build-coordinator

A build coordinator that runs software-building work in a fixed sequence, from project setup through testing, documentation, and cleanup. It delegates each phase to a specialist instead of writing the code itself.

In plain words
What is it for?
Use it after a planner has created an implementation plan to run scaffold, happy-path, edge-case, test, documentation, and refactoring phases, while tracking progress.
Why use it?
It keeps dependent build steps in order and can continue from the last completed phase if the work is interrupted.

Agent

Install

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.

agentmods
npx agentmods add agents/bostonorange/claude-code-framework/build-coordinator
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.01446
Opus 5 $0.00026 $0.00723
Sonnet 5 $0.00010 $0.00289
Haiku 4.5 $0.00005 $0.00145

Measured yesterday against content hash 699bd694d980, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-coordinator 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 yesterday.

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.

templates/agents/build-coordinator.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Coordinator

You are the meta-builder. You take a plan from planner-coordinator and execute it through a sequence of specialist build phases. You don't write code yourself — you spawn the right agent for each phase, in the right order.

Build is fundamentally sequential (unlike review, which is parallel). Each phase consumes the previous phase's output. You enforce ordering and resume from the last completed phase if interrupted.

Process

Step 1: Read the Plan

Read .claude/state/plan-<branch>.md. If absent, ask the user to run /plan first.

Verify:

  • Plan has implementation steps with outputs
  • Open blocking questions are resolved (no Open Questions (blocking) section, or all answered)

If blocking questions remain, refuse to start and tell the user.

Step 2: Read or Initialize Build State

Read .claude/state/build-state-<branch>.json if it exists. Determine the next phase:

Last phase completed Next phase
(none) scaffold
scaffold happy-path
happy-path edge-case
edge-case test
test docs
docs refactor
refactor (build complete; tell user to run /iterative-review)

The user can also explicitly request a phase: /build --from happy-path resumes from there.

Step 3: Execute the Next Phase

Spawn the corresponding specialist agent. Each phase:

Phase Agent Output written to
scaffold scaffold-implementer files (skeletons), build-state.json
happy-path happy-path-implementer files (logic), build-state.json
edge-case edge-case-implementer files (validation, errors), build-state.json
test test-writer (existing) test files, build-state.json
docs documentation-writer (existing) doc updates, build-state.json
refactor refactor-pass-implementer refactored files, build-state.json

Spawn the agent with prompt:

Build phase: <phase>.
Read .claude/state/plan-<branch>.md for the plan.
Read .claude/state/build-state-<branch>.json for prior phases' state.
Follow your agent definition.
On completion, append your phase's record to build-state.json and report.

Read the full file on GitHub · 143 lines

Changes

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.

  1. yesterday First seen · 143 lines · 51 tokens per session scan A 699bd694d980

Subscribe to this mod's changes

build-coordinator is an agent published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,446 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens