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.
npx skills add robisson/build-like-amazon-agent-skills --skill correction-of-errorsgit clone --depth 1 https://github.com/robisson/build-like-amazon-agent-skillsWrote 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.
[](https://agentmods.dev/skills/robisson/build-like-amazon-agent-skills/correction-of-errors)<a href="https://agentmods.dev/skills/robisson/build-like-amazon-agent-skills/correction-of-errors"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/correction-of-errors/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/robisson/build-like-amazon-agent-skills/correction-of-errors"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/correction-of-errors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01917 |
| Opus 5 | $0.00015 | $0.00958 |
| Sonnet 5 | $0.00006 | $0.00383 |
| Haiku 4.5 | $0.00003 | $0.00192 |
Grade A, and why
Correction of Errors 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Correction of Errors (COE)
Overview
A Correction of Errors (COE) is a blameless post-incident document that analyzes what happened, why it happened, and what mechanisms will prevent recurrence. The goal is not to assign blame—it is to improve the system so the same class of failure cannot happen again. COEs produce mechanisms (automated safeguards), not promises ("we'll be more careful"). Every COE must result in concrete action items with owners and due dates that make the system more resilient.
When to Use
- After any incident that reveals a systemic gap (even if low severity)
- After near-misses that could have been highly severy with slightly different conditions
- When the same type of failure recurs (even at low severity)
- When requested by leadership for learning purposes
Agent Persona
Load agents/coe-reviewer.md when reviewing a COE. Use it to enforce blameless analysis, timeline accuracy, root-cause depth, mechanism quality, and concrete action items with owners and dates.
Amazon Context
Amazon's COE process is one of its most powerful learning mechanisms. The document is written by the team that experienced the incident, reviewed by senior leadership, and shared broadly for organizational learning. The key insight: people don't cause failures—systems allow failures. If a single person's mistake can cause a customer-impacting incident, the system lacks sufficient safeguards. COEs that conclude "the engineer should have been more careful" are rejected. COEs that conclude "we will add an automated check that prevents this class of error" are accepted.
The Process
Timeline (Within 24 hours of incident)
- Incident Commander or on-call engineer drafts initial timeline
- All participants review and add their perspective
- Timeline must include:
- Exact times (timezone-explicit) for each event
- What was observed at each point
- What actions were taken and by whom
- What information was available (and what wasn't)
- When customer impact started and ended
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.
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.
- 10d ago First seen · 171 lines · 31 tokens per session scan A 0dbcca1fbcd4
Correction of Errors is a skill published in the GitHub repository robisson/build-like-amazon-agent-skills (14 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 1,917 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.
Other skills, from other repositories
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
comet-hotfix
A quick workflow for fixing an existing bug in Comet, a tool that manages structured code changes. It moves through opening the change, building, checking, and archiving it.