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 build-accelerationgit 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/build-acceleration)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/build-acceleration"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/build-acceleration/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/build-acceleration"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/build-acceleration.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 | $0.00044 | $0.01620 |
| Opus 5 | $0.00022 | $0.00810 |
| Sonnet 5 | $0.00009 | $0.00324 |
| Haiku 4.5 | $0.00004 | $0.00162 |
Grade A, and why
build-acceleration 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build acceleration
Reduce C/C++ build times: measure first, then apply caching (ccache, sccache), distributed compilation (distcc), unity builds, precompiled headers, split DWARF, and include pruning.
Contract
| Field | Bound contract |
|---|---|
| Trigger | A C/C++ build is too slow, or the task sets up ccache, sccache, distcc, precompiled headers, unity builds, split DWARF, or IWYU include pruning. |
| Authority | Reversible local: writes only build configuration (CMakeLists.txt, ccache.conf, environment variables) and local build outputs; rollback is version control plus deleting the build directory. No remote mutation. |
| Side effect | Local builds and cache daemons; distcc and sccache contact user-configured workers or storage. |
| Done | The chosen technique is configured and a before/after build time is measured, or the blocker is reported. |
Inputs
- Build system (required): CMake, Make, Meson, or Bazel; gathered from the tree.
- Compiler (required): GCC or Clang; affects flag support.
- Bottleneck evidence (optional): existing timings or a profiler report.
- Cache or distribution infrastructure (optional): shared cache directory, distcc workers, sccache storage backend.
Procedure
- Measure before changing anything. A speedup claim without a baseline is not a claim. Done when: a baseline build time is recorded.
time cmake --build build -j"$(nproc)"
# Per-translation-unit cost, GCC and Clang
cmake -S . -B build -DCMAKE_CXX_FLAGS="-ftime-report"
cmake --build build 2>&1 | grep "Total" | sort -t: -k2 -rn | head -20
# Ninja keeps per-edge timings in build/.ninja_log; inspect with
# ninja -d stats or feed the log to ninjatracing for a Chrome trace
ninja -C build -d stats
- Set up ccache for compiler caching. Done when:
ccache -sshows hits on a rebuild.
apt-get install ccache # Debian/Ubuntu
brew install ccache # macOS
ccache -s # hit rate
ccache --set-config=max_size=20G
ccache -C # clear cache
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.
- 3d ago First seen · 144 lines · 44 tokens per session scan A cdebbec2a9de
build-acceleration is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,620 once invoked, about $0.0002 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.
xmake-targets
Use when configuring targets in xmake.lua — setting kind (binary/static/shared), adding files/includes/links, defining dependencies between targets, and applying per-target compile/link flags.
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…