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 keyelifeai/keye-open-skills --skill keye-network-optimizergit clone --depth 1 https://github.com/keyelifeai/keye-open-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/keyelifeai/keye-open-skills/keye-network-optimizer)<a href="https://agentmods.dev/skills/keyelifeai/keye-open-skills/keye-network-optimizer"><img src="https://agentmods.dev/badge/skills/keyelifeai/keye-open-skills/keye-network-optimizer/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/keyelifeai/keye-open-skills/keye-network-optimizer"><img src="https://agentmods.dev/badge/skills/keyelifeai/keye-open-skills/keye-network-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.02370 |
| Opus 5 | $0.00047 | $0.01185 |
| Sonnet 5 | $0.00019 | $0.00474 |
| Haiku 4.5 | $0.00009 | $0.00237 |
Grade A, and why
keye-network-optimizer 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 11d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keye Network Optimizer
Use this workflow on macOS. Preserve connectivity, proxy access, VPN access, and remote sessions while collecting comparable evidence.
Non-negotiable safety rules
- Follow this order: diagnose, make the smallest reversible change, retest.
- Never run destructive resets such as deleting network services, removing VPN profiles, resetting all network preferences, or unloading system daemons.
- Do not use
sudo, disable a VPN/TUN/proxy, change MTU, or terminate a process without first explaining the effect and obtaining user approval. - Treat a user requirement to keep a proxy for GFW access as a hard constraint.
- Record the current value and an exact rollback command before every change.
- Do not hardcode interface names, gateway addresses, proxy ports, DNS winners, or network service names from a previous run.
- Run throughput, ping, DNS, and traffic sampling sequentially. Concurrent tests create load and invalidate latency and packet-loss comparisons.
- Keep before and after conditions identical. A TUN-on versus TUN-off comparison is a separate A/B test and must be labeled as such.
Phase 1: establish scope and safety
- Confirm the host is macOS and note whether the user is local or connected through SSH, Screen Sharing, a VPN, or another remote-control path.
- Ask whether proxy/VPN/TUN connectivity is mandatory if the user has not said.
- Ask other users and applications to pause large transfers for the baseline.
- Create a timestamped evidence directory and keep raw before/after outputs.
- Do not make changes until all required before measurements are complete.
Use shell variables with task-specific names. If a multi-line snippet uses Bash
arrays, run it with bash -lc rather than relying on zsh behavior.
Phase 2: collect the before baseline
Collect these snapshots first:
sw_vers
scutil --nwi
route -n get default
scutil --dns
scutil --proxy
networksetup -listallhardwareports
networksetup -listallnetworkservices
networksetup -listnetworkserviceorder
What ships with it
1 file 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.
- 11d ago First seen · 248 lines · 94 tokens per session scan A 67aaa0b44642
keye-network-optimizer is a skill published in the GitHub repository keyelifeai/keye-open-skills (10 stars, last pushed 12d ago), licensed MIT. It adds 94 tokens to every session and 2,370 once invoked, about $0.0005 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
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
competition-firmware-layout
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
catc-troubleshoot
Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when a device is unreachable, a user reports connectivity problems, an interface…