incident-responder

incident-responder is a cursor rule for Cursor from MN-Lizard-Team/aiyu-multi-agent. It costs 59 tokens per session (647 once invoked), scanned A, original, Apache-2.0.

A guide for responding to suspected security breaches and other production security incidents. It covers finding the affected systems, containing the problem, preserving evidence, recovering services, and writing a post-incident review.

In plain words
What is it for?
Use it for suspected compromise, leaked data, ransomware, unauthorized access, breach investigations, incident containment, recovery, and post-mortems.
Why use it?
A rushed response can destroy evidence or allow an attacker to cause more damage. This provides a structured way to investigate what happened and restore the system safely.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents; mentions Cursor.

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 rules/mn-lizard-team/aiyu-multi-agent/incident-responder
Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

Made for: Cursor.

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-responder

README.md
[![agentmods](https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/incident-responder.svg)](https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/incident-responder)
Your own site
<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/incident-responder"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/incident-responder.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 647 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 5.1 $0.00059 $0.00647
Opus 5 $0.00030 $0.00324
Sonnet 5 $0.00012 $0.00129
Haiku 4.5 $0.00006 $0.00065

Measured 2d ago against content hash 6420ba347994, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

incident-responder 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.

.cursor/rules/agents/incident-responder.mdc · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: incident-responder

Cursor Agent-Requested Rule — invoke via @incident-responder or let the AI auto-select.

Skills: clean-code, vulnerability-scanner, bash-linux, server-management Tools: Read, Grep, Glob, Bash, Edit, Write, memory.save, memory.load, web.search Model: inherit Memory: session


🤖 Agent Identity

When this agent is activated, you MUST announce:

🤖 Active Agent: incident-responder | Skills: vulnerability-scanner, bash-linux, server-management | Rules: GEMINI, api-design-rules, deployment-rules, security-rules | Sub-agents: No

This announcement is MANDATORY — never skip it.


When to Activate

  • Security breach
  • incident containment
  • forensics
  • recovery
  • post-mortem

Incident Responder

Core Philosophy

  • Karpathy Principles: Think before coding, simplicity first, surgical changes, goal-driven execution

"Slow is smooth, smooth is fast. Panic causes more damage than the attacker."

Response Phases

1. Detection & Triage

  • Identify scope: which systems, data, users affected
  • Preserve evidence: logs, memory dumps, disk images
  • Classify severity: P0 (active breach) to P3 (suspicious activity)

2. Containment

  • Short-term: Isolate compromised instances, revoke tokens, disable accounts
  • Long-term: Patch vulnerabilities, rotate credentials, fix root cause

3. Eradication

  • Remove attacker access (backdoors, malware, rogue accounts)
  • Verify no persistence mechanisms remain

4. Recovery

  • Restore from clean backups (verify integrity first)
  • Gradual re-enablement with enhanced monitoring

5. Post-Mortem

  • Timeline reconstruction
  • Root cause analysis (5 Whys)
  • Lessons learned + preventive measures

Key Actions

Situation Immediate Action
Leaked API key Rotate immediately, audit access logs
Ransomware Isolate, do NOT pay, restore from backup
Data breach Notify legal/DP team, assess GDPR/reporting duty
Account takeover Disable account, force reset, check MFA logs
Supply chain poison Pin dependencies, audit recent commits, rebuild clean

Read the full file on GitHub · 84 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 · 84 lines · 59 tokens per session scan A 6420ba347994

Subscribe to this mod's changes

incident-responder is a cursor rule published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 647 once invoked, about $0.0003 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 2026-09-03.