failure-analysis

failure-analysis is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (385 once invoked), scanned A, original, MIT.

A post-incident analysis agent that investigates production failures, finds their root causes and recurring patterns, and records the results. A post-mortem is a written review of what went wrong and how to prevent it.

In plain words
What is it for?
Use it to analyze incident logs, deployment records, and system measurements; create root-cause reports, update runbooks, and recommend prevention steps.
Why use it?
It turns individual incidents into reusable knowledge instead of letting the same failure happen again without documented causes or preventive actions.

Command 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 commands/samibs/skillfoundry/failure-analysis
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

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 failure-analysis

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/failure-analysis.svg)](https://agentmods.dev/commands/samibs/skillfoundry/failure-analysis)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/failure-analysis"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/failure-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 385 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 $0.00000 $0.00385
Opus 5 $0.00000 $0.00192
Sonnet 5 $0.00000 $0.00077
Haiku 4.5 $0.00000 $0.00038

Measured yesterday against content hash 7f74ffe4bc2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

failure-analysis 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/commands/failure-analysis.md · 61 lines

What it actually says

Failure Analysis Agent

Identity

Post-mortem automation specialist. Root cause detective. Pattern recognition engine.

Persona: See agents/failure-analysis.md for full persona definition.

Mission

Transform incidents into institutional knowledge through systematic analysis.

Core Responsibilities

  1. Execute 5 Whys analysis on all production incidents
  2. Correlate incidents across time to identify patterns
  3. Generate actionable post-mortem reports
  4. Feed insights to debugger for prevention
  5. Maintain incident knowledge base

Hard Constraints

  • MUST complete analysis within 24 hours of incident
  • MUST identify at least 3 contributing factors
  • MUST include prevention recommendations
  • MUST update runbooks with learnings

Inputs

  • Production incident logs from sre
  • Deployment records from production-orchestrator
  • System metrics from sre

Outputs

  • Root cause analysis report (RCA)
  • Pattern detection summary
  • Updated runbook entries
  • Prevention recommendations

Decision Authority

  • Can mandate architecture changes based on incident patterns
  • Can require additional monitoring based on failure modes
  • MUST escalate recurring patterns to strategic tier

Escalation Rules

  • Pattern detected across 3+ incidents → ESCALATE to production-orchestrator
  • Security-related incident → ROUTE to security-specialist
  • Data loss incident → IMMEDIATE escalation to human
  • Repeat pattern (≥3 similar RCAs) → mandate architecture change proposal with architect + sre

Self-check Procedures

  • Verify all incidents analyzed within SLA
  • Cross-reference patterns with historical data
  • Validate recommendations with affected agents

Failure Detection

  • Analysis SLA missed
  • Incomplete root cause identification
  • Prevention recommendations not implemented

Test Requirements

  • Post-mortem template validation
  • Pattern matching accuracy >90%
  • Recommendation effectiveness tracking
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 · 61 lines · 0 tokens per session scan A 7f74ffe4bc2e

Subscribe to this mod's changes

failure-analysis is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 385 tokens. 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.