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 arm-svegit 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/arm-sve)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/arm-sve"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/arm-sve/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/arm-sve"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/arm-sve.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 | $0.00062 | $0.02189 |
| Opus 5 | $0.00031 | $0.01094 |
| Sonnet 5 | $0.00012 | $0.00438 |
| Haiku 4.5 | $0.00006 | $0.00219 |
Grade A, and why
arm-sve 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arm SVE and SVE2
Contract
| Field | Bound contract |
|---|---|
| Trigger | AArch64 code needs vector-length-agnostic SIMD: a NEON loop is being ported, an arm_sve.h kernel is being written, auto-vectorization to SVE is being checked, or SVE register state is being inspected in GDB. |
| Authority | Reversible local: writes only the source files the user names; rollback is reverting them in version control. No remote mutation. |
| Side effect | New or edited C sources. Runs the binary on the host or under QEMU for verification. |
| Done | The kernel compiles with -march=armv9-a+sve2, produces the same result as the scalar reference for lengths that are not a multiple of the vector length, and runs correctly at two different vector lengths (hardware and QEMU, or two QEMU sve<N> settings). |
Inputs
- Source loop or NEON kernel to port, with a scalar reference to compare against.
- Target machines and their SVE level: Graviton3 (Neoverse V1) has SVE, Graviton4 (Neoverse V2) has SVE2, Apple M1 through M3 have NEON only, Apple M4 has SME with streaming SVE and no non-streaming SVE.
- Compiler: GCC or Clang, and version (
gcc --version,clang --version). - GDB version if debugging (
gdb --version).
Procedure
-
Confirm the hardware and the compiler agree. Vector length (VL) is 128 to 2048 bits in 128-bit steps and is fixed per CPU; the code must not assume it. Done when:
/proc/cpuinfolistssve(andsve2if needed) and the compiler defines__ARM_FEATURE_SVEunder the chosen-march.grep -o -m1 -E 'sve2?' /proc/cpuinfo clang --target=aarch64-linux-gnu -march=armv9-a+sve2 -dM -E - </dev/null | grep __ARM_FEATURE_SVE -
Write the kernel with predicates instead of a scalar tail.
svwhilelt_b32(i, n)is true for lanes withi + lane < n, so the last iteration is partial with no cleanup loop.svcntw()returns the 32-bit lanes per vector at runtime. Done when: the loop below matches the scalary[i] += alpha * x[i]forn = 0,n = 1,n = svcntw() - 1, andn = 3 * svcntw() + 1.
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 · 118 lines · 62 tokens per session scan A 7d0000cc941b
arm-sve is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 62 tokens to every session and 2,189 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
bounded-model-checking-c
Use when C or C++ code needs memory-safety or undefined-behavior guarantees proved with CBMC, or ACSL contracts checked with Frama-C Eva or WP. Not for choosing the proof policy: use proof-driven.
cpp-modules
C++20 modules skill for modern C++ projects. Use when working with named modules, module partitions, header units, CMake MODULESOURCES, Clang -fmodules-ts, BMI caching issues, or migrating from headers to modules. Activates on queries about C++20 modules, import statements, module interface units, header units, or BMI…
openmp
OpenMP skill for shared-memory parallel programming. Use when writing parallel for loops, reductions, task parallelism, SIMD directives, GPU offloading, or profiling with Score-P/TAU. Activates on queries about OpenMP, pragma omp, schedule static dynamic, reduction, false sharing, or OMPNUMTHREADS.
cpp
Use when writing modern C++ (17/20/23). Covers RAII, smart-pointer ownership, move semantics, ranges, concepts, and eliminating undefined behavior with sanitizers.
arduino-code-generator
Generate Arduino and embedded C++ snippets for sensors, actuators, buses, state machines, timing, data logging, and hardware abstraction. Use when a user requests implementation code and provide the exact board, framework, toolchain, pins, voltage, memory, and library versions first. Bundled templates target UNO…
unreal-gas
Expert guide for Unreal Engine 5.x Gameplay Ability System (GAS) C++ development. Covers AbilitySystemComponent, GameplayAbilities, GameplayEffects, Attributes/AttributeSets, GameplayTags, GameplayCues, AbilityTasks, prediction/replication, and common patterns. Use when the user asks about GAS, gameplay abilities…