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 pledgeandgrow/pledge-skills --skill bazelgit clone --depth 1 https://github.com/pledgeandgrow/pledge-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/pledgeandgrow/pledge-skills/bazel)<a href="https://agentmods.dev/skills/pledgeandgrow/pledge-skills/bazel"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/bazel/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/pledgeandgrow/pledge-skills/bazel"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/bazel.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 | $0.00035 | $0.03293 |
| Opus 5 | $0.00017 | $0.01647 |
| Sonnet 5 | $0.00007 | $0.00659 |
| Haiku 4.5 | $0.00003 | $0.00329 |
Grade A, and why
bazel-docs 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 9d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bazel 9.x — Build System Documentation
Source: bazel.build/docs | bazel.build/start | bazel.build/reference | bazel.build/extending | bazel.build/community
Overview
Bazel is a fast, hermetic, multi-platform build system that uses a high-level build language (Starlark) to describe build properties at a semantic level. It caches all previous work, tracks file content and command changes, and rebuilds only what's necessary. Bazel runs on Linux, macOS, and Windows, and scales to 100k+ source files.
- Website: bazel.build
- GitHub: github.com/bazelbuild/bazel
- Releases: bazel.build/release
- Install: bazel.build/install
- Current LTS: 9.2.0 | Also: 8.7.0, 7.7.1, 6.6.0
Core Concepts
- Repositories: Directory tree with boundary marker (MODULE.bazel, REPO.bazel, or WORKSPACE)
- Workspace: Environment shared by all Bazel commands from the same main repo
- Packages: Directory containing a BUILD/BUILD.bazel file
- Targets: Files (source/generated) and rules defined in BUILD files
- Labels: Canonical identifiers for targets (
//package-name:target-name) - Dependencies: Declared (BUILD file) vs actual (needed for correct build)
- Hermeticity: Builds isolated from external environment
- Runes/Starlark: Python-like DSL for writing BUILD files and extensions
- Action Graph: DAG of build actions (inputs → outputs)
- Three Phases: Loading → Analysis → Execution
File Index
| File | Coverage |
|---|---|
| getting-started.md | Intro, installation, first builds (C++/Java/Android/iOS/Go), concepts (repos, workspaces, packages, targets, labels, BUILD files, dependencies, visibility, hermeticity), building programs, bazelrc, scripts, client/server |
| user-guide.md | BUILD style guide, external dependencies (Bzlmod), commands & options, query (bazel query/aquery/cquery), configurable attributes, C++ integration, code coverage, Windows, performance optimization, remote execution (RBE, caching, dynamic execution, sandbox, workers, BEP), tutorials, migration |
| extending.md | Extension concepts, rules, symbolic macros, legacy macros, depsets, aspects, repository rules, configurations, platforms, toolchains, execution groups, Starlark language, style guide, testing rules, performance, deploying rules, Stardoc |
| reference.md | Build encyclopedia (all native rules: cc_, java_, py_, sh_, objc_, proto_, general, platforms), test encyclopedia, command-line reference, query reference, glossary, Starlark API (global functions, providers, built-in types, top-level modules, configuration fragments) |
What ships with it
4 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.
- 9d ago First seen · 175 lines · 35 tokens per session scan A 2004d2fbb36e
bazel-docs is a skill published in the GitHub repository pledgeandgrow/pledge-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 3,293 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-monorepo-expert
Expert knowledge for managing large-scale Bazel monorepos with multiple services, shared libraries, and cross-cutting concerns. Use for workspace structure, visibility, and dependency management.
rules-quarkus
Expert knowledge for building Quarkus applications with Bazel using the rulesquarkus build system. Use when user asks about Quarkus+Bazel builds, augmentation, or troubleshooting.
bazel-expert
Expert knowledge for writing idiomatic Bazel rules, Starlark best practices, and build performance optimization. Use for Bazel build system questions.
init-workspace-rules
Create agent rules.
bazel-k8s-expert
Expert knowledge for deploying Quarkus/Java applications to Kubernetes using Bazel. Covers rulesk8s, Helm, Kustomize, ConfigMaps, Secrets, and health probes.
bazel-oci-expert
Expert knowledge for building OCI container images with Bazel using rulesoci. Use for containerizing Quarkus/Java applications, multi-arch builds, and image optimization.