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 mechanism-creationgit 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/mechanism-creation)<a href="https://agentmods.dev/skills/robisson/build-like-amazon-agent-skills/mechanism-creation"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/mechanism-creation/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/mechanism-creation"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/mechanism-creation.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 | $0.00016 | $0.01923 |
| Opus 5 | $0.00008 | $0.00962 |
| Sonnet 5 | $0.00003 | $0.00385 |
| Haiku 4.5 | $0.00002 | $0.00192 |
Grade A, and why
Mechanism Creation 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 11d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mechanism Creation
Overview
A mechanism is an automated system, process, or tool that prevents a known class of failure without requiring human vigilance. Mechanisms replace good intentions with guaranteed outcomes. When you discover a problem—through COEs, operational reviews, or metrics analysis—the highest-quality response is not "we'll be more careful" but "we'll build a mechanism that makes this class of error impossible." Mechanisms are Amazon's primary tool for converting incidents into permanent improvements.
When to Use
- After any COE identifies a systemic gap
- When the same type of issue recurs despite awareness
- When a manual process is the only thing preventing failure
- When a checklist item is routinely missed
- When "human error" is cited as a root cause (this means a mechanism is missing)
- When scaling a process beyond what human attention can reliably cover
Amazon Context
Jeff Bezos famously said: "Good intentions don't work. Mechanisms do." This captures a core Amazon principle: you cannot rely on people to consistently do the right thing under pressure, fatigue, or time constraints. Instead, you build systems that make the right thing automatic and the wrong thing difficult or impossible. Every recurring problem at Amazon is eventually addressed by a mechanism. Teams that rely on training, documentation, or vigilance instead of mechanisms eventually have the same incident again.
The Process
Identifying Mechanism Opportunities
Look for these signals that a mechanism is needed:
- Recurring incidents: Same root cause appears in 2+ COEs
- Human-dependent safeguards: "The engineer checks X before Y" — what happens when they forget?
- Manual checklists: Steps that must be performed in order — what happens when step 3 is skipped?
- Training-dependent processes: "New hires are trained on this" — what happens before training?
- "We'll be more careful" action items: If the solution requires sustained human attention, it will fail
- Scaling breakdowns: Process that worked with 3 people but fails with 30
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.
- 11d ago First seen · 168 lines · 16 tokens per session scan A dea96c876e31
Mechanism Creation is a skill published in the GitHub repository robisson/build-like-amazon-agent-skills (15 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 1,923 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.
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.