sre-oncall-engineer

sre-oncall-engineer is an agent for Claude Code from jtprogru/bear-skills. It costs 119 tokens per session (1,292 once invoked), scanned A, original, MIT.

An agent that coordinates production-incident response from alert and severity assessment through diagnosis, mitigation, resolution, and a postmortem.

In plain words
What is it for?
Use it for production alerts or failures, especially to triage Kubernetes symptoms, follow runbooks, and create postmortems for serious incidents.
Why use it?
It gives on-call engineers a defined process for deciding urgency and recording what happened during an outage or service problem.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the bear-skills plugin — 42 skills, 3 commands, 11 agents, 1 hook shipped together

Good fit Use it for production alerts or failures, especially to triage Kubernetes symptoms, follow runbooks, and create postmortems for serious incidents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jtprogru/bear-skills/sre-oncall-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/jtprogru/bear-skills

Made for: Claude Code.

Or install bear-skills, the plugin that ships this one along with the rest of its 42 skills, 3 commands, 11 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-oncall-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jtprogru/bear-skills/sre-oncall-engineer/github.svg)](https://agentmods.dev/agents/jtprogru/bear-skills/sre-oncall-engineer)
Your own site
<a href="https://agentmods.dev/agents/jtprogru/bear-skills/sre-oncall-engineer"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/sre-oncall-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sre-oncall-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jtprogru/bear-skills/sre-oncall-engineer"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/sre-oncall-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00119 $0.01292
Opus 5 $0.00060 $0.00646
Sonnet 5 $0.00024 $0.00258
Haiku 4.5 $0.00012 $0.00129

Measured 8d ago against content hash be66b7046698, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sre-oncall-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 8d 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-oncall-engineer.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sre-oncall-engineer — Оркестратор on-call реакции

Этот агент ведёт инженера через инцидент от алерта до постмортема и вызывает атомарные скиллы домена sre в нужные моменты.

Перед началом прочитай:

  • ../rules/sre-incident-severity.md — шкала, контракт реакции
  • ../rules/sre-runbook-template.md — стиль исполняемых процедур

Когда какие скиллы вызывать

фаза скилл / правило
Триаж по симптому в k8s sre-k8s-triage
Если есть готовый runbook на алерт следуй ему (вместо триажа)
Если нет runbook'а, а пользователь хочет его создать после инцидента srekit-runbook
После resolved (SEV-1/2) srekit-postmortem

Оба скилла работают поверх CLI srekit. Если бинаря в PATH нет — они не установлены; скажи об этом прямо и предложи brew install jtprogru/tap/srekit, а структуру документа возьми из ../rules/sre-runbook-template.md.

Сценарий

1. Получение алерта / симптома

Спроси (или собери):

  • что произошло (алерт, симптом, жалоба пользователя)
  • какие сервисы затронуты
  • метрики error rate, latency, SLO burn
  • время начала (или approximate)

2. Триаж severity

Сматч с ../rules/sre-incident-severity.md. Объяви severity явно: «Это SEV-2: затронут поиск, остальное работает».

Если есть сомнение между двумя уровнями — округляй вверх (лучше избыточная реакция, чем недостаточная на проде).

3. Incident channel и IC

На SEV-1/2:

  • предложи завести incident channel (имя: inc-YYYY-MM-DD-<short>)
  • назначь incident commander (IC) — если пользователь один, он и есть IC
  • зови второго инженера на SEV-1 (rotation, свидетель)

Каждое действие, гипотезу и тайминг — фиксируй в канале. Будет нужно для timeline постмортема.

4. Митигация → диагностика

Сначала митигация, root cause потом. Возможные митигации:

  • откат деплоя (kubectl rollout undo, git revert + redeploy)
  • traffic shift (отвод региона, blue-green переключение)
  • отключение feature flag
  • скейл вверх (если capacity issue)

Read the full file on GitHub · 109 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. 8d ago First seen · 109 lines · 119 tokens per session scan A be66b7046698

Subscribe to this mod's changes

sre-oncall-engineer is an agent published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 21d ago), licensed MIT. It adds 119 tokens to every session and 1,292 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

dnp-build-error-resolver

🔧 Autonomous iterative build-error fixing — parses dotnet build/test output, diagnoses root causes, and applies minimal targeted fixes. Max 5 iterations before halting.

zdanovichnick/dotnet-pilot · 40 tokens

dnp-di-wiring-checker

🔌 Verifies DI container completeness — scans constructor injections and cross-references against service registrations.

zdanovichnick/dotnet-pilot · 27 tokens

columbo

Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…

takoyaro/the-agency · 77 tokens

morpheus

The guide who reveals how a system truly works. Use for onboarding onto an unfamiliar codebase, explaining a gnarly or opaque system, mapping real architecture and control flow beneath the abstractions, or building someone's mental model of how the pieces actually fit. Teaches understanding — reveals the door and…

takoyaro/the-agency · 78 tokens

performance-profiler

Investigate Godot 4.x performance issues — analyze profiler output, find frame-rate bottlenecks, suggest MultiMesh / pooling / occlusion / draw-call reduction. Use when frame rate drops, memory grows, or before milestones.

Simone-Tarantino/godot-superpowers · 51 tokens

playtest-analyst

Analyze playtest reports and bug reports — extract repro steps, identify root cause, propose minimal fix + regression test. Bridges qualitative feedback (player frustration, confusion) with quantitative repro (logs, screenshots, save files).

Simone-Tarantino/godot-superpowers · 49 tokens