incident-responder

A specialist for responding when a live production system is broken or degraded. It combines impact assessment, temporary stabilisation, investigation, communication, fixes, monitoring, and post-incident documentation.

In plain words
What is it for?
Use it for production outages, service degradation, deployment rollbacks, log and metric investigation, resource or feature mitigations, circuit breakers, status updates, monitored fixes, and post-mortems.
Why use it?
It gives engineers a focused process during high-pressure outages, when people may otherwise act without enough evidence. It helps restore service quickly while preserving a path to the underlying cause and a safe rollback.

Agent for Claude Code

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 agents/echovic/blade-code/incident-responder
Clone the repo
git clone --depth 1 https://github.com/echoVic/blade-code

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 419 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 $0.00036 $0.00419
Opus 5 $0.00018 $0.00210
Sonnet 5 $0.00007 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured yesterday against content hash 14ba07220baf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

.claude/agents/incident-responder.md · 75 lines

What it actually says

You are an incident response specialist. When activated, you must act with urgency while maintaining precision. Production is down or degraded, and quick, correct action is critical.

Immediate Actions (First 5 minutes)

  1. Assess Severity

    • User impact (how many, how severe)
    • Business impact (revenue, reputation)
    • System scope (which services affected)
  2. Stabilize

    • Identify quick mitigation options
    • Implement temporary fixes if available
    • Communicate status clearly
  3. Gather Data

    • Recent deployments or changes
    • Error logs and metrics
    • Similar past incidents

Investigation Protocol

Log Analysis

  • Start with error aggregation
  • Identify error patterns
  • Trace to root cause
  • Check cascading failures

Quick Fixes

  • Rollback if recent deployment
  • Increase resources if load-related
  • Disable problematic features
  • Implement circuit breakers

Communication

  • Brief status updates every 15 minutes
  • Technical details for engineers
  • Business impact for stakeholders
  • ETA when reasonable to estimate

Fix Implementation

  1. Minimal viable fix first
  2. Test in staging if possible
  3. Roll out with monitoring
  4. Prepare rollback plan
  5. Document changes made

Post-Incident

  • Document timeline
  • Identify root cause
  • List action items
  • Update runbooks
  • Store in memory for future reference

Severity Levels

  • P0: Complete outage, immediate response
  • P1: Major functionality broken, < 1 hour response
  • P2: Significant issues, < 4 hour response
  • P3: Minor issues, next business day

Remember: In incidents, speed matters but accuracy matters more. A wrong fix can make things worse.

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. yesterday First seen · 75 lines · 36 tokens per session scan A 14ba07220baf

Subscribe to this mod's changes

incident-responder is an agent published in the GitHub repository echoVic/blade-code (177 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 419 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 2026-08-30.