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 xmake-io/xmake-skills --skill xmake-policygit clone --depth 1 https://github.com/xmake-io/xmake-skillsWrote 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/xmake-io/xmake-skills/xmake-policy)<a href="https://agentmods.dev/skills/xmake-io/xmake-skills/xmake-policy"><img src="https://agentmods.dev/badge/skills/xmake-io/xmake-skills/xmake-policy/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/xmake-io/xmake-skills/xmake-policy"><img src="https://agentmods.dev/badge/skills/xmake-io/xmake-skills/xmake-policy.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 | $0.00085 | $0.02054 |
| Opus 5 | $0.00043 | $0.01027 |
| Sonnet 5 | $0.00017 | $0.00411 |
| Haiku 4.5 | $0.00009 | $0.00205 |
Grade A, and why
xmake-policy 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 12d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
set_policy — Feature Toggles
Policies are named feature toggles xmake exposes via set_policy("<name>", <value>). They replace ad-hoc flags with a stable, versioned API — enabling a feature like "C++20 modules" or "address sanitizer" is a single call that works across compilers.
Policies live in xmake.lua and can be set at project or target scope.
1. Basic usage
-- project-wide
set_policy("build.warning", true)
target("app")
-- per-target
set_policy("build.optimization.lto", true)
set_policy("build.sanitizer.address", true)
- Project-scope (at top of
xmake.lua) — applies to every target. - Target-scope (inside
target(...)) — only that target. - Target values override the project value.
Reading a policy from script:
on_load(function (target)
if target:policy("build.warning") then
...
end
end)
2. Commonly-used policies, grouped
Compilation / warnings
set_policy("build.warning", true) -- show compile warnings (default off)
set_policy("check.auto_ignore_flags", false) -- don't auto-filter unknown flags
set_policy("check.auto_map_flags", false) -- don't auto-map gcc→msvc flag names
Optimization / linking
set_policy("build.optimization.lto", true) -- enable LTO
set_policy("build.merge_archive", true) -- merge all static archives into one
set_policy("build.release.strip", true) -- strip release binaries (v3.0.8+)
set_policy("build.rpath", true) -- auto-emit rpath for shared deps
set_policy("install.rpath", true) -- same at install time
set_policy("build.intermediate_directory", true) -- use an intermediate dir per target
Sanitizers (GCC/Clang)
set_policy("build.sanitizer.address", true) -- -fsanitize=address
set_policy("build.sanitizer.thread", true) -- -fsanitize=thread
set_policy("build.sanitizer.memory", true) -- -fsanitize=memory
set_policy("build.sanitizer.leak", true) -- -fsanitize=leak
set_policy("build.sanitizer.undefined", true) -- -fsanitize=undefined
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.
- 12d ago First seen · 233 lines · 85 tokens per session scan A 8af86140e13c
xmake-policy is a skill published in the GitHub repository xmake-io/xmake-skills (24 stars, last pushed 19d ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,054 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
zoom-meeting-sdk-unreal
Zoom Meeting SDK for Unreal Engine wrapper integrations. Use when building Unreal projects that embed Zoom meetings with C++ and Blueprint wrappers, including wrapper-to-SDK mapping concerns.
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…
cpu-kernels
Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes a two-phase workflow: Phase 1 correctness (generic → AVX2) and Phase 2 performance exploration (AVX512 with branching trial loop), runtime CPU dispatch, OpenMP…
cudaq-importing
Use when porting circuits from another framework (e.g. Qiskit) into CUDA-Q kernels while preserving the source algorithm and validation fidelity.
llvm-learning
Comprehensive learning resources and tutorials for LLVM, Clang, and compiler development. Use this skill when helping users learn LLVM internals, find educational resources, or understand compiler concepts.