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 agentmods add skills/azure/documentdb-agent-kit/storagenpx skills add Azure/documentdb-agent-kit --skill storagegit clone --depth 1 https://github.com/Azure/documentdb-agent-kitWhat 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 | $0.00109 | $0.00670 |
| Opus 5 | $0.00055 | $0.00335 |
| Sonnet 5 | $0.00022 | $0.00134 |
| Haiku 4.5 | $0.00011 | $0.00067 |
Grade A, and why
documentdb-storage 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 2d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storage — Azure DocumentDB
Azure DocumentDB clusters use remote premium SSD storage. Two disk types are offered:
| Storage type | IOPS / bandwidth scaling | Max IOPS | CMK | Use it for |
|---|---|---|---|---|
| Premium SSD (v1) | Scales with disk capacity — bigger disk → higher IOPS | 20,000 | ✔️ | Legacy clusters, scenarios that require CMK |
| Premium SSD v2 | Decoupled from disk size — IOPS/bandwidth gated by compute tier | 80,000 | ❌ | New production clusters; any I/O-intensive workload |
Premium SSD v2 is the default recommendation for new clusters. It delivers up to a 12× performance boost at no added cost by removing the disk-size lever from the IOPS equation — you size storage for capacity and size compute for throughput, independently.
How Premium SSD v2 changes sizing
On Premium SSD v1, hitting 20,000 IOPS required provisioning a 20 TB disk even when only ~1 TB of data was stored. On Premium SSD v2, the highest achievable IOPS and bandwidth for the chosen compute tier are auto-configured regardless of disk size:
- Choose storage size based on how much data the cluster will hold.
- Choose compute tier based on how much IOPS / MBps the workload needs (see storage-tier-iops-caps).
- No knobs to tune — the upper-bound IOPS/bandwidth for the tier are applied automatically at no extra cost.
Rules
- storage-choose-premium-ssdv2 — When to pick Premium SSD v2 vs Premium SSD; the CMK trade-off.
- storage-tier-iops-caps — Compute-tier → max IOPS / MBps table; size compute for throughput, not disk for IOPS.
- storage-premium-ssdv2-limitations — Known limits: no CMK, capacity-change cap, replication restrictions, no online v1→v2 migration.
- storage-disk-hydration-sequencing — Space out compute scale / storage scale / HA-enable operations while the disk is hydrating.
What ships with it
4 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.
- 2d ago First seen · 36 lines · 109 tokens per session scan A c292bc1d080e
documentdb-storage is a skill published in the GitHub repository Azure/documentdb-agent-kit (5 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 670 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…