incident-response

An incident-management guide covering the response to outages and other operational problems. It supports triage, communication, mitigation, and a postmortem, which is a review of what happened and how to prevent a repeat.

In plain words
What is it for?
Use it to start an incident, publish status updates, manage mitigation, or create a blameless root-cause report after the incident.
Why use it?
It keeps teams from fixing silently, skipping severity assessment, blaming individuals, or closing an incident without prevention work. It also keeps rollback available as a mitigation option.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00041 $0.02126
Opus 5 $0.00020 $0.01063
Sonnet 5 $0.00008 $0.00425
Haiku 4.5 $0.00004 $0.00213

Measured 2d ago against content hash db3afdeda7a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

incident-response scanned grade A with 1 finding 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.

Makes network callslowCapability

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

- Use `curl`/`wget` to fetch dashboards or error pages mentioned
skills/incident-response/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incident Response

You are managing an incident through its full lifecycle using structured incident management practices.

Red Flags — STOP if you're

  • Fixing before communicating (stakeholders must know first)
  • Skipping severity classification
  • Writing a postmortem with blame (blameless only)
  • Closing an incident without prevention items
  • Ignoring rollback as a mitigation option

Communicate first. Fix second. Learn always.


Pre-Check

  1. Check for Draft context:
ls draft/ 2>/dev/null

This skill works standalone — incidents don't wait for project setup.

  1. If available, follow the base procedure in core/shared/draft-context-loading.md.

Step 1: Parse Arguments

  • /draft:incident-response new <description> — Start new incident
  • /draft:incident-response update <status> — Post status update
  • /draft:incident-response postmortem — Generate postmortem report
  • /draft:incident-response (no args) — Interactive: ask which mode

NEW Mode — Start Incident

Step 2: Triage

Classify severity:

Level Response Time Who Examples
SEV1 Immediate, all-hands Entire team Data loss, complete outage, security breach
SEV2 15 minutes On-call + team lead Major feature broken, significant degradation
SEV3 1 hour On-call Minor feature broken, workaround exists
SEV4 Next business day Assigned engineer Cosmetic issue, minor inconvenience

Assess:

  1. What is broken? (from description or Jira ticket)
  2. Who is affected? (from draft/product.md user types if available)
  3. What is the blast radius? (from draft/.ai-context.md service topology if available)
  4. Is data at risk? (escalate to SEV1 if yes)

Step 3: Communicate

Generate initial status update:

INCIDENT: {description}
Severity: SEV{1-4}
Impact: {who/what is affected}
Status: Investigating
Commander: {name or "unassigned"}
Next update: {time — SEV1: 15min, SEV2: 30min, SEV3: 1hr}

Read the full file on GitHub · 249 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 · 249 lines · 41 tokens per session scan A db3afdeda7a0

Subscribe to this mod's changes

incident-response is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 14d ago), licensed MIT. It adds 41 tokens to every session and 2,126 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.