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 compiler-optimizations-deepgit 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/compiler-optimizations-deep)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/compiler-optimizations-deep"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/compiler-optimizations-deep.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.01668 |
| Opus 5 | $0.00024 | $0.00834 |
| Sonnet 5 | $0.00010 | $0.00334 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade A, and why
compiler-optimizations-deep 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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compiler optimizations, deep
Contract
| Field | Bound contract |
|---|---|
| Trigger | A hot loop stayed scalar at -O3, assembly shows spills, -O3 runs slower than -O2, GCC and Clang produce different code for the same source, or a profile-guided or post-link optimization is being planned or produced no gain. |
| Authority | Reversible local: writes only instrumented binaries, profiles, and remark files under a scratch directory named in the report; rollback is deleting that directory. No remote mutation. |
| Side effect | Runs the compiler with remark flags, and when asked, an instrumented build and a training run. Project files are not modified. |
| Done | Each symptom is attributed to a named pipeline stage with the compiler's own remark or output as evidence, and each fix is stated as a source change, a flag, or a workflow step the user can apply. |
Inputs
- Source and the exact compile command (required): the flags decide which passes run.
- Compiler and version (required if not inferrable):
clang --versionorgcc --version. Grounded current stables are LLVM/Clang 23.1.0 and GCC 16.2; flags below are confirmed against Clang 23.1.0. - The symptom (required): a loop that did not vectorize, spills in a function, a slower
-O3, or a PGO or BOLT plan. - A representative workload (required for PGO or BOLT): the input the production binary will see.
Procedure
-
Place the symptom in the pipeline. After the frontend emits LLVM IR (or GIMPLE in GCC), the mid-level passes run (dead code elimination, GVN, loop-invariant code motion, inlining), then loop passes (unroll, vectorize), then codegen preparation, instruction selection, register allocation, and scheduling. Pass order matters: LICM must hoist an invariant before the vectorizer can prove the loop simple. Done when: the stage is named.
-
For a loop that did not vectorize, ask the compiler why:
clang -O3 -Rpass=loop-vectorize -Rpass-missed=loop-vectorize -Rpass-analysis=loop-vectorize -c foo.c
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.
- yesterday First seen · 86 lines · 48 tokens per session scan A 7ff1ce88bd6e
compiler-optimizations-deep is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,668 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
cpp-pro
Writes, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and high-performance systems techniques. Use when building or refactoring C++ code requiring concepts, ranges, coroutines, SIMD optimization, or careful memory management — or when addressing performance…
memory-safety-patterns
Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.
cpp
Comprehensive C/C++ programming reference covering everything from C11-C23 and C++11-C++23, system programming, CUDA GPU computing, debugging tools, Rust interop, and advanced topics. Use for: C/C++ questions, C/C++ interview preparation, modern language features, RAII/memory management, templates/generics, CUDA…
cpp-debugging
Use when a C++ failure involves memory lifetime, undefined behavior, native crashes, or debugger-only state — debug with symbols, sanitizers, and platform-native debuggers before patching symptoms.
gcc
GCC compiler skill for C/C++ projects. Use when selecting optimization levels, warning flags, debug builds, LTO, sanitizer instrumentation, or diagnosing compilation errors with GCC. Covers flag selection for debug vs release, ABI concerns, preprocessor macros, profile-guided optimization, and integration with build…
cuopt-developer
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.