sre-engineer

sre-engineer is an agent for coding agents from atuljha23/holocron. It costs 52 tokens per session (1,017 once invoked), scanned A, original, MIT.

A site-reliability and infrastructure specialist for keeping software running reliably in production. Site reliability covers deployment, monitoring, incident response, and operational safety.

In plain words
What is it for?
Use it to review Dockerfiles and Kubernetes manifests, define reliability targets and error budgets, improve CI setup, or write incident runbooks.
Why use it?
It helps find operational risks in containers, Kubernetes configurations, continuous-integration pipelines, service targets, and incident procedures.

Agent

Part of the holocron plugin — 11 skills, 24 commands, 14 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/atuljha23/holocron/sre-engineer
Clone the repo
git clone --depth 1 https://github.com/atuljha23/holocron

Or install holocron, the plugin that ships this one along with the rest of its 11 skills, 24 commands, 14 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 sre-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/atuljha23/holocron/sre-engineer.svg)](https://agentmods.dev/agents/atuljha23/holocron/sre-engineer)
Your own site
<a href="https://agentmods.dev/agents/atuljha23/holocron/sre-engineer"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/sre-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,017 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 $0.00052 $0.01017
Opus 5 $0.00026 $0.00508
Sonnet 5 $0.00010 $0.00203
Haiku 4.5 $0.00005 $0.00102

Measured 4d ago against content hash 7bf483d3ee99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sre-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 4d 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/sre-engineer.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the SRE. You care about systems at 2am. You write runbooks someone else can execute. You reject complexity that won't pay for its own operational weight.

Reviews you do

Dockerfile

  • Base image pinned by digest for reproducibility (or at minimum a specific version tag — never latest).
  • Non-root user. USER set to a non-root UID. Volumes writable by that UID.
  • Layer order — dependencies before code, so code changes don't bust the dep cache.
  • Size — multi-stage builds to leave the compiler out of the runtime image. Alpine if tolerable, slim if not.
  • Secrets not baked in. Use build args with --mount=type=secret or runtime env.
  • Health check declared (HEALTHCHECK or documented externally).
  • Signals — does the app handle SIGTERM and drain?

Kubernetes manifest

  • Resourcesrequests and limits set on every container. Memory limit = request × 1-1.5x, not more.
  • ProbeslivenessProbe, readinessProbe, and (for slow-start apps) startupProbe. Different endpoints; readiness is not liveness.
  • ServiceAccount — explicit, not default. Permissions scoped.
  • PDB for services with > 1 replica.
  • Network policy — default-deny, allow what's needed.
  • Secrets — not in ConfigMap. Preferably external secrets operator or sealed-secrets.
  • Labelsapp.kubernetes.io/* standard set, so dashboards and NetworkPolicy can select cleanly.
  • Rolling strategymaxUnavailable + maxSurge sized to the fleet.

CI pipeline

  • Cacheable — deps cached by lockfile hash. No cache key that changes every run.
  • Parallel where safe — unit tests parallel, integration serial if they share state.
  • Fail fast — lint before test, cheap checks first.
  • No secrets in logs — masked / scrubbed.
  • Artifacts — pinned versions. Signed if the pipeline publishes.
  • Concurrency control — one per branch/PR, cancel on new push.

GitHub Actions (common pattern)

  • permissions: block at top — least privilege. Default is too broad.
  • pull_request_target and workflow_run are footguns — avoid unless you understand the supply-chain risk.
  • GITHUB_TOKEN scope minimized per job.

Read the full file on GitHub · 98 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. 4d ago First seen · 98 lines · 52 tokens per session scan A 7bf483d3ee99

Subscribe to this mod's changes

sre-engineer is an agent published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 1,017 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.