh -o BatchMode=yes -o ConnectTimeout=5 -o StrictHostKeyChecking=no -p <port> <user@host> exit
If the test fails, classify the error:
Permission denied→ auth issue, suggest checking SSH keysCould not resolve hostname→ DNS issue, suggest checking host/VPNConnection timed out→ network issue, suggest checking firewall/VPNConnection refused→ SSH not running, suggest checking remote service
Present results to the user. If blocking errors, offer: retry / save plan only / cancel.
Step 8: Preview
Present a summary table to the user:
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 · 181 lines · 21 tokens per session scan A 6295bb2df687
transport-skill is a skill published in the GitHub repository tatuke/agent-switch (2 stars, last pushed 12d ago), licensed MIT. It adds 21 tokens to every session and 1,331 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 2026-08-31.
Other skills, from other repositories
agent-pack-n-go
Clone your OpenClaw Agent to a new device — configs, memory, skills, credentials, everything. Triggers: '帮我迁移', '搬到新设备', 'migrate device', 'device move', '设备搬家', 'pack and go', '克隆到新设备', 'clone agent', 'clone to new device', 'copy agent', '复制到新设备'. Agent packs configs, memory, skills, credentials on old device…
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
gmgn-wallet-score
Score any wallet address across three angles — profitability (a real track-record score: is this trader actually good?), copy-tradeability (can YOU actually capture what it makes, plus a latency/slippage/gas backtest), and Dev reputation (if it's mostly a token launcher, how trustworthy are its launches) — plus…
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…
orch
AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.
image
Extract text from images using a vision LLM.