incident-response

incident-response is a skill for Claude Code from juanmhidalgo/claude-plugins. It costs 47 tokens per session (1,831 once invoked), scanned A, original, MIT.

A workflow for handling production incidents, meaning serious problems that affect users or a live service.

In plain words
What is it for?
Use it for initial triage, severity and role assignment, status updates, and a blameless postmortem after the incident.
Why use it?
It helps teams coordinate quickly during an outage and review what happened afterward without blaming individuals.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the debug plugin — 2 skills, 2 commands shipped together

Good fit Use it for initial triage, severity and role assignment, status updates, and a blameless postmortem after the incident.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/juanmhidalgo/claude-plugins/incident-response
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.

Any agent
npx skills add juanmhidalgo/claude-plugins --skill incident-response
Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Made for: Claude Code.

Or install debug, the plugin that ships this one along with the rest of its 2 skills, 2 commands.

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 incident-response

README.md
[![agentmods](https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/incident-response/github.svg)](https://agentmods.dev/skills/juanmhidalgo/claude-plugins/incident-response)
Your own site
<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/incident-response"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/incident-response/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 incident-response

Your own site · 80×15
<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/incident-response"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/incident-response.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,831 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 $0.00047 $0.01831
Opus 5 $0.00023 $0.00915
Sonnet 5 $0.00009 $0.00366
Haiku 4.5 $0.00005 $0.00183

Measured 9d ago against content hash 5fa9e58adacc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

incident-response 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 9d 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.

debug/skills/incident-response/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incident Response

Run an incident through three phases: new (triage) → update (status broadcast) → postmortem (blameless retrospective).

When to use this vs. debugging-strategies

  • Incident response: production is degraded, multiple users affected, time-pressured, multi-actor coordination needed.
  • debugging-strategies: a bug in your local environment or CI, single engineer working through it.

If you started in debugging-strategies and it escalated into a customer-impacting outage, switch here. The mindset shifts from "find the cause" to "stop the bleeding, then find the cause." The actual investigation work still uses debug:debugging-strategies — this skill is the coordination layer on top.

Mode 1 — new: Triage

Detect, classify severity, assign roles. The first 5 minutes set the trajectory.

Severity Classification

Level Criteria Response
SEV1 Service down for all users / data loss in progress / security breach Immediate; all-hands; page incident commander
SEV2 Major feature degraded for many users / persistent errors on critical paths Within 15 min; assign IC and comms
SEV3 Minor feature issue for some users / non-critical degradation Within 1 hour; one responder
SEV4 Cosmetic / low-impact / single-user issue Next business day; ticket

Triage Output Template

# Incident: <title>
**Severity**: SEV<X>
**Detected**: <timestamp>  **Detected by**: <alert / customer / oncall>
**Affected**: <users / regions / features>

## Initial Hypothesis
<one paragraph — what we currently think is happening, with confidence>

## Roles
- **Incident Commander**: <name>
- **Communications**: <name>
- **Responders**: <names>

## Immediate Actions
- [ ] <stop-the-bleeding step>
- [ ] <containment step>
- [ ] <data-collection step (logs, metrics, repro)>

Mode 2 — update: Status Broadcast

Post regular updates to keep stakeholders informed. Cadence:

  • SEV1: every 15 minutes minimum
  • SEV2: every 30 minutes
  • SEV3: every 1 hour or on status change

Read the full file on GitHub · 175 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. 9d ago First seen · 175 lines · 47 tokens per session scan A 5fa9e58adacc

Subscribe to this mod's changes

incident-response is a skill published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,831 once invoked, about $0.0002 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 skills, from other repositories