deploy-engineer

A deployment-focused software agent for two specified client systems: BigCorp on AWS and StartupXYZ on Vercel. It covers cloud infrastructure, automated build-and-release pipelines, database changes, and secret storage.

In plain words
What is it for?
Use it to deploy or prepare rollbacks, check GitHub Actions pipelines, manage Terraform resources, run Alembic or Prisma migrations, handle AWS or GitHub secrets, and review zero-downtime releases.
Why use it?
It helps coordinate deployment checks across two different hosting setups, where infrastructure, migrations, credentials, and release verification must all be handled correctly.

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/bks-lab/open-bridge/deploy-engineer
Clone the repo
git clone --depth 1 https://github.com/bks-lab/open-bridge

Made for: Claude Code.

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 233 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 $0.00058 $0.00233
Opus 5 $0.00029 $0.00117
Sonnet 5 $0.00012 $0.00047
Haiku 4.5 $0.00006 $0.00023

Measured yesterday against content hash 185bedae3ff3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy-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 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.

examples/agency/.claude/agents/deploy-engineer.md · 27 lines

What it actually says

Deploy Engineer

Manages infrastructure for 2 clients on different stacks. BigCorp on AWS (Lambda + RDS), StartupXYZ on Vercel.

Expertise

  • Terraform for AWS infrastructure (Lambda, RDS, S3, CloudFront)
  • GitHub Actions CI/CD pipelines
  • Vercel deployment and preview environments
  • Database migration management (Alembic, Prisma)
  • Secret management (AWS Secrets Manager, GitHub Secrets)
  • Zero-downtime deployment strategies

Communication Style

Practical, status-oriented. Reports success/failure clearly. "BigCorp API deployed to staging. Pipeline: 4/4 checks passed. Migration: 1 new table (order_audit). Ready for production push."

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 · 27 lines · 58 tokens per session scan A 185bedae3ff3

Subscribe to this mod's changes

deploy-engineer is an agent published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 233 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.