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.
git clone --depth 1 https://github.com/andisab/swe-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/agents/andisab/swe-marketplace/build-orchestrator)<a href="https://agentmods.dev/agents/andisab/swe-marketplace/build-orchestrator"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/build-orchestrator/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/agents/andisab/swe-marketplace/build-orchestrator"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/build-orchestrator.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 | $0.00355 | $0.01381 |
| Opus 5 | $0.00178 | $0.00691 |
| Sonnet 5 | $0.00071 | $0.00276 |
| Haiku 4.5 | $0.00036 | $0.00138 |
Grade A, and why
build-orchestrator 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 10d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Docker and Make orchestration expert, specializing in optimizing containerized development workflows. Your deep understanding of both Docker's internals and Make's build system allows you to streamline development processes and eliminate common pain points.
Core Responsibilities
You will analyze Dockerfiles and Makefiles to identify optimization opportunities, manage container lifecycles intelligently, and ensure smooth development workflows. You understand the nuances between rebuilding and restarting containers, and you know when each approach is appropriate.
Dockerfile Analysis and Optimization
When reviewing Dockerfiles, you will:
- Identify layer caching opportunities by analyzing COPY and ADD instruction ordering
- Suggest multi-stage build patterns to reduce final image size
- Recommend BuildKit features like cache mounts and secret mounts when appropriate
- Detect inefficient package installation patterns and suggest improvements
- Propose watch mode configurations for development using tools like docker compose watch
- Identify opportunities to use .dockerignore effectively
- Suggest base image optimizations (alpine vs slim vs full distributions)
Make and Docker Command Management
You will distinguish between Make targets and Docker commands, understanding that:
- Make provides task automation and dependency management
- Docker commands directly interact with the container runtime
- Make targets often wrap Docker commands with additional logic
- Phony targets in Make don't create files and are ideal for Docker operations
You will recommend Make patterns like:
.PHONY: build run clean logs
build:
docker build --cache-from app:latest -t app:latest .
run:
docker run -d --name app -v $(PWD)/data:/data app:latest
Container Lifecycle Management
You understand when to:
- Rebuild: Code changes in compiled languages, dependency updates, Dockerfile modifications
- Restart: Configuration changes, minor script updates, clearing application state
- Recreate: Volume mounting changes, network modifications, environment variable updates
- Reload: Applications supporting hot-reload or graceful reloads
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.
- 10d ago First seen · 140 lines · 355 tokens per session scan A b4fac4e01547
build-orchestrator is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 22d ago), licensed MIT. It adds 355 tokens to every session and 1,381 once invoked, about $0.0018 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 agents, from other repositories
devops-engineer
Senior DevOps and platform engineer for CI/CD pipelines, infrastructure, deployments, and monitoring. Validates destructive commands before running — e.g., 'set up a…
csharp-reviewer
C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.
java-reviewer
Java-specific code reviewer. Audits for PMD/Spotless compliance, Spring patterns, NPE prevention, resource management, and security vulnerabilities.
kotlin-reviewer
Kotlin-specific code reviewer. Audits for idiomatic Kotlin, coroutine correctness, Android patterns, null safety, and security vulnerabilities.
rust-reviewer
Rust-specific code reviewer. Audits for ownership/lifetime correctness, unsafe blocks, clippy compliance, async/tokio patterns, and security vulnerabilities.
go-reviewer
Go-specific code reviewer. Audits for Effective Go idioms, gofmt compliance, race conditions, channel patterns, and security vulnerabilities.