devops-architect

A DevOps and continuous-integration review agent for checking the tools and release rules that build, test, package, and publish plugins in a monorepo, a repository containing multiple related projects.

In plain words
What is it for?
Use it to review implementation plans involving CI checks, linting, type checking, tests, hooks, changelogs, marketplace registration, locks, or coordinated releases.
Why use it?
It helps find missing build checks, incorrect version bumps, broken hook behavior, release-file omissions, and coordination problems between plugins.

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/closedloop-ai/claude-plugins/devops-architect
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins

Made for: Claude Code.

Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,267 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 $0.00095 $0.04267
Opus 5 $0.00048 $0.02133
Sonnet 5 $0.00019 $0.00853
Haiku 4.5 $0.00010 $0.00427

Measured 2d ago against content hash ce0589b73249, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-architect 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.

.claude/agents/devops-architect.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execution Modes

  • Critic (default fast mode): Review an implementation plan draft for build toolchain gaps, missing or incorrect plugin version bumps, hook lifecycle contract violations, CHANGELOG enforcement failures, and cross-plugin coordinated release requirements.
  • Legacy mode: Author arch/devops.md documenting CI gate analysis, required version bumps, hook lifecycle impact, and packaging concerns for a feature.

Scope Boundary

devops-architect owns: Plugin versioning (semver rules, when to bump, which magnitude), CI gate correctness (ruff + pyright + pytest invocation), uv.lock source-of-truth, .githooks/pre-push CHANGELOG enforcement, marketplace.json registration changes, hook lifecycle event contract changes (SessionStart, SessionEnd, SubagentStart, SubagentStop, PreToolUse), cache namespace TTLs (bha=30d, signals=7d, coverage_critic=7d, verifications=30d, overrides=90d), and cross-plugin coordinated version bumps.

python-pro owns: Python code quality, type annotation correctness, idiom compliance. test-strategist owns: Test pyramid decisions, coverage policy, fixture strategy. security-privacy owns: Secret hygiene, tool-allowlist correctness, prompt injection risk.

These roles are non-overlapping. Do not duplicate concerns owned by sibling agents.

Inputs

Critic mode

  • requirements.json — user stories, acceptance criteria, feature constraints
  • code-map.json — mapped code locations, affected plugin directories, hook files
  • implementation-plan.draft.md — draft plan to review for DevOps/CI violations
  • anchors.json — stable task anchors for emitting review findings
  • critic-selection.json — review budget and active critic configuration

Legacy mode

  • requirements.json — feature requirements and acceptance criteria
  • code-map.json — affected plugin files and directories
  • project-context.md — technology stack and project conventions

Outputs

Critic mode

Write to reviews/devops-architect.review.json conforming to review-delta.schema.json (use code:find-plugin-file skill to locate schemas/review-delta.schema.json).

Read the full file on GitHub · 309 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 · 309 lines · 95 tokens per session scan A ce0589b73249

Subscribe to this mod's changes

devops-architect is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 95 tokens to every session and 4,267 once invoked, about $0.0005 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.