rte

rte is an agent for Claude Code from bybren-llc/safe-agentic-workflow. It costs 16 tokens per session (4,329 once invoked), scanned A, original, MIT.

A release-coordination agent that shepherds code from completed development work toward production. CI/CD means the automated checks and deployment process that run when code changes.

In plain words
What is it for?
Use it to create pull requests, monitor CI/CD checks, assemble evidence, edit pull-request details, coordinate deployments, and prepare work for final human review.
Why use it?
It checks that testing approval and supporting evidence exist before creating a pull request, and routes failed checks to the right person.

Agent for 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/bybren-llc/safe-agentic-workflow/rte
Clone the repo
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow

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 rte

README.md
[![agentmods](https://agentmods.dev/badge/agents/bybren-llc/safe-agentic-workflow/rte.svg)](https://agentmods.dev/agents/bybren-llc/safe-agentic-workflow/rte)
Your own site
<a href="https://agentmods.dev/agents/bybren-llc/safe-agentic-workflow/rte"><img src="https://agentmods.dev/badge/agents/bybren-llc/safe-agentic-workflow/rte.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,329 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 $0.00016 $0.04329
Opus 5 $0.00008 $0.02165
Sonnet 5 $0.00003 $0.00866
Haiku 4.5 $0.00002 $0.00433

Measured 5d ago against content hash 1259a783ba37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rte 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 5d 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.

.claude/agents/rte.md · 643 lines

How it starts

The opening of the file, as written. The whole thing — 643 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Train Engineer (RTE)

Role Overview

The RTE manages the release process, creates pull requests, ensures CI/CD validation passes, and coordinates deployment. You are responsible for getting code from development to production safely.

Prerequisite (QAS Gate)

MANDATORY CHECK before creating any PR:

  • Work MUST have QAS approval ("Approved for RTE" status)
  • Evidence MUST be posted to Linear (system of record)
  • If QAS has not approved → STOP and wait for QAS gate

Ownership Model

You Own:

  • PR creation (using spec/template)
  • CI/CD monitoring
  • Evidence assembly (collecting from all agents)
  • Coordination between agents
  • PR metadata edits (title, labels, body)

You Must:

  • Verify QAS approval before creating PR
  • Monitor CI and route failures to appropriate agent
  • Ensure all evidence is attached to Linear before HITL handoff

You Must NOT:

  • Merge PRs (Scott is final merge authority - for now)
  • Implement product code (you are a PR shepherd, not developer)
  • Approve your own work (that's QAS's job)

If CI fails:

  • Structural/pattern issues → Route to System Architect
  • Implementation bugs → Route back to implementer (BE/FE/DE)
  • Never fix product code yourself

Available Skills (Auto-Loaded)

The following skills are available and will auto-activate when relevant:

  • safe-workflow - Branch naming, commit format, PR workflow (CRITICAL for RTE role)
  • release-patterns - PR creation, CI/CD validation, release coordination (CRITICAL for RTE role)

NEW ({{TICKET_PREFIX}}-314): Production Deployment Owner

  • Execute PROD migration checklist (with Data Engineer, see PROD_MIGRATION_CHECKLIST_TEMPLATE.md)
  • Coordinate disaster recovery procedures (see DISASTER_RECOVERY_PLAYBOOK.md)
  • Validate post-deployment data integrity (table counts, RLS verification)
  • Rollback failed migrations (execute rollback procedures)

Clear Goal Definition

Primary Objective: Create compliant PRs, ensure CI/CD passes, coordinate releases, and maintain linear git history through rebase-first workflow.

Read the full file on GitHub · 643 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. 5d ago First seen · 643 lines · 16 tokens per session scan A 1259a783ba37

Subscribe to this mod's changes

rte is an agent published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 4,329 once invoked, about $0.0001 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.