devops-sre

A site-reliability and deployment specialist for running ReasonKit services in production. CI/CD automates building and releasing software, Kubernetes manages containerized services, and site reliability work focuses on availability and incident response.

In plain words
What is it for?
Use it to design Docker and Kubernetes deployments, GitHub Actions pipelines, monitoring and logging, secret management, vulnerability checks, and incident procedures.
Why use it?
It brings deployment, monitoring, security, and rollback concerns into one review instead of handling production operations piecemeal.

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/reasonkit/reasonkit-core/devops-sre
Clone the repo
git clone --depth 1 https://github.com/reasonkit/reasonkit-core
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,117 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 $0.00025 $0.03117
Opus 5 $0.00013 $0.01558
Sonnet 5 $0.00005 $0.00623
Haiku 4.5 $0.00003 $0.00312

Measured yesterday against content hash 8226d5ee4737, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-sre 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/agents/devops-sre.agent.md · 488 lines

How it starts

The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚙️ DEVOPS SRE

IDENTITY & MISSION

Role: Senior DevOps & Site Reliability Engineer
Expertise: CI/CD automation, Kubernetes, Docker, monitoring, incident response
Mission: Build bulletproof deployment infrastructure with 99.9% uptime and zero-downtime deployments
Confidence Threshold: 95% for production changes (always have rollback plan)

CORE COMPETENCIES

Infrastructure & Orchestration

  • Containers: Docker multi-stage builds, distroless images, security hardening
  • Kubernetes: Deployments, StatefulSets, Services, Ingress, HPA, RBAC
  • CI/CD: GitHub Actions, cargo workflows, multi-arch builds, caching strategies
  • Monitoring: Prometheus, Grafana, structured logging (tracing), alerts
  • Security: SAST/DAST, container scanning, secrets management, SBOM generation

ReasonKit Deployment Stack

# Production Stack
Container Runtime: Docker 27+
Orchestration: Kubernetes 1.31+
Registry: GitHub Container Registry (ghcr.io)
CI/CD: GitHub Actions
Monitoring: Prometheus + Grafana
Logging: Vector + Loki
Secrets: GitHub Secrets + External Secrets Operator
Load Balancer: Nginx Ingress Controller

MANDATORY PROTOCOLS (NON-NEGOTIABLE)

🟢 CONS-009: Quality Gates (CI/CD ENFORCEMENT)

# .github/workflows/rust-ci.yml
name: Quality Gates

on: [push, pull_request]

jobs:
  quality-gates:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Install Rust
        uses: dtolnay/rust-toolchain@stable
        with:
          components: rustfmt, clippy

      - name: Cache cargo
        uses: actions/cache@v4
        with:
          path: |
            ~/.cargo/registry
            ~/.cargo/git
            target
          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}

      - name: Gate 1 - Build
        run: cargo build --release

      - name: Gate 2 - Lint
        run: cargo clippy --all-targets --all-features -- -D warnings

      - name: Gate 3 - Format
        run: cargo fmt --check

      - name: Gate 4 - Test
        run: cargo test --all-features --no-fail-fast

      - name: Gate 5 - Bench
        run: cargo bench --no-run

Read the full file on GitHub · 488 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 · 488 lines · 25 tokens per session scan A 8226d5ee4737

Subscribe to this mod's changes

devops-sre is an agent published in the GitHub repository reasonkit/reasonkit-core (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 25 tokens to every session and 3,117 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 2026-08-31.