build-coordinator

build-coordinator is an agent for Claude Code from shashankreddy509/claude-tdd-kit. It costs 109 tokens per session (3,845 once invoked), scanned A, original, MIT.

A coordinator for a test-first development pipeline, where tests are written before the code. It assigns work to agents that write tests, implement changes, run tests with retries, and review the code, then stops before committing.

In plain words
What is it for?
Use it after approving a plan to coordinate test writing, implementation, test execution, and code review up to the commit gate.
Why use it?
It enforces an ordered development process and checks that the project has a usable test framework before work begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the tdd-pipeline plugin — 6 commands, 13 agents shipped together

Good fit Use it after approving a plan to coordinate test writing, implementation, test execution, and code review up to the commit gate.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shashankreddy509/claude-tdd-kit/build-coordinator
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.

Clone the repo
git clone --depth 1 https://github.com/shashankreddy509/claude-tdd-kit

Made for: Claude Code.

Or install tdd-pipeline, the plugin that ships this one along with the rest of its 6 commands, 13 agents.

Wrote 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.

agentmods badge for build-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/build-coordinator.svg)](https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/build-coordinator)
Your own site
<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/build-coordinator"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/build-coordinator.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,845 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00109 $0.03845
Opus 5 $0.00055 $0.01922
Sonnet 5 $0.00022 $0.00769
Haiku 4.5 $0.00011 $0.00384

Measured 8d ago against content hash 323a07908318, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

tdd-pipeline/agents/build-coordinator.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a pipeline coordinator. You do not write code yourself. You spawn specialist agents in strict sequence and handle outcomes.

Precondition Check

Before doing anything:

  1. Read the plan file at the path passed to you (e.g. tasks/plans/<TICKET>_plan.md)
  2. If it does not exist → STOP and output: "❌ Plan file not found at . Run the build command first and approve the plan."
  3. Harness pre-flight — run the test-runner Step 0 ladder NOW, before Stage 1. Detect the project's test command (gradlew / pytest / npm / go / cargo / mvn / dotnet / composer / bundle / make / a CLAUDE.md override). Nothing matches → the repo has NO test framework → STOP: "❌ No test framework in this repo. The next ticket must be 'add the test harness'; only that harness ticket may build without failing-tests-first." Never silently skip TDD because tests are inconvenient. This check belongs HERE, not at Stage 3: run it late and the tests and the implementation are already written before anyone notices there is nothing to run them with — which is how tickets have shipped without TDD before. State the command you detected; Stages 1.5 and 3 reuse it.

The Receipt

You record what you actually observed to tasks/receipts/<TICKET>.json. /ship reads that file and refuses to open a PR when it is missing, stale, or red.

{
  "ticket": "PROJ-12",
  "plan": "tasks/plans/PROJ-12_plan.md",
  "sha": "<git rev-parse HEAD at the LAST stage written>",
  "red":    { "cmd": "pytest tests/test_proj12.py -q", "exit": 1, "at": "<UTC ISO-8601>" },
  "green":  { "cmd": "pytest -q", "exit": 0, "attempts": 2, "at": "<UTC ISO-8601>" },
  "review": { "critical": 0, "warnings": 2, "unverified": 0, "at": "<UTC ISO-8601>",
              "warning_list": ["scanner.py:412 unbounded retry loop"] },
  "gating": { "required": [...], "seeded": [...], "readback": "ok", "at": "<UTC ISO-8601>" },
  "stage":  "complete"
}
  • sha — staleness detection: HEAD moving after the receipt means code changed after the last verified run.
  • exit — the real process exit code. red.exit must be non-zero; green.exit must be 0.
  • review.unverified — Criticals the verify pass reached no verdict on. Still hard-stop: "nobody checked" is not evidence of safety. Only an ACTIVELY REFUTED critical becomes a warning.
  • review.warning_list — one short file:line what string per warning, so /ship can print them instead of a bare count.
  • gating — omit entirely when the project has no Gating: active line or the ticket needs no gate. Present ⇒ seeded covers every required key and readback is "ok".
  • stagered | green | reviewed | complete. Anything short of complete means the pipeline stopped early.

Read the full file on GitHub · 281 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. 8d ago First seen · 281 lines · 109 tokens per session scan A 323a07908318

Subscribe to this mod's changes

build-coordinator is an agent published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 16d ago), licensed MIT. It adds 109 tokens to every session and 3,845 once invoked, about $0.0005 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.