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 agentmods add commands/sigistry/marketplace/build-explaingit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/build-explain)<a href="https://agentmods.dev/commands/sigistry/marketplace/build-explain"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/build-explain.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00849 |
| Opus 5 | $0.00007 | $0.00425 |
| Sonnet 5 | $0.00003 | $0.00170 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
build-explain 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 6d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decode this repository's build system so you can build and test without holding the whole dependency graph in your head. Use this when make, Bazel, Gradle, or a monorepo task runner is opaque and you just need the right command for one package. $ARGUMENTS may name a target, package, or module to focus on (e.g. //services/api:test, web, :app:assembleDebug); with no argument, map the whole build.
Process
Step 1: Detect the build system
Identify the driver(s) from their manifests, a repo can have more than one layer (a top-level task runner over a per-language build). Consult the build-system-decode skill (build-systems.md) for per-tool details.
| Manifest | Build system |
|---|---|
Makefile |
Make |
BUILD, BUILD.bazel, WORKSPACE, MODULE.bazel |
Bazel |
build.gradle(.kts), settings.gradle |
Gradle |
pom.xml |
Maven |
package.json scripts, lockfile |
npm / pnpm / yarn scripts |
nx.json, project.json |
Nx |
turbo.json |
Turborepo |
CMakeLists.txt |
CMake |
Cargo.toml ([workspace]) |
cargo |
go.mod, go.work |
go build |
Step 2: Enumerate the targets
List what you can actually run and what each does, do not invent targets. Use the tool's own introspection rather than parsing by eye:
- Make: read
.PHONYand rule names;make -qp/make helpif present. - Bazel:
bazel query //...,bazel query 'deps(//target)'. - Gradle:
./gradlew tasks --all,:project:dependencies. - Maven:
mvn -q help:describe, the<modules>list. - npm/pnpm/yarn: the
scriptsblock; workspace list. - Nx/Turbo:
nx graph/turbo run build --dry,project.json/turbo.jsonpipeline/tasks. - cargo/go:
cargo metadata,go list ./....
Step 3: Map the dependency graph
Show which packages/modules depend on which, and where the slow edges are. Identify the difference between building the world and building one package plus only its dependencies. For monorepos, apply the build-system-decode skill's monorepo-patterns.md (workspaces, project graph, affected/changed detection).
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.
- 6d ago First seen · 53 lines · 14 tokens per session scan A b61e508a5374
build-explain is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 849 once invoked, about $0.0001 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 commands, from other repositories
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
review
Pressure-test an important decision, plan, proposal, strategy, architecture, or recommendation with adaptive depth and token-efficient verification.
dotnet-structure
Analyze and recommend .NET backend solution and folder structure improvements. Checks projects, layers, oversized files, and boundary clarity.
compliance-fix
Show Qualimetry review findings for a file and apply the standards-compliant fix.
clean-gone
Clean up local branches that have been deleted from the remote repository.
commit-push-pr
Complete workflow — commit, push, and create a pull request in one step.