Incident Response Planner

Incident Response Planner is a skill for Claude Code, Codex from AgentEra/Agently. It costs 37 tokens per session (282 once invoked), scanned A, original, Apache-2.0.

A procedure for turning an infrastructure alert into a response plan and an on-call runbook. An infrastructure incident is a problem affecting services or systems; an on-call runbook is a checklist an engineer can follow during an outage or alert.

In plain words
What is it for?
Use it to assess incidents, choose immediate mitigations, coordinate responders, investigate failures in order, estimate resolution time, and write an executable checklist.
Why use it?
It organizes urgent work around severity, impact, mitigation, investigation, communication, and timing. It also makes each action verifiable and includes rollback guidance for irreversible steps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to assess incidents, choose immediate mitigations, coordinate responders, investigate failures in order, estimate resolution time, and write an executable checklist.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentera/agently/incident-response-planner
About the project

Agently is a Python framework for building AI applications that coordinate language models, structured data, tools, and multi-step workflows. Teams use it to create assistants, internal copilots, knowledge tools, operational workflows, and AI-backed APIs.

AgentEra/Agently · 1,649 stars · on GitHub · agently.tech

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 AgentEra/Agently --skill incident-response-planner
Clone the repo
git clone --depth 1 https://github.com/AgentEra/Agently

Made for: Claude Code, Codex.

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 Planner

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentera/agently/incident-response-planner.svg)](https://agentmods.dev/skills/agentera/agently/incident-response-planner)
Your own site
<a href="https://agentmods.dev/skills/agentera/agently/incident-response-planner"><img src="https://agentmods.dev/badge/skills/agentera/agently/incident-response-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 282 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00037 $0.00282
Opus 5 $0.00018 $0.00141
Sonnet 5 $0.00007 $0.00056
Haiku 4.5 $0.00004 $0.00028

Measured 9d ago against content hash c86fdf5a9d07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Incident Response Planner 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.

examples/archived/pre-4.1.3.8-skills-orchestration/agent_auto_orchestration/skills/incident-response-planner/SKILL.md · 30 lines

What it actually says

Incident Response Planner

You are an SRE incident commander. Given an incident alert, produce two things in one response: a response plan and a runbook.

Response plan

Cover all six areas, be specific and actionable, avoid generic advice:

  1. Severity assessment (P0/P1/P2/P3) with justification.
  2. Impact radius (which services, users, regions are affected).
  3. Immediate mitigation actions (what to do right now).
  4. Investigation steps (what to investigate and in what order).
  5. Stakeholders to notify (teams, roles, external parties).
  6. Expected resolution timeline (best case / worst case).

Runbook

Convert the plan into a step-by-step checklist an on-call engineer can follow at 3 AM. Each step states: the action, the owner role (e.g. on-call SRE, database team, security), the expected outcome, and a verification check. Include rollback steps for any irreversible action.

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 · 30 lines · 37 tokens per session scan A c86fdf5a9d07

Subscribe to this mod's changes

Incident Response Planner is a skill published in the GitHub repository AgentEra/Agently (1,649 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 282 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.