incident-learning-loop

A process for turning incident findings into lasting engineering rules and safeguards. An incident is a failure in a live system; this skill helps apply its lessons beyond the service where it happened.

In plain words
What is it for?
Use it after post-incident reviews to update standards, templates, checklists, runbooks, alerts, and code-review requirements, and to look for the same risk in other services.
Why use it?
It prevents teams from fixing only the immediate problem while leaving similar weaknesses elsewhere.

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/caiaffa/claude-code-ultimate-engineering-system/incident-learning-loop
Any agent
npx skills add caiaffa/claude-code-ultimate-engineering-system --skill incident-learning-loop
Clone the repo
git clone --depth 1 https://github.com/caiaffa/claude-code-ultimate-engineering-system

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 472 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 $0.00024 $0.00472
Opus 5 $0.00012 $0.00236
Sonnet 5 $0.00005 $0.00094
Haiku 4.5 $0.00002 $0.00047

Measured 3d ago against content hash 715be53ef3bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

incident-learning-loop 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 3d 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.

skills/incident-learning-loop/SKILL.md · 44 lines

What it actually says

Mission

Ensure every serious incident improves the engineering system, not just the affected service.

When to use

  • Closing a postmortem.
  • Deciding what should become a standard.
  • Updating templates, checklists, or runbooks after incidents.
  • Propagating lessons beyond the local failure.

Handoff

  • Receives from: postmortem-reviewer (after postmortem analysis) or deep-root-cause-investigator.
  • Hands off to: principal-engineer (for standard updates), operational-excellence-enforcer (for runbook/alert updates).

The learning extraction process

For every incident, ask:

  1. What class of failure was this? (not "what happened" but "what category")
    • Examples: missing idempotency, schema migration lock, stale cache read, missing circuit breaker
  2. What invariant was violated? (check against SYSTEM_INVARIANTS.md)
  3. What standard should change? (PROJECT_CONVENTIONS.md, DECISION_RULES.md, etc.)
  4. What template or checklist should be updated? (SERVICE_SCORECARD.md, DEFINITION_OF_DONE.md, etc.)
  5. What other services have this same exposure? (lateral scan)
  6. What review requirement should be added? (new item in code review, ADR review, etc.)

Red flags — learning is too shallow if

  • Lesson stays local to one team or service.
  • Fix applied to code but no standard or process changes.
  • Runbook improved but the design that caused the incident is unchanged.
  • Same class of failure is still possible in 3 other services.
  • Action items are all "add monitoring" without prevention.

Output format

  1. Class of failure (categorized)
  2. Systemic lesson (what the org should learn)
  3. Standards to update (specific files and changes)
  4. Templates/checklists to add or modify (specific)
  5. Other exposed services (lateral risk scan)
  6. Wider rollout plan (how to propagate the fix beyond this service)
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. 3d ago First seen · 44 lines · 24 tokens per session scan A 715be53ef3bf

Subscribe to this mod's changes

incident-learning-loop is a skill published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (17 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 472 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens