post-mortem

A structured review process for understanding why a workflow, build, deployment, or operational task failed. It records the evidence, likely root cause, affected area, fixes, and ways to prevent a repeat.

In plain words
What is it for?
Use it after failed worker jobs, rejected pull requests, broken CI/CD pipelines, or other unexpected workflow results. It helps separate configuration, code, environment, and external causes.
Why use it?
It turns scattered logs and error messages into a consistent incident report. The analysis is read-only, so it does not change files while investigating.

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/silver2dream/ai-workflow-kit/post-mortem
Any agent
npx skills add silver2dream/ai-workflow-kit --skill post-mortem
Clone the repo
git clone --depth 1 https://github.com/silver2dream/ai-workflow-kit

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 526 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 $0.00050 $0.00526
Opus 5 $0.00025 $0.00263
Sonnet 5 $0.00010 $0.00105
Haiku 4.5 $0.00005 $0.00053

Measured 2d ago against content hash b1ae3c8e8591, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

post-mortem 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.

.ai/skills/post-mortem/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post-Mortem Skill

Structured failure analysis workflow for diagnosing and learning from workflow failures, build breaks, and operational incidents.

Overview

This skill provides a systematic approach to failure analysis when something goes wrong in the AWK workflow pipeline. It walks through evidence collection, root cause identification, impact assessment, and actionable remediation -- producing a structured report that can be referenced for future prevention.

When to Use

Use this skill when:

  • A Worker dispatch fails or times out
  • A PR is rejected due to unexpected errors
  • CI/CD pipeline breaks
  • awkit kickoff encounters unrecoverable errors
  • Any workflow step produces unexpected results
  • User invokes /post-mortem

Workflow

Phase 1: Analyze Failure

Read phases/analyze-failure.md

Walk through the structured failure analysis:

  1. Collect failure context (trace files, logs, error messages)
  2. Identify root cause (categorize: config, code, environment, external)
  3. Determine blast radius (what was affected)
  4. Generate remediation steps
  5. Create prevention measures
  6. Output structured report

Critical Rules

  1. DO NOT modify any files during analysis -- this is a read-only diagnostic skill
  2. Collect evidence first -- never jump to conclusions without supporting data
  3. Categorize accurately -- misclassification leads to wrong remediation
  4. Be specific in remediation -- vague advice is not actionable
  5. Always produce the structured report -- even if root cause is uncertain

Integration with AWK Workflow

This skill is used after a failure has occurred. It does not interfere with active workflows.

  • Safe to run while awkit kickoff is active (read-only)
  • Results can inform new issues created via /create-issues
  • Prevention measures may lead to config or rule updates

Self-Check

On each phase entry, output:

[POST-MORTEM] <timestamp> | <phase> | loaded: <filename>

Quick Reference

Phase Action File
1. Analyze Failure Full structured failure analysis phases/analyze-failure.md

Read the full file on GitHub · 67 lines

Files

What ships with it

1 file 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. 2d ago First seen · 67 lines · 0 tokens per session scan A b1ae3c8e8591

Subscribe to this mod's changes

post-mortem is a skill published in the GitHub repository silver2dream/ai-workflow-kit (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 526 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

create-interactive-slides

발표문·강의안·제품 시연을 스토리보드로 구조화하고 체험형 또는 시연형 HTML·CSS·JavaScript 슬라이드로 제작·검증한다. 내용에 맞는 인터랙션, 발표자 노트, 시연 cue, 리허설과 fallback이 필요할 때 사용한다. 일반 PPTX 편집이나 정적인 문서 작성에는 사용하지 않는다.

HYEXE/codex-plugins · 95 tokens

prompt-coach

사용자가 대상 작업을 실행하지 않고 재사용 가능한 최종 프롬프트 자체를 만들거나, 막연한 아이디어를 질문으로 구체화해 프롬프트만 함께 작성하려 할 때 사용한다. 요청의 충분성을 판단해 필요한 경우에만 핵심 질문을 하고 사용자의 의도·제약·권한을 보존한 프롬프트를 반환한다. Prompt Compiler 플러그인으로 일반 작업을 요청했거나 요청을 개선한 뒤 실제 수행·검증하는 것이 주목적이면 prompt-compiler를, 기존 프롬프트의 품질 평가·비교·회귀 진단이 주목적이면 prompt-evaluator를 사용한다.

HYEXE/codex-plugins · 151 tokens

prompt-evaluator

프롬프트, 에이전트 지침과 워크플로 명세를 의도 보존, 모호성, 권한 경계, 작업 분해, capability routing, 최신성, 검증 가능성과 instruction/data boundary 관점에서 진단하고 수정안·비교 결과·회귀 평가 케이스를 작성한다. 사용자가 기존 프롬프트의 리뷰, 평가, 문제 진단, 전후 비교, 회귀 테스트, red-team 점검을 요청하거나 Prompt Compiler의 동작 품질을 검증하려 할 때 사용한다. 실행하지 않고 새 최종 프롬프트를 함께 작성하는 것이 주목적이면 prompt-coach를, 요청을 먼저 보완한 뒤 실제…

HYEXE/codex-plugins · 171 tokens

implement-async-ui-state

기존 프론트엔드에서 요청·스트림·background job·batch 작업의 비동기 상태를 실제 코드로 구현하고 검증한다. 사용자가 upload·generate·export·save·agent·tool 실행 화면에 접수·진행·사용자 입력 대기·부분 성공·오류·취소·재시도·재연결을 구현하거나 중복 실행, optimistic rollback, stale·late response와 job identity 문제를 해결해 달라고 할 때 사용한다. Dialog·Combobox·Carousel의 키보드·포커스·제스처 계약이 주 결과면…

HYEXE/codex-plugins · 183 tokens

implement-ui-interaction

기존 프론트엔드에 키보드·포커스·터치·포인터·제스처가 정확한 widget 상호작용을 구현하고 검증한다. 사용자가 Dialog, Popover, Tooltip, Menu, Combobox, Carousel, drag·swipe·pinch 또는 floating positioning을 실제 코드로 만들어 달라고 할 때 사용한다. 요청·스트림·background job·batch의 중복 실행, 취소·재시도·부분 성공 같은 비동기 작업 수명주기가 주 결과면 implement-async-ui-state를, 시간 기반 모션 자체가 주 결과면…

HYEXE/codex-plugins · 180 tokens

build-data-visualization

데이터와 사용자 과업에 맞는 차트·시각화 표현을 정하고 Bklit UI, Recharts, Apache ECharts, Observable Plot, D3 또는 기존 도구로 실제 프론트엔드에 구현·검증한다. 사용자가 대시보드 차트, 분석 화면, 실시간·대용량 시각화, 지도·네트워크·사용자 정의 그래픽, Bklit UI 설치·활용이나 접근 가능한 데이터 표현을 요청할 때 사용한다. 원칙 설명·명세만 필요하면 uiux-advisor를, 기존 차트 감사만 필요하면 uiux-auditor를 사용한다.

HYEXE/codex-plugins · 145 tokens