Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentnpx agentmods add skills/outlinedriven/outline-driven-development/dpdkWrote 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/dpdk)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/dpdk"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/dpdk/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/dpdk"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/dpdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 28 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 30 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Privilege Escalation · line 28 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 30 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 31 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 32 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 56 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 57 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 58 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 124 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00050 | $0.02029 |
| Opus 5 | $0.00025 | $0.01014 |
| Sonnet 5 | $0.00010 | $0.00406 |
| Haiku 4.5 | $0.00005 | $0.00203 |
Grade B, and why
dpdk 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
echo 1024 | sudo tee /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DPDK
Contract
| Field | Bound contract |
|---|---|
| Trigger | Building a userspace DPDK dataplane: EAL init, port and PMD setup, rte_eth_rx_burst/tx_burst, mbuf pools, rte_ring, RSS, testpmd validation, or virtio-under-QEMU testing. |
| Authority | Read-only. Writes nothing. Chat output only. No remote mutation. |
| Side effect | Returns setup commands, driver code, and a validation plan. No source files are modified. |
| Done | The hugepage and EAL setup, the port init and burst loop, the RSS configuration, and a testpmd validation run are delivered. |
Inputs
- Target NIC and driver (required): the PCI address, the current kernel driver, and the PMD that will own it.
- Core and memory layout (optional): lcore list, memory channels, hugepage size. Defaults to one lcore per RX queue.
- Test plan (optional): testpmd forward mode and traffic generator, when the request includes validation.
Procedure
-
Set up hugepages before EAL starts. EAL maps hugepages at startup and fails when pages are short.
echo 1024 | sudo tee /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages # 1 GiB pages help TLB reach on large-memory boxes echo 4 | sudo tee /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages sudo mkdir -p /mnt/huge sudo mount -t hugetlbfs nodev /mnt/huge grep Huge /proc/meminfoDone when:
/proc/meminforeports the requested hugepage count. -
Initialize EAL.
rte_eal_initconsumes its arguments and returns how many it took; the rest belong to the application.int ret = rte_eal_init(argc, argv); if (ret < 0) rte_exit(EXIT_FAILURE, "EAL init failed\n"); return run_dataplane(argc - ret, argv + ret);./dpdk_app -l 0-3 -n 4 --huge-dir=/mnt/huge -- -p 0x3 # -l: lcore list -n: memory channels # --proc-type=primary --file-prefix=pfx for a second instanceDone when: the app starts with its lcore list and the argument split is respected.
-
Bind the NIC to a PMD and configure the port. Physical NICs need
vfio-pci(with IOMMU) or auiodriver.
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 · 158 lines · 50 tokens per session scan B c9f3436f202a
dpdk is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,029 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
automatic-cybernetic-flow-design
Use when the user wants a cybernetic flow design document for an interactive system. Specifies sensors, actuators, feedback paths, delays, and oscillation risk, and writes the design to a named local file. Not for implementing or deploying the system.
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
unifi-protect
How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…
mi300-hip-vs-nvidia
MI300 HIP programming differences vs NVIDIA—wavefront vs warp, memory hierarchy, MFMA usage, occupancy, and profiling pitfalls.
gpu-memory-model
GPU memory model skill for SIMT execution and memory hierarchy. Use when analyzing warp divergence, memory coalescing, shared memory bank conflicts, cache behavior, atomics, or occupancy tradeoffs. Activates on queries about SIMT, warp coalescing, bank conflicts, wavefront, GPU occupancy, or memory-bound kernels.
ios-build-cleanup
Use when the user wants a clean Xcode rebuild by deleting DerivedData and build artifacts. Do not use for diagnosing a specific build error: use ios-build-fix.