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 OutlineDriven/outline-driven-development --skill apple-silicongit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/apple-silicon)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/apple-silicon"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/apple-silicon/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/outlinedriven/outline-driven-development/apple-silicon"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/apple-silicon.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 | $0.00052 | $0.01954 |
| Opus 5 | $0.00026 | $0.00977 |
| Sonnet 5 | $0.00010 | $0.00391 |
| Haiku 4.5 | $0.00005 | $0.00195 |
Grade A, and why
apple-silicon 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 3d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Silicon
Contract
| Field | Bound contract |
|---|---|
| Trigger | Code runs on an M-series Mac and needs to be checked for page-size assumptions, moved onto Accelerate or Metal for matrix work, profiled with Instruments or the command-line memory tools, or diagnosed for Rosetta 2 translation. |
| Authority | Read-only: reads the host through sysctl, arch, lipo, file, xctrace, vmmap, heap, leaks, and sample, and writes traces only under the output path the user names; rollback is deleting those trace files. No remote mutation. |
| Side effect | Trace and sample files in the named output directory. Profiling attaches to the target process. |
| Done | The report names the chip and its features from sysctl, states whether the binary runs native or translated, lists every page-size assumption found in the code with its fix, and points each hotspot at the Accelerate, Metal, or threading change that addresses it. |
Inputs
- The binary or source under review, and how it is launched.
- Whether the workload is matrix or convolution heavy (Accelerate and Metal candidates) or general CPU work.
- Output directory for traces.
- Xcode command-line tools installed (
xcode-select -pprints the path).
Procedure
-
Read the hardware. All CPU cores, the GPU, and the Neural Engine share one DRAM pool, so a Metal buffer in shared storage mode needs no copy to reach the GPU, and one process's memory total includes its GPU allocations. Done when: chip name, core counts, memory size, cache line, and page size are recorded.
sysctl -n machdep.cpu.brand_string sysctl hw.physicalcpu hw.logicalcpu hw.memsize sysctl hw.cachelinesize sysctl hw.pagesize # 16384 on Apple Silicon macOS sysctl hw.optional.arm # FEAT_* flags; grep for the one in questionM4 exposes
hw.optional.arm.FEAT_SME; no M-series chip through M4 exposes non-streaming SVE, so SVE intrinsics outside streaming mode raiseSIGILLthere (seearm-sve).
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.
- 3d ago First seen · 133 lines · 52 tokens per session scan A b37efcbea98f
apple-silicon is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,954 once invoked, about $0.0003 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 2026-09-06.
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…
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…
evpn-vxlan-fabric
EVPN/VXLAN fabric audit and troubleshooting — VTEPs, VNIs, route types, multihoming, underlay/overlay validation. Use when troubleshooting VXLAN overlay reachability, auditing leaf-spine fabric health, debugging silent hosts or asymmetric flooding, or validating anycast gateway and ESI multihoming state.
triaging-robot-logs
Use when investigating a robot log or flight log with bagel — finding events, anomalies, or "what happened around X" in rosbags, MCAP, CAN, MDF4, ULog, or Betaflight files. Routes to the server's triage capability.
yam-robot-debugging
Use for YAM real-robot debugging: saved-script edits, physical runs, artifact inspection, autonomous patch-and-retry loops, and compact runtime context updates.
diagnose-hid-keycodes
Find out what an unknown USB/Bluetooth HID button actually emits without assuming the label or documentation. Uses Karabiner's.