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 koolamusic/claudefiles --skill wildcard-proxygit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/koolamusic/claudefiles/wildcard-proxy)<a href="https://agentmods.dev/skills/koolamusic/claudefiles/wildcard-proxy"><img src="https://agentmods.dev/badge/skills/koolamusic/claudefiles/wildcard-proxy/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/koolamusic/claudefiles/wildcard-proxy"><img src="https://agentmods.dev/badge/skills/koolamusic/claudefiles/wildcard-proxy.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 | $0.00118 | $0.02260 |
| Opus 5.5 | $0.00047 | $0.00904 |
| Sonnet 5.5 | $0.00024 | $0.00452 |
| Haiku 4.5 | $0.00012 | $0.00226 |
Grade B, and why
wildcard-proxy scanned grade B with 2 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 7d 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.
3. **Ports 80 and 443** reachable from the internet and not held by another server: `sudo ss -tlnp '( sport = :80 or sport = :443 )'`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Wildcard DNS**: `*.{{DOMAIN}}` resolves to this server. Check with a label nobody has used: `dig +short zq.{{DOMAIN}}` should print the server's public IP (`curl -4 -s ifconfig.me`; also check `dig +short AAAA` if t How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wildcard Proxy
One Caddy config, installed once per server, that routes https://<label>.<domain>/ to 127.0.0.1:<port>. After install, exposing a service is just binding it to a loopback port. A short name is one line in a names file.
How a label becomes a port
Checked in this order; first match wins.
| Label | Rule | Example |
|---|---|---|
| short name | listed in wildcard-proxy.names |
ui → 4001 |
| port number | matches the allowed port regex | 4012 → 4012 |
| any two letters | 1 + two-digit alphabet position of each letter (a=00 … z=25) |
ab → 10001, hz → 10725, zz → 12525 |
The computed range is 10000–12525. Port for letters xy = 10000 + 100·pos(x) + pos(y). A short name overrides that name's computed port: ui would otherwise be 12008.
Anything else (abc, a1, 3000 outside the ranges, deeper subdomains) gets no certificate and no route.
Inputs
| Placeholder | Meaning | Default |
|---|---|---|
{{DOMAIN}} |
the wildcard parent, e.g. host.example.net |
ask the user |
{{DOMAIN_RE}} |
same, dots escaped | derived |
{{PORT_RE}} |
allowed numeric labels, as regex alternatives | 40[0-9][0-9]|80[0-9][0-9] (4000–4099, 8000–8099) |
{{ASK_PORT}} |
loopback port for the certificate gate | 5555 |
Use [0-9][0-9], not [0-9]{2}, in PORT_RE. Caddyfile braces look like placeholders.
Prerequisites — check before installing
- Caddy v2 installed and running as a systemd service:
caddy version,systemctl is-active caddy. - Wildcard DNS:
*.{{DOMAIN}}resolves to this server. Check with a label nobody has used:dig +short zq.{{DOMAIN}}should print the server's public IP (curl -4 -s ifconfig.me; also checkdig +short AAAAif the server has IPv6). - Ports 80 and 443 reachable from the internet and not held by another server:
sudo ss -tlnp '( sport = :80 or sport = :443 )'. - No other
on_demand_tlsblock in/etc/caddy/Caddyfile. Caddy allows oneaskendpoint. If one exists, stop and ask the user. Merging two gates is a design decision. The exception is an older inline version of this same config: replace it with the import, and keep the static sites. ASK_PORTfree:ss -tln | grep ':{{ASK_PORT}} 'prints nothing, or only Caddy itself when migrating an older version of this config.- Nothing private already listening on a routable port. After install, anything bound to loopback on a routed port is public. Before install, list what is already there:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 148 lines · 118 tokens per session scan B 4fb72ccc5bd6
wildcard-proxy is a skill published in the GitHub repository koolamusic/claudefiles (130 stars, last pushed 4d ago), licensed MIT. It adds 118 tokens to every session and 2,260 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".