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 sigistry/marketplace --skill build-system-decodegit 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/skills/sigistry/marketplace/build-system-decode)<a href="https://agentmods.dev/skills/sigistry/marketplace/build-system-decode"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/build-system-decode/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/sigistry/marketplace/build-system-decode"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/build-system-decode.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 | $0.00109 | $0.00851 |
| Opus 5.5 | $0.00044 | $0.00340 |
| Sonnet 5.5 | $0.00022 | $0.00170 |
| Haiku 4.5 | $0.00011 | $0.00085 |
Grade A, and why
build-system-decode 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 1mo 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build System Decode
Purpose
A repeatable way to understand and drive an unfamiliar build, so you can answer "what can I run, what does it do, and how do I build/test just my package?" without holding the whole dependency graph in your head. Detect the tool from its manifest, use the tool's own introspection instead of hand-parsing config, and always find the narrowest command that gets your package green.
Detection: manifest → build system
| Manifest file(s) | Build system | Introspection command |
|---|---|---|
Makefile |
Make | make help, make -qp, grep .PHONY |
BUILD(.bazel), WORKSPACE, MODULE.bazel |
Bazel | bazel query //... |
build.gradle(.kts), settings.gradle |
Gradle | ./gradlew tasks --all |
pom.xml |
Maven | mvn help:describe, <modules> |
package.json scripts + lockfile |
npm/pnpm/yarn | read scripts, <pm> run |
nx.json, project.json |
Nx | nx graph, nx show projects |
turbo.json |
Turborepo | turbo run build --dry |
CMakeLists.txt |
CMake | cmake --build . --target help |
Cargo.toml ([workspace]) |
cargo | cargo metadata, --workspace |
go.mod, go.work |
go build | go list ./... |
A repo often has two layers: a top-level orchestrator (Make, Nx, Turbo, Bazel) driving per-language builds underneath. Identify both.
The three questions to answer
- What targets exist? Use the tool's list/query command, never invent a target. Distinguish real build/test/lint targets from convenience aliases.
- What depends on what? Get the graph from the tool (
bazel query 'deps(...)',gradle :p:dependencies,nx graph,cargo metadata). Find the difference between "build the world" and "build my package + only its deps." - How do I build/test one package? Every ecosystem has a scoping flag, the single most useful thing to a newcomer. Make it the headline (see
build-systems.md).
Decision checklist
- Detect the tool(s) from the manifest table above; cite the file.
- Run the introspection command to enumerate real targets.
- Pull the dependency graph from the tool, not by eye.
- Identify the single-package build/test command and the affected/changed command.
- Note required bootstrap (toolchain fetch,
bazel sync, lockfile verification) before the first build works.
What ships with it
2 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.
- 1mo ago First seen · 43 lines · 109 tokens per session scan A 2a818d8f623f
build-system-decode is a skill published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 851 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
cold-start-problem
Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…
clean-architecture
Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…