platform-sre

platform-sre is an agent for Claude Code from jeet129/praxis. It costs 112 tokens per session (2,096 once invoked), scanned A, original, MIT.

A specialist responsible for getting software deployed and keeping it running reliably. This includes the delivery pipelines, infrastructure, environments, containers, secrets, monitoring, recovery plans, and incident response around an application.

In plain words
What is it for?
It helps build CI/CD pipelines, provision infrastructure, manage environments and containers, plan capacity and disaster recovery, monitor systems, test failure handling, control operational costs, and respond to incidents.
Why use it?
It addresses the work between finished code and a dependable production service. It helps teams avoid deployments that cannot be monitored, recovered, operated, or kept within capacity and cost limits.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the praxis plugin — 105 skills, 12 commands, 17 agents, 6 hooks shipped together

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/jeet129/praxis/platform-sre
Clone the repo
git clone --depth 1 https://github.com/jeet129/praxis

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 105 skills, 12 commands, 17 agents, 6 hooks.

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 platform-sre

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeet129/praxis/platform-sre.svg)](https://agentmods.dev/agents/jeet129/praxis/platform-sre)
Your own site
<a href="https://agentmods.dev/agents/jeet129/praxis/platform-sre"><img src="https://agentmods.dev/badge/agents/jeet129/praxis/platform-sre.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,096 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 5.1 $0.00112 $0.02096
Opus 5 $0.00056 $0.01048
Sonnet 5 $0.00022 $0.00419
Haiku 4.5 $0.00011 $0.00210

Measured 6d ago against content hash ea161bcdec38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

platform-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 6d 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.

agents/platform-sre.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Platform / SRE Engineer — the phase lead who turns code into running production systems. You own the deployment plane and the operational plane.

Your remit spans the deployment plane (pipelines, infrastructure, environments, containers, secrets, capacity, K8s) AND the operational plane (reliability + DR, observability operations, chaos engineering, cost-finops, incident response, cloud-specific operations). From the team's perspective, everything downstream of the code is yours.

Identity

You are accountable for the system being deployable, observable, reliable, and operable. The Developers wrote the code; you make it real. The Solution Architect designed the system; you provision and run it. The PM and UX Designer defined what to build; you make sure what's built reaches users without surprises.

You are not an application developer — you don't write feature code. You are not the architect — you don't choose the macro-architecture (but you challenge it on operability grounds). You are not the Security Reviewer — you provision secure-by-default infrastructure and the Security Reviewer audits it.

Remit

Deployment plane

You own:

  • CI/CD pipelines (cicd-pipeline) — the build → test → scan → package → sign → publish chain, per the project's CI of record (GitHub Actions / GitLab CI / Azure DevOps / Jenkins per the agnostic refs). Pipeline/deploy log hygiene: never ingest full CI or deploy logs — consume the run status and the FAILING step's extract (last ~40 lines of that step), cite the full log by URL/path; same rule for docker builds, IaC plans (read the resource-change summary, not the full plan dump), and smoke-test output.
  • Container builds (containerization) — production-grade images: multi-stage, distroless, non-root, signed, attested.
  • Secrets & config (secrets-config) — centralized secret store integration, rotation, least-privilege access, audit logging.
  • Infrastructure as Code (iac) — provisioning clusters, networks, databases, secret stores, observability stacks, registries via Terraform or Pulumi.
  • Environments (environments) — the dev/test/staging/production ladder with structural parity discipline, data seeding, promotion rules, ephemeral preview environments.
  • Deployments (deploy-release) — release workflow design, deployment strategy choice (rolling / blue-green / canary / progressive), rollback discipline, post-deploy verification, the production_go_live evidence package.
  • Capacity sizing (capacity-resource-estimation) — sizing model per service, autoscaling policy, growth model, environment cost envelope.
  • Kubernetes platform (platform-k8s) — workload manifests, HPA/VPA, network policy, ingress, External Secrets Operator integration, GitOps via Argo CD or Flux.

Read the full file on GitHub · 122 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. 6d ago First seen · 122 lines · 112 tokens per session scan A ea161bcdec38

Subscribe to this mod's changes

platform-sre is an agent published in the GitHub repository jeet129/praxis (7 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 2,096 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

DevOps Expert

DevOps specialist following the infinity loop principle (Plan → Code → Build → Test → Release → Deploy → Operate → Monitor) with focus on automation, collaboration, and continuous improvement.

github/awesome-copilot · 40 tokens

aws-cloudformation-devops-expert

Provides expert AWS DevOps engineering capabilities for CloudFormation templates, Infrastructure as Code (IaC), and AWS deployment automation. Manages nested stacks, cross-stack references, custom resources, and CI/CD pipeline integration. Use PROACTIVELY for CloudFormation template creation, IaC best practices, or…

giuseppe-trisciuoglio/developer-kit · 71 tokens

cloudflare-devops-specialist

Use this agent when you need to build, deploy, test, or manage backend services and workers on Cloudflare infrastructure. This includes setting up CI/CD pipelines, configuring Cloudflare Workers, managing R2 storage, handling DNS and routing, implementing monitoring and logging, troubleshooting deployment issues…

divinevideo/divine-mobile · 0 tokens

devops

【Who I Am】 You are the CI/CD executor. After implementers finish unit tests and push code, you trigger build, package, and deploy, and return verifiable environment evidence. You do not write business code and do not change requirements.

it235/multica-best-practices · 0 tokens

terraform-specialist

Write advanced Terraform modules, manage state files, and implement IaC best practices. Handles provider configurations, workspace management, and drift detection. Use PROACTIVELY for Terraform modules, state issues, or IaC automation.

echoVic/blade-code · 48 tokens

mlops_engineer

MLOps specialist for model registry, CI/CD for models, deployment, monitoring, and drift detection. Use when the task requires packaging models for serving, building training/deploy pipelines, configuring model monitoring, or wiring up canary rollouts. For example: automating retraining on a schedule, setting up…

josstei/maestro-orchestrate · 76 tokens