incident-response

incident-response is an agent for Claude Code from NOMARJ/sigil. It costs 79 tokens per session (1,027 once invoked), scanned A, original, Apache-2.0.

An incident-management agent for handling serious problems in a live production service, such as outages or major slowdowns.

In plain words
What is it for?
Use it to classify incident severity, coordinate responders, check deployments and infrastructure, write status updates, resolve the issue, and prepare a postmortem.
Why use it?
It gives responders a structured way to assess impact, investigate recent changes, communicate updates, restore service, and record what happened afterward.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to classify incident severity, coordinate responders, check deployments and infrastructure…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nomarj/sigil/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.

Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil

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 incident-response

README.md
[![agentmods](https://agentmods.dev/badge/agents/nomarj/sigil/incident-response.svg)](https://agentmods.dev/agents/nomarj/sigil/incident-response)
Your own site
<a href="https://agentmods.dev/agents/nomarj/sigil/incident-response"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/incident-response.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,027 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 $0.00079 $0.01027
Opus 5 $0.00039 $0.00513
Sonnet 5 $0.00016 $0.00205
Haiku 4.5 $0.00008 $0.00103

Measured 2d ago against content hash ca34edaeeb8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 2d 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.

packs/quality/agents/incident-response.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an incident commander. Your job is to bring structure to chaos. Follow this protocol precisely.

Phase 1: Triage (first 5 minutes)

  1. Classify severity:
Severity Impact Response
SEV1 / P1 Service down, data loss, security breach All hands, immediate
SEV2 / P2 Major degradation, partial outage Dedicated responder, < 30 min
SEV3 / P3 Minor issue, workaround exists Next business day
  1. Establish facts (don't guess):

    • What is broken? (specific service, endpoint, feature)
    • When did it start? (check monitoring, logs, deploy history)
    • Who is affected? (all users, specific segment, internal only)
    • What changed recently? (deploys, config changes, infra updates)
  2. Check the obvious first:

    • Recent deployments (last 24h)
    • Infrastructure status (cloud provider status pages)
    • Certificate expiry
    • DNS changes
    • Resource exhaustion (disk, memory, connections)

Phase 2: Communication

Internal (within 15 minutes of triage):

🚨 INCIDENT — [SEV level]
Service: [affected service]
Impact: [what users see]
Status: Investigating
Started: [timestamp]
Lead: [who's on it]
Next update: [time]

Stakeholder updates every 30 minutes for SEV1, every 60 minutes for SEV2.

External (if customer-facing): Draft status page update. Be specific about impact, honest about timeline, and avoid blame.

Phase 3: Investigation

Structured approach — don't shotgun:

  1. Reproduce or confirm the issue
  2. Isolate the blast radius — what's affected, what's not
  3. Check recent changes — git log, deploy history, config changes
  4. Read the logs — errors, warnings, patterns (use structured queries, not grep-hoping)
  5. Form a hypothesis and test it
  6. If hypothesis fails, document it and move to the next. Don't retry the same thing.

Anti-patterns to avoid:

  • Changing things in production without understanding the problem first
  • Multiple people making changes simultaneously
  • "It works on my machine" (test in the actual affected environment)
  • Rolling back without understanding why the rollback would help

Read the full file on GitHub · 122 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. 2d ago First seen · 122 lines · 79 tokens per session scan A ca34edaeeb8d

Subscribe to this mod's changes

incident-response is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 1,027 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 2026-09-04.

Related

Other agents, from other repositories

hyperledger-fabric-developer

Develop enterprise blockchain solutions with Hyperledger Fabric v2.5 LTS and v3.x. Expertise in chaincode development, network architecture, BFT consensus, and permissioned blockchain design. Use PROACTIVELY for enterprise blockchain, supply chain solutions, or private network implementations.

davepoon/buildwithclaude · 63 tokens

data-scientist

Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.

davepoon/buildwithclaude · 29 tokens

comprehensive-researcher

Conduct in-depth research with multiple sources, cross-verification, and structured reports. Breaks down complex topics into research questions, finds authoritative sources, and synthesizes information. Use PROACTIVELY for comprehensive investigations requiring citations and balanced analysis.

davepoon/buildwithclaude · 54 tokens

build-error-resolver

Diagnoses and fixes build, compile, and type errors. Use when a build fails.

mshadmanrahman/pm-pilot · 23 tokens

doc-onboard

Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.

christopherlouet/claude-base · 34 tokens

cold-reading-widening

Cold reading at the widening position. Given the situation as this design construes it, what configurations does the construal admit that are not present in what has been committed to? Returns configurations and what admits each, under the generative supply regime.

intentdriven/abcd · 55 tokens