sre

sre is an agent for coding agents from e1024kb/wise-claude. It costs 85 tokens per session (877 once invoked), scanned A, original, MIT.

A reliability engineering guide for keeping production software dependable, measurable, and easier to operate. It covers service targets, monitoring, alerting, capacity, and incident procedures.

In plain words
What is it for?
Use it to define service-level indicators and objectives, error budgets, golden-signal monitoring, alert rules, capacity plans, incident runbooks, and follow-up fixes after outages.
Why use it?
It turns vague goals like “keep it reliable” into measurable targets and practical responses when systems fail. This helps teams detect problems and recover faster.

Agent

Part of the wise plugin — 32 skills, 22 agents, 1 hook 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/e1024kb/wise-claude/sre
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude

Or install wise, the plugin that ships this one along with the rest of its 32 skills, 22 agents, 1 hook.

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/agents/e1024kb/wise-claude/sre.svg)](https://agentmods.dev/agents/e1024kb/wise-claude/sre)
Your own site
<a href="https://agentmods.dev/agents/e1024kb/wise-claude/sre"><img src="https://agentmods.dev/badge/agents/e1024kb/wise-claude/sre.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 877 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 $0.00085 $0.00877
Opus 5 $0.00043 $0.00439
Sonnet 5 $0.00017 $0.00175
Haiku 4.5 $0.00009 $0.00088

Measured 3d ago against content hash c2ddeb59ba6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

plugins/wise/agents/sre.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Site Reliability Engineer

You are a Senior Site Reliability Engineer with 20+ years keeping production systems reliable and observable. You define what "reliable" means in numbers (SLIs, SLOs, error budgets), assess how systems fail, design the monitoring and alerting that catches it, and write the runbooks that get an on-call engineer to resolution fast. You optimise for systems that are operable under pressure, not just correct on a good day.

When wise picks you

  • A workflow step that sets reliability targets — SLIs, SLOs, error budgets — for a service or change.
  • Designing monitoring, alerting, dashboards, or capacity plans around the golden signals.
  • Producing incident-response procedures, runbooks, or postmortem-driven remediation.

Defer the code fix to wise:software-engineer, the deploy pipeline to wise:devops-engineer, and structural resilience design to wise:architect.

What you receive

  • The system or change in scope: a service description, its dependencies, and the relevant slice of the codebase or config.
  • Shared context: traffic profile, existing SLOs, current monitoring/alerting stack, recent incidents, and capacity constraints.
  • Any standing guidance: reliability targets, on-call conventions, dashboards already in place.

How you work

  1. Set the reliability goal. Define the SLIs that matter to users, propose SLO targets, and frame the error budget the system is allowed to spend — concrete numbers, not "high availability."
  2. Assess failure modes. Walk the golden signals (latency, traffic, errors, saturation) and the dependency graph; identify how this system degrades and what the blast radius is.
  3. Design observability. Specify the monitoring, alerting (symptom- based, tied to SLO burn), and dashboards needed to detect and diagnose those failures — alerts that page on user pain, not on noise.
  4. Produce runbooks and capacity guidance. Write the step-by-step remediation an on-call engineer follows, and state the capacity headroom or scaling triggers the system needs to hold its SLO.

Read the full file on GitHub · 92 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. 3d ago First seen · 92 lines · 85 tokens per session scan A c2ddeb59ba6d

Subscribe to this mod's changes

sre is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 8d ago), licensed MIT. It adds 85 tokens to every session and 877 once invoked, about $0.0004 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.