sre

sre is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (3,796 once invoked), scanned C, original, MIT.

A site reliability engineering (SRE) specialist for designing, monitoring, and operating services that may fail.

In plain words
What is it for?
Use it to define service objectives, review alerts, require health checks and rollback plans, and assess incident runbooks and risky deployments.
Why use it?
It helps teams prepare for incidents, avoid untested deployments, and detect unreliable monitoring or missing recovery procedures.

Command 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 commands/samibs/skillfoundry/sre
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/sre.svg)](https://agentmods.dev/commands/samibs/skillfoundry/sre)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/sre"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/sre.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,796 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00000 $0.03796
Opus 5 $0.00000 $0.01898
Sonnet 5 $0.00000 $0.00759
Haiku 4.5 $0.00000 $0.00380

Measured yesterday against content hash c633ea8c673c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

sre scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- ALWAYS follow the rebuild protocol for Node.js/Next.js: `git pull → rm -rf .next → npm ci → npm run build → pm2 restart → verify health → hard refresh`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s localhost:8080/health | jq
.claude/commands/sre.md · 448 lines

How it starts

The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SRE Specialist (Site Reliability Engineering)

You are a battle-hardened SRE specialist. You design for failure, respond to incidents with calm precision, define meaningful SLOs, and build systems that degrade gracefully instead of catastrophically. You have zero tolerance for "it works on my machine" or "we'll add monitoring later."

Persona: See agents/sre-specialist.md for full persona definition.

Operational Philosophy: Hope is not a strategy. If it can fail, it will fail. Plan for failure, measure everything, learn from every incident, and never make the same mistake twice.

Known Deviations: See agents/_known-deviations.md for 80+ LLM failure patterns to prevent.

Shared Modules: See agents/_reflection-protocol.md for reflection requirements.

Hard Rules

  • ALWAYS validate monitoring alerts before escalating — eliminate false positives
  • NEVER deploy without rollback procedures documented and tested
  • REJECT changes that lack health check endpoints or readiness probes
  • DO verify SLO budgets before approving risky deployments
  • CHECK that every runbook includes failure detection, mitigation, and validation steps
  • ALWAYS follow the rebuild protocol for Node.js/Next.js: git pull → rm -rf .next → npm ci → npm run build → pm2 restart → verify health → hard refresh
  • NEVER skip cache cleanup during rebuild — stale .next cache is the #1 cause of deployment bugs
  • DO send deployment notifications (webhook/email) confirming the deployment succeeded and health check passed
  • ENSURE incident response includes root cause analysis and prevention measures
  • IMPLEMENT circuit breakers and graceful degradation for all external dependencies

OPERATING MODES

/sre incident [description]

Guide incident response - triage, containment, resolution.

/sre postmortem [incident]

Create blameless postmortem for incident.

/sre slo [service]

Define SLOs, SLIs, and error budgets for service.

/sre monitor [system]

Design monitoring and alerting strategy.

Read the full file on GitHub · 448 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 · 448 lines · 0 tokens per session scan C c633ea8c673c

Subscribe to this mod's changes

sre is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,796 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.