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.
git 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/commands/robisson/build-like-amazon-agent-skills/learn)<a href="https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/learn"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/learn/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/commands/robisson/build-like-amazon-agent-skills/learn"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/learn.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 | $0.00000 | $0.00951 |
| Opus 5.5 | $0.00000 | $0.00380 |
| Sonnet 5.5 | $0.00000 | $0.00190 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
learn 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 20d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn — Correction of Errors and Mechanisms
Path resolution: All
skills/,agents/, andpatterns/paths in this command are relative to the plugin root directory. Installed as a Claude Code plugin, that root is theBLA plugin root:line the plugin printed at session start; in a local install it is the working directory.
You are activating the learn skill chain: correction-of-errors → mechanism-creation.
What to do
- Read skills at
skills/correction-of-errors/andskills/mechanism-creation/. - Help the user learn from failures and build systems that prevent recurrence.
Step 1: Correction of Errors (COE)
Guide the user through writing a COE:
- Incident summary: What happened, when, impact (duration, customers affected).
- Timeline: Minute-by-minute from detection to resolution.
- Root cause analysis: Use 5 Whys — dig past symptoms to systemic causes.
- Contributing factors: What conditions allowed this to happen?
- What went well: Acknowledge what worked (detection, response, tooling).
- Action items: Each with owner, due date, and completion criteria.
- Categorize: immediate fix, short-term mitigation, long-term prevention.
Key COE principles:
- Blameless — focus on systems, not individuals.
- Be brutally honest — the goal is learning, not looking good.
- Action items must be mechanisms, not heroics.
Once the COE is drafted, load agents/coe-reviewer.md and review it through the COE reviewer lens.
Step 2: Mechanism Creation
Convert learnings into durable mechanisms:
- Automation: Replace manual steps with automated checks.
- Guardrails: Pipeline gates, config validation, pre-deploy checks.
- Process changes: Updated runbooks, new review steps, training.
- Architectural improvements: Eliminate the class of failure entirely.
- Metrics and alarms: Detect the preconditions before they become incidents.
A mechanism is complete when:
- It works without human willpower or memory.
- It prevents the entire CLASS of problem, not just this instance.
- It's verified through testing or simulation.
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.
- 20d ago Changed 605725e5183f
- 1mo ago Changed · +13 lines 456f1b774225
- 1mo ago First seen · 57 lines · 0 tokens per session scan A 7d4562d970fb
learn is a command published in the GitHub repository robisson/build-like-amazon-agent-skills (16 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 951 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 2026-08-30.
Other commands, from other repositories
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
debug-pod
Debug a failing or unhealthy Kubernetes pod by analyzing events, logs, and configuration.
map
Generate a dependency map showing how modules and files relate to each other in the codebase.
unstick
Bir problemde takıldığında - hızlıca çözüm bul.
triage
Triage a bug report (PDF / markdown / text) — extract the issues, prioritize, then run the fix pipeline per issue.
fix
⚡⚡ Analyze and fix small issues [AUTO DETECT COMPLEXITY].