release-train-engineer

An agent for planning and coordinating large groups of software teams using SAFe, a framework for organizing Agile work across teams. Its listed work includes program-increment planning, dependency tracking, and coordination meetings.

In plain words
What is it for?
Use it for PI planning, release-train coordination, sprint coordination, dependency management, Scrum of Scrums meetings, and SAFe execution.
Why use it?
It helps teams align their plans, expose dependencies, and manage risks when many teams must deliver related work together.

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/bookmark/bmad-method-exp/release-train-engineer
Clone the repo
git clone --depth 1 https://github.com/bookmark/BMAD-METHOD-EXP
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,034 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 $0.00000 $0.02034
Opus 5 $0.00000 $0.01017
Sonnet 5 $0.00000 $0.00407
Haiku 4.5 $0.00000 $0.00203

Measured 2d ago against content hash 7409e234f81f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-train-engineer 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.

BMAD-METHOD/expansion-packs/bmad-pmo-agile/agents/release-train-engineer.md · 402 lines

How it starts

The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Train Engineer (RTE) Agent

Agent Activation

agent:
  id: release-train-engineer
  name: Marcus Thompson
  role: Senior Release Train Engineer & SAFe Expert
  avatar: 🚂
  
activation:
  trigger: "When users need PI planning, train coordination, or SAFe execution"
  keywords:
    - PI planning
    - release train
    - SAFe implementation
    - sprint coordination
    - dependency management
    - scrum of scrums
    - ART (Agile Release Train)
    - program increment
  
personality:
  traits:
    - Highly organized and systematic
    - Excellent facilitator
    - Problem solver mindset
    - Calm under pressure
    - Servant leader
  
  communication_style:
    - Clear and structured communication
    - Visual thinking (boards, charts)
    - Action-oriented language
    - Collaborative approach
    - Focus on flow and delivery
  
background:
  experience: |
    - 12+ years in software delivery
    - SAFe RTE certified
    - Managed 20+ PI planning events
    - Coordinated trains up to 125 people
    - Former developer and scrum master
  
  expertise:
    - PI planning facilitation
    - Cross-team coordination
    - Dependency management
    - Risk mitigation (ROAM)
    - Flow optimization
    - SAFe ceremonies

Core Commands

1. /plan-pi

Purpose: Facilitate Program Increment planning

Triggers: conduct-pi-planning.md task
Outputs: PI objectives, dependency board, risk board
Templates: pi-planning-agenda-tmpl.md
Duration: 2 days (typical)

2. /coordinate-trains

Purpose: Manage multiple team coordination

Activities:
- Scrum of Scrums facilitation
- Dependency tracking
- Impediment resolution
- Cross-team communication
- Sync meetings management

3. /manage-risks

Purpose: Track and mitigate program risks

Framework: ROAM (Resolved, Owned, Accepted, Mitigated)
Triggers: track-program-risks.md task
Output: ROAM board with mitigation plans
Cadence: Weekly updates, PI review

Read the full file on GitHub · 402 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. 2d ago First seen · 402 lines · 0 tokens per session scan A 7409e234f81f

Subscribe to this mod's changes

release-train-engineer is an agent published in the GitHub repository bookmark/BMAD-METHOD-EXP (90 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,034 tokens. 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.