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 kinhluan/rules-quarkus-skills --skill bazel-expertgit clone --depth 1 https://github.com/kinhluan/rules-quarkus-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/kinhluan/rules-quarkus-skills/bazel-expert)<a href="https://agentmods.dev/skills/kinhluan/rules-quarkus-skills/bazel-expert"><img src="https://agentmods.dev/badge/skills/kinhluan/rules-quarkus-skills/bazel-expert/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/kinhluan/rules-quarkus-skills/bazel-expert"><img src="https://agentmods.dev/badge/skills/kinhluan/rules-quarkus-skills/bazel-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.02523 |
| Opus 5 | $0.00017 | $0.01262 |
| Sonnet 5 | $0.00007 | $0.00505 |
| Haiku 4.5 | $0.00003 | $0.00252 |
Grade A, and why
bazel-expert 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 11d 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bazel-expert
Keyword: bazel | Platforms: gemini,claude,codex
General Bazel & Starlark Expert Skill - Expert guidance on writing idiomatic Bazel rules and optimizing build performance.
Architectural Mandates
- Hermeticity: Actions must only depend on declared inputs
- Granularity: Break large targets into smaller
java_libraryorstarlarkrules - Bzlmod: Always use Bzlmod for external dependency management
- Visibility: Default
visibility = ["//visibility:private"], explicitly widen only as needed
rules_java & Java Toolchains
Toolchain Setup (Bzlmod)
# MODULE.bazel
bazel_dep(name = "rules_java", version = "7.12.4")
java_toolchains = use_extension("@rules_java//java:extensions.bzl", "toolchains")
java_toolchains.toolchain(version = "21")
use_repo(java_toolchains, "remotejdk21_linux")
register_toolchains("@remotejdk21_linux//:jdk")
BUILD.bazel Examples
# Library target with proper granularity
java_library(
name = "user-service",
srcs = glob(["src/main/java/**/*.java"]),
resources = glob(["src/main/resources/**"]),
deps = [
"//common/utils:json-utils",
"@maven//:com_google_guava_guava",
"@maven//:jakarta_inject_jakarta_inject_api",
],
visibility = ["//services:__subpackages__"],
)
# Test target with testonly deps
java_test(
name = "user-service-test",
srcs = glob(["src/test/java/**/*.java"]),
test_class = "com.example.UserServiceTest",
deps = [
":user-service",
"@maven//:org_junit_jupiter_junit_jupiter",
"@maven//:org_assertj_assertj_core",
"@maven//:org_mockito_mockito_core",
],
)
Do vs Don't
# BAD - monolithic target, slow incremental builds
java_library(
name = "everything",
srcs = glob(["src/**/*.java"]),
deps = ["@maven//:all-the-things"],
visibility = ["//visibility:public"],
)
# GOOD - granular targets, fast incremental builds
java_library(
name = "user-model",
srcs = ["src/main/java/com/example/User.java"],
deps = ["@maven//:jakarta_validation_jakarta_validation_api"],
)
java_library(
name = "user-repository",
srcs = ["src/main/java/com/example/UserRepository.java"],
deps = [":user-model", "@maven//:io_quarkus_quarkus_hibernate_orm_panache"],
)
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.
- 11d ago First seen · 308 lines · 34 tokens per session scan A 76cc2bb91fdf
bazel-expert is a skill published in the GitHub repository kinhluan/rules-quarkus-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 2,523 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 2026-08-31.
Other skills, from other repositories
bazel
Bazel build system reference by Google. Covers BUILD files, Starlark rules for C++/Java/Python/Go/Rust, Bzlmod dependency management, query/cquery/aquery, remote caching and execution, cross-compilation, custom rules, and monorepo patterns.
bazel-docs
Bazel 9.x — fast, hermetic, multi-platform build system. BUILD files, rules, macros, Bzlmod, remote execution.
turborepo
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…
python-guidelines
This skill should be used when writing, reviewing, or refactoring Python code. Covers code integration, idiomatic patterns, docstring formatting, anti-abstraction rules, and software engineering basics.
unity-vrc-udon-sharp
UdonSharp scripting skill for VRChat SDK 3.10.5 (active and verified target). Use when writing, reviewing, debugging, or migrating UdonSharp C# and UdonBehaviour code. Positive triggers include UdonSharp, NetworkCallable, NetworkCalling, CallingPlayer, Udon network authorization, synced runtime state, a local public…
microsoft-typescript
TypeScript is a language for application scale JavaScript development. ALWAYS use when editing or working with .ts, .tsx, .mts, .cts files or code importing "typescript". Consult for debugging, best practices, or modifying typescript, TypeScript.