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 alexpizarro/azure-lean-stack-skills --skill curating-azure-deployment-learningsgit clone --depth 1 https://github.com/alexpizarro/azure-lean-stack-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/alexpizarro/azure-lean-stack-skills/curating-azure-deployment-learnings)<a href="https://agentmods.dev/skills/alexpizarro/azure-lean-stack-skills/curating-azure-deployment-learnings"><img src="https://agentmods.dev/badge/skills/alexpizarro/azure-lean-stack-skills/curating-azure-deployment-learnings/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/alexpizarro/azure-lean-stack-skills/curating-azure-deployment-learnings"><img src="https://agentmods.dev/badge/skills/alexpizarro/azure-lean-stack-skills/curating-azure-deployment-learnings.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 | $0.00104 | $0.01632 |
| Opus 5.5 | $0.00042 | $0.00653 |
| Sonnet 5.5 | $0.00021 | $0.00326 |
| Haiku 4.5 | $0.00010 | $0.00163 |
Grade A, and why
curating-azure-deployment-learnings 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 1mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curating Azure Deployment Learnings
The feedback loop that keeps the diagnosing-azure-deployment-failures gotcha catalogue current. Capture lessons from real projects in learnings/, then promote recurring ones into the catalogue.
learnings/is gitignored in the plugin repo — learnings are private field notes (they name customers, subscriptions and costs). Only the promoted gotcha row is shared. The commit SHA recorded in a learning's Status line therefore points at the gotcha commit, and is for the author's own audit trail. Keep learnings in whichever private location suits you (LEARNINGS_DIRoverrides the default for every script).
When to invoke
- A deployment problem was solved — capture it before it's forgotten
- Reviewing accumulated
learnings/*.mdfor promotion candidates - Triaging which learnings are project-specific vs broadly reusable
The pipeline
Project hits a problem in the field
↓
Solve it — file a learning in learnings/{date}_{project}.md
↓
Periodically review learnings/ — what shows up across multiple projects?
↓
Promote recurring ones to skills/diagnosing-azure-deployment-failures/references/gotchas.md
↓
Mark the learning entry "✅ Promoted in commit {sha}"
Learning file format
---
project: trg-directory-content-crawl
date: 2026-05-20
issues:
- docker-hub-rate-limit
- crawl4ai-pinning
severity: medium
promoted: false
---
# Session Learnings — TRG Directory Content Crawl
## Issue 1 — Docker Hub anonymous pulls hit rate limit in CI
### What happened
After 20+ successful deploys, the GitHub Actions runner started getting `toomanyrequests`
errors when pulling `unclecode/crawl4ai:latest`.
### Root cause
Docker Hub limits anonymous pulls to 100/6h per IP. GitHub-hosted runners share IPs,
so the project's pulls were rate-limited from other workflows on the same NAT IP.
### Fix applied
Pinned the image to `crawl4ai:0.8.6` and mirrored it into our ACR. Updated deploy.sh
and the Bicep template.
Files changed: `azure/deploy.sh:83`, `infra/modules/crawler.bicep:42`.
Status: ✅ Promoted — docker-hub-rate-limit → gotcha #31, crawl4ai-pinning → gotcha #38 (commit abc1234).
What ships with it
3 files 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.
- 1mo ago Changed · +12 lines e70a9ae178b5
- 1mo ago First seen · 141 lines · 104 tokens per session scan A 69a8bfec3440
curating-azure-deployment-learnings is a skill published in the GitHub repository alexpizarro/azure-lean-stack-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,632 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
azure-kubernetes-automatic-readiness
Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic…
azure-diagnostics
Debug Azure production issues using AppLens, Azure Monitor, resource health, and safe triage, including evidence-only diagnosis without live access. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, container app 503 or target…
azure-diagnostics
Investigate AKS, VM, App Service, Functions and messaging incidents using scoped evidence.
azure-expert
Expert-level Microsoft Azure cloud platform, services, and architecture. Use when the user mentions cloud, Microsoft platforms, Azure Functions, or Cosmos DB.
datadog-ninja
Master orchestrator for 57 official Datadog agent skills from DataDog/pup and datadog-labs/agent-skills. Use when working with ANY Datadog observability task: APM and distributed tracing, log search and pipelines, monitors and alerting, live production debugging, audit trail investigations, browser SDK…
cloud-native-azure-functions
Use this skill when the user says 'azure functions', 'durable functions', 'orchestrator function', 'activity function', 'durable entities', 'event grid trigger', 'flex consumption', 'azure functions hosting plan', 'fan-out fan-in azure'. Designs Azure Functions apps and Durable Functions workflows with correct…