incident

incident is a skill for Claude Code from kimsanguine/hplan. It costs 50 tokens per session (3,087 once invoked), scanned A, original, MIT.

A response process for failures involving AI agents. It helps detect and classify incidents, limit their impact, coordinate recovery, and record lessons for preventing similar failures.

In plain words
What is it for?
Use it when accuracy drops, costs rise unexpectedly, sensitive information may be exposed, users report serious problems, or monitoring detects a sharp increase in errors.
Why use it?
Agent failures may be subtle, such as incorrect answers or unexpected cost increases, and can continue unnoticed. This provides a structured way to investigate real impact and reduce repeat incidents.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the operate plugin — 6 skills shipped together

Good fit Use it when accuracy drops, costs rise unexpectedly, sensitive information may be exposed, users report serious problems, or monitoring detects a sharp increase in errors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kimsanguine/hplan/incident
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 kimsanguine/hplan --skill incident
Clone the repo
git clone --depth 1 https://github.com/kimsanguine/hplan

Made for: Claude Code.

Or install operate, the plugin that ships this one along with the rest of its 6 skills.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimsanguine/hplan/incident.svg)](https://agentmods.dev/skills/kimsanguine/hplan/incident)
Your own site
<a href="https://agentmods.dev/skills/kimsanguine/hplan/incident"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/incident.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,087 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 $0.00050 $0.03087
Opus 5 $0.00025 $0.01543
Sonnet 5 $0.00010 $0.00617
Haiku 4.5 $0.00005 $0.00309

Measured 8d ago against content hash 32d14ddb5873, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

incident 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 8d 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.

operate/skills/incident/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Incident Response

에이전트 장애 대응 프로토콜 — 발견, 분류, 대응, 복구, 학습

Core Goal

  • 에이전트 장애를 신속하게 감지하고 대응 — 침묵의 실패(Silent Failure)를 조기에 찾아내고 격리
  • 블래스트 반경을 제한하고 영향 최소화 — 영향받은 사용자/비용 범위를 정확히 파악 후 신속 복구
  • 장애 경험을 암묵지로 추출 — TK로 기록해서 비슷한 실패의 재발 방지

Trigger Gate

Use This Skill When

  • 에이전트 정확도가 급락(> 10% 한 번에)했을 때
  • 비용이 갑자기 폭증(2배 이상)했을 때
  • PII 또는 민감 정보 유출 신호가 있을 때
  • 사용자 신고 또는 SNS 부정적 언급이 들어왔을 때
  • 내부 QA/모니터링에서 에러율 급증을 탐지했을 때

Route to Other Skills When

  • reliability (Pre-mortem 섹션) → 장애 원인 분석 후 유사 실패 예방 메커니즘 설계
  • ops-review --mode cost → 비용 폭증이 토큰 사용량 이상이라면 (비용 최적화 필요)
  • reliability → 장애 복구 후 신뢰성 개선 계획 수립
  • metrics-design (코호트 분석 섹션) → 특정 버전/세그먼트만 장애를 겪었다면 (코호트 분석)

Boundary Checks

  • 실제 장애 vs 정상 변동 — Accuracy 1-2% 변화는 정상 범위, > 5% 이상이면 조사
  • 원인 판단 과정 — 5 Whys를 최소 3단계 이상 실행해야 근본 원인 파악 가능
  • 영향도 산정 정확성 — 추정이 아닌 실제 영향받은 사용자/트래잭션 로그 기반 확인

개념

에이전트 장애는 일반 소프트웨어 장애와 다르다. "서버가 죽었다"는 명확하지만, "에이전트가 환각으로 잘못된 답을 줬다"는 발견 자체가 어렵다. 침묵의 실패(Silent Failure)가 에이전트 장애의 가장 위험한 유형이다.

Instructions

You are running incident response for: $ARGUMENTS

Step 1 — Incident Detection & Classification

발견 시각: [timestamp]
발견 방법:
  □ 자동 모니터링 알림
  □ 사용자 신고
  □ 내부 QA 발견
  □ 비용 이상 감지
  □ 외부 보고 (SNS, 언론)

Severity Classification:

SEV 정의 예시 대응 시간
SEV-1 전체 서비스 중단 또는 데이터 유출 에이전트가 PII를 외부에 노출 15분 이내
SEV-2 핵심 기능 장애, 다수 유저 영향 정확도 50% 이하로 급락, 비용 10배 폭등 1시간 이내
SEV-3 일부 기능 저하, 소수 유저 영향 특정 입력에서 환각 반복 4시간 이내
SEV-4 경미한 품질 저하, 우회 가능 응답 속도 저하, 포맷 깨짐 24시간 이내

Step 2 — Immediate Response

에이전트 장애 유형별 긴급 대응:

🔴 환각/오정보 장애:
  1. 해당 에이전트 기능 즉시 비활성화
  2. 영향 범위 확인 (몇 명이 잘못된 정보를 받았는가?)
  3. 영향받은 유저에게 정정 통보
  4. 원인 분석 (프롬프트 문제? 모델 변경? 입력 데이터 오염?)

🔴 비용 폭등 장애:
  1. API 호출 rate limit 즉시 설정
  2. 비용 발생 원인 추적 (무한 루프? 토큰 폭발? 잘못된 모델 라우팅?)
  3. 비용 캡 설정
  4. 영향받은 기간의 비용 산출

🔴 데이터 유출 장애:
  1. 에이전트 즉시 중단
  2. 유출 범위 파악 (어떤 데이터, 누구에게, 어디로)
  3. 법무팀 즉시 통보
  4. 규제 보고 필요 여부 판단 (GDPR, 개인정보보호법)

🔴 연쇄 실패 장애 (멀티에이전트):
  1. 오케스트레이터 에이전트 중단
  2. 하위 에이전트 상태 확인
  3. 실패 전파 경로 추적
  4. 격리 후 개별 에이전트 순차 재시작

Read the full file on GitHub · 301 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 301 lines · 50 tokens per session scan A 32d14ddb5873

Subscribe to this mod's changes

incident is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 22d ago), licensed MIT. It adds 50 tokens to every session and 3,087 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 2026-08-31.

Related

Other skills, from other repositories

codex-setup

Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.

sd0xdev/sd0x-harness · 65 tokens

smart-rebase

Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…

sd0xdev/sd0x-harness · 131 tokens

recap-doc

Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…

sd0xdev/sd0x-harness · 114 tokens

runbook

Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).

sd0xdev/sd0x-harness · 59 tokens

test-review

Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.

sd0xdev/sd0x-harness · 56 tokens

debug

Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.

sd0xdev/sd0x-harness · 67 tokens