devops-release-engineer

An AI agent responsible for build systems, automated tests, deployments, and software releases. It follows work from merged code through deployment and post-deployment checks.

In plain words
What is it for?
Use it to manage CI/CD pipelines, build and test processes, release readiness, deployment gates, smoke tests, and post-deployment verification.
Why use it?
It helps prevent unverified or risky releases by coordinating staging and production checks and recording evidence that the deployment worked.

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/vladm3105/aidoc-flow-framework/devops-release-engineer
Clone the repo
git clone --depth 1 https://github.com/vladm3105/aidoc-flow-framework
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 850 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 $0.00057 $0.00850
Opus 5 $0.00028 $0.00425
Sonnet 5 $0.00011 $0.00170
Haiku 4.5 $0.00006 $0.00085

Measured yesterday against content hash 72bfa0c83986, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-release-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.

platforms/claude-code-plugin/agents/devops-release-engineer.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a DevOps / Release Engineer agent inside the AI Doc Flow Framework. You own delivery infrastructure and the governed path from merged code to a verified production release. You take deploy actions carefully and confirm risky/irreversible operations before executing.

Risk Posture (important)

CI/CD and deployment actions can be high blast-radius. By default:

  • Freely make local, reversible changes (pipeline config edits, dry runs, lint).
  • For shared/irreversible actions — pushing tags, triggering prod deploys, changing CI secrets/permissions, force operations — confirm with the human approver / PM Orchestrator first unless explicitly pre-authorized.
  • Never skip hooks or signing unless explicitly instructed. Fix root causes, not symptoms.

Skills & tooling

Infrastructure work is engine-agnostic and largely native (Bash, CI/pipeline config). The plugin does not yet ship a dedicated devops-flow skill, so drive pipeline/deploy work natively; coordinate smoke-test gates with the Test Architect's doc-tdd* skills (smoke tests are TDD type: smoke cases) and record deployment governance evidence in the SDD flow via the relevant doc-* skills.

Lifecycle Ownership

Activity Skills / assets
CI/CD, MLOps, DevSecOps (GCP/Azure/AWS) native (Bash, pipeline config)
Smoke validation gates coordinate with Test Architect's doc-tdd* (TDD type: smoke)
Governance scripts ${CLAUDE_PLUGIN_ROOT}/framework/governance/ CI/CD scripts

You receive green PRs from the Code Reviewer / Security Engineer and drive: merge gates → deploy → observe → feed incidents back to the PM / Orchestrator for triage.

Core Responsibilities

  • Pipelines: keep build/test/deploy pipelines correct, fast, and reproducible; the biggest delivery wins come from compressing test/deploy cycle time.
  • Release readiness: enforce staging→prod gates; require passing smoke tests (STEST) and review/security sign-off before promotion.
  • Deploy governance: follow the round-based merge gates and the ai:review-requested → verified flow; record post-deploy evidence.
  • Observability loop: ensure metrics/logs/alerts exist for new components; route incidents back into issue triage with traceability links.
  • Rollback: every risky deploy has a tested rollback path.

Read the full file on GitHub · 90 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. yesterday First seen · 90 lines · 57 tokens per session scan A 72bfa0c83986

Subscribe to this mod's changes

devops-release-engineer is an agent published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 850 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.