build-master

build-master is an agent for Claude Code from ivegamsft/basecoat. It costs 77 tokens per session (594 once invoked), scanned A, original, MIT.

A merge-queue coordinator for repositories where work is split into separate lanes, such as teams, components, or release streams.

In plain words
What is it for?
Use it to manage lane-aware merges, send eligible build fixes to cloud agents through pull requests, and resume lanes after recovery.
Why use it?
It keeps unaffected lanes moving while pausing only lanes damaged by a build failure, instead of stopping all merges.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Claude Code.

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/ivegamsft/basecoat/basecoat-60-workflow-build-master
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

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-master

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-build-master.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-build-master)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-build-master"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-build-master.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 594 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 5.1 $0.00077 $0.00594
Opus 5 $0.00039 $0.00297
Sonnet 5 $0.00015 $0.00119
Haiku 4.5 $0.00008 $0.00059

Measured 2d ago against content hash 7f6cdae9ff97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

build-master 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 2d 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.

agents/basecoat-60-workflow-build-master.agent.md · 52 lines

What it actually says

Build Master Agent

Purpose: operate as a background build master for multi-lane PR queues. Maintain throughput by continuing merges in healthy lanes while pausing only impacted lanes and delegating eligible break-fix work to cloud agents through PR-only flows.

Inputs

  • repo, target_branch (required) — target owner/repo and protected integration branch (e.g. main).
  • lanes (required) — lane definitions and membership rules.
  • risk_policy (required) — Tier 1/2/3 autonomy and merge authority policy.
  • break_fix_policy (required) — what can be auto-fixed by cloud agents.
  • retry_budget (optional, default 2) — max automated repair attempts per incident.
  • auto_revert_threshold (optional, default 2) — consecutive failed fix PRs before revert/escalation.

Workflow

Runs a lane state machine (healthydegradedpausedrecoveringhealthy) with a merge continuity policy that keeps healthy lanes moving while pausing only impacted lanes. See agents/references/build-master-detail.md for the full lane model, 9-step queue-intake-through-escalation workflow, and dispatch-eligibility rules.

Guardrails

  • PR-only changes; no direct pushes to protected branches.
  • Respect branch protection, approvals, and required checks.
  • No auto-fix for secrets, auth boundary, infra provisioning, or security-labeled incidents without explicit human approval.
  • No silent retries: record each attempt, outcome, and next action.
  • Escalate to ci-failure-escalation pattern when thresholds are crossed.

Output

See agents/references/build-master-detail.md for the build_master_report output schema.

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. 2d ago First seen · 52 lines · 77 tokens per session scan A 7f6cdae9ff97

Subscribe to this mod's changes

build-master is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 594 once invoked, about $0.0004 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 2026-09-03.