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 anivaryam/anivaryam-plugins --skill tunnelgit clone --depth 1 https://github.com/anivaryam/anivaryam-pluginsWrote 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/anivaryam/anivaryam-plugins/tunnel)<a href="https://agentmods.dev/skills/anivaryam/anivaryam-plugins/tunnel"><img src="https://agentmods.dev/badge/skills/anivaryam/anivaryam-plugins/tunnel/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/anivaryam/anivaryam-plugins/tunnel"><img src="https://agentmods.dev/badge/skills/anivaryam/anivaryam-plugins/tunnel.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 | $0.00176 | $0.02464 |
| Opus 5.5 | $0.00070 | $0.00986 |
| Sonnet 5.5 | $0.00035 | $0.00493 |
| Haiku 4.5 | $0.00018 | $0.00246 |
Grade A, and why
tunnel scanned grade A 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf https://test.relay.example.com/ # hit it (subdomain mode) How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tunnel
Self-hosted ngrok alternative. CLI client + relay server. You own the relay, so the public URL stays under your domain.
Repo: github.com/anivaryam/tunnel. Binary: tunnel (install via brokit install tunnel, release tarball, or go install — note: go install skips daemon mode).
When to reach for it
- Need a public URL for a local dev server, webhook receiver, or demo.
- Need a public URL for TCP (Postgres, SSH) or UDP (DNS, game server).
- ngrok rate limits / quotas are blocking work.
- You control DNS and want the public URL under your own domain.
Do NOT use for: production traffic (deploy the app properly), bypassing corporate firewall policy, or anything where the public URL is the final delivery surface.
One-time setup
tunnel config set-server https://relay.example.com
tunnel config set-token <your-token>
tunnel config show # confirm (token masked)
tunnel doctor # validate config + relay reachability
Config lives at ~/.tunnel/config.yml (mode 0600). The doctor step is cheap and catches the common breakages (bad URL, unreachable relay, missing token) before you try to expose anything.
Expose a port
tunnel http 3000 # random 16-char ID
tunnel http 3000 --name api # stable, requestable name
tunnel http 3000 --inspect # local inspector at :4040
tunnel tcp 5432 # Postgres / SSH / etc.
tunnel udp 53 # DNS / game server / etc.
URL form depends on the relay's BASE_DOMAIN:
- Path mode (no
BASE_DOMAIN):https://relay.example.com/t/<id>/ - Subdomain mode (
BASE_DOMAIN=relay.example.com):https://<id>.relay.example.com/
Named tunnels follow the same rule with <name> in place of <id>. Name rules: 1–32 chars, [a-z0-9-], no leading/trailing hyphen. Reserved names (dashboard, metrics, mail, login, app, docs, status, staging, prod, …) are rejected — full list in the relay's internal/server/names.go.
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.
- 2mo ago First seen · 169 lines · 0 tokens per session scan A 837b631d1355
tunnel is a skill published in the GitHub repository anivaryam/anivaryam-plugins (2 stars, last pushed 5mo ago), licensed MIT. It adds 176 tokens to every session and 2,464 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
tunnel compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tunnelanivaryam/anivaryam-plugins | Skill | 2 | 5mo ago | MIT | A | 176 | Claude Code |
| gke-compute-classesgoogle/skills | Skill | 23k | today | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 23k | today | Apache-2.0 | A | 85 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 23k | today | Apache-2.0 | A | 171 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | today | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | today | MIT | A | 78 | Claude Code |