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 ohong/agent-skills --skill fast-wifigit clone --depth 1 https://github.com/ohong/agent-skillsWrote 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/ohong/agent-skills/fast-wifi)<a href="https://agentmods.dev/skills/ohong/agent-skills/fast-wifi"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/fast-wifi/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/ohong/agent-skills/fast-wifi"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/fast-wifi.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 | $0.00031 | $0.01719 |
| Opus 5 | $0.00015 | $0.00860 |
| Sonnet 5 | $0.00006 | $0.00344 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade B, and why
fast-wifi 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 10d 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.
- `sudo ifconfig awdl0 down` and `sudo ifconfig llw0 down` can reduce periodic Wi-Fi latency spikes from Apple peer interfaces, but they need an admin password and can affect AirDrop/AirPlay/Continuity. Restore with `up` How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fast Wi-Fi
Goal
Improve the active connection when possible, and prove what changed with before/after measurements. Treat the current network state as authoritative; if the user names an SSID, verify the Mac is actually on it before acting. On public or captive networks, prefer reversible joins, GUI-assisted authentication, and clear evidence over speculative tuning.
Core Workflow
-
Identify the active interface and route.
- Prefer
networksetup -listallhardwareportsto confirm Wi-Fi isen0. - Run
route -n get default,scutil --nwi,ipconfig getsummary en0, andsystem_profiler SPAirPortDataType. - Use
scripts/wifi_snapshot.sh en0for a compact first pass.
- Prefer
-
Establish a baseline before changing anything.
- Record SSID or network evidence, gateway, IP, PHY mode, band, channel width, signal/noise, transmit rate, DNS, proxy state, first-hop latency, public latency, captive/auth state, and
networkQuality -I en0 -s. - Separate idle latency from loaded throughput. First-hop latency to the gateway proves whether the issue starts on the local Wi-Fi/AP path.
- If comparing close candidates, take at least two samples or treat download/upload differences under about 10% as noise. Prefer the network with lower loss, lower first-hop latency, and better loaded responsiveness when throughput is effectively tied.
- Record SSID or network evidence, gateway, IP, PHY mode, band, channel width, signal/noise, transmit rate, DNS, proxy state, first-hop latency, public latency, captive/auth state, and
-
Interpret the bottleneck.
- Weak signal: RSSI worse than about
-70 dBm, poor SNR, low MCS, or low transmit rate. - Bad AP/channel contention: good RSSI but narrow channel width, low or bouncing transmit rate, first-hop jitter/loss, or many neighboring APs on the same channel.
- Public/captive shaping: open network, option 82 or captive-network markers, good RSSI but very low throughput and high first-hop latency.
- VPN/proxy issue: default route through
utun*, active VPN process, or configured proxy. - Private Relay or per-network privacy issue: captive portals, rate-limited sites, or network-auth pages fail while basic IP connectivity works; inspect "Limit IP address tracking" and Private Wi-Fi Address mode only when symptoms point there.
- Background traffic issue: speed test responsiveness is poor and Activity Monitor or
nettopshows sync/backup/media/download traffic competing for the public link. - DNS issue: gateway and public pings are healthy, but resolver queries are slow or failing.
- ISP/uplink issue: first hop is clean but external latency/throughput is poor.
- Weak signal: RSSI worse than about
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.
- 10d ago First seen · 102 lines · 31 tokens per session scan B 14fd46f3444b
fast-wifi is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 10d ago), licensed MIT. It adds 31 tokens to every session and 1,719 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.