ai-agents-workspace-starter: Skill for Claude Code

.agents/skills/storage-patterns/SKILL.md

storage-patterns is a skill for Claude Code, Codex from systemowiec/ai-agents-workspace-starter. It costs 21 tokens per session (631 once invoked), scanned A, original, MIT.

Rules for handling uploaded files, generated documents, and temporary files. They define where files go, how names and folders are chosen, and how users or tenants are kept separate.

In plain words
What is it for?
Use it when building file uploads, PDF reports, JSON exports, temporary files, or storage that may later move to a service such as S3.
Why use it?
They prevent filename collisions, unsafe storage layouts, mixed customer data, and directories becoming difficult to manage as files accumulate.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is systemowiec/ai-agents-workspace-starter's own configuration. It tells Claude Code and Codex how to work on ai-agents-workspace-starter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-agents-workspace-starter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to systemowiec/ai-agents-workspace-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/systemowiec/ai-agents-workspace-starter/main/.agents/skills/storage-patterns/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/systemowiec/ai-agents-workspace-starter

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for storage-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/systemowiec/ai-agents-workspace-starter/storage-patterns/github.svg)](https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/storage-patterns)
Your own site
<a href="https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/storage-patterns"><img src="https://agentmods.dev/badge/skills/systemowiec/ai-agents-workspace-starter/storage-patterns/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.

agentmods 80×15 button for storage-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/systemowiec/ai-agents-workspace-starter/storage-patterns"><img src="https://agentmods.dev/badge/skills/systemowiec/ai-agents-workspace-starter/storage-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 631 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00631
Opus 5.5 $0.00008 $0.00252
Sonnet 5.5 $0.00004 $0.00126
Haiku 4.5 $0.00002 $0.00063

Measured 2mo ago against content hash d64fd01ccc74, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

storage-patterns 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 2mo 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.

.agents/skills/storage-patterns/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Storage Patterns

File management and storage patterns. Read when working with uploads, file generation, documents.


Architecture

Storage is a bind mount from host to container:

  • Host: ${STORAGE_PATH:-./storage}/ (from .env)
  • Container: /app/storage/

Directory Hierarchy

storage/
  {tenant_id}/                  # per-tenant/user isolation
    uploads/                    # files uploaded by user
      {YYYY-MM}/                # date-based partitioning
        {uuid}.{ext}            # unique name (never the original!)
    generated/                  # system-generated files
      reports/
        {uuid}.pdf
      exports/
        {uuid}.json
    temp/                       # temporary files (cleaned by cron/task)
      {uuid}.{ext}

Rules

  1. Never use the original filename as the disk name -> UUID + extension
  2. Original name stored in database (column original_filename)
  3. Date partitioning (YYYY-MM/) prevents millions of files in a single directory
  4. Isolation per tenant/user -> {tenant_id}/ at the top level
  5. Temp cleaned automatically after 24h (Huey periodic task)
  6. STORAGE_PATH configurable via .env -> easy migration to S3/GCS in the future

Database Model (StoredFile)

  • Table: stored_files
  • Columns: id (PK), uuid (unique, indexed), tenant_id (FK to users, indexed), original_filename (500), storage_path (1000, relative to STORAGE_PATH), mime_type (255), size_bytes (BigInteger), category (50: uploads/generated/temp), created_at

Port (interface)

  • ABC class FileStorage with async methods:
    • save(tenant_id, category, filename, content) -> str (returns UUID)
    • get_path(tenant_id, uuid) -> Path | None
    • delete(tenant_id, uuid) -> bool

Adapter (local implementation)

  • Class LocalFileStorage(FileStorage) with base_path: str = "/app/storage"
  • save(): generates UUID, extracts extension from original filename, creates date-partitioned path {tenant_id}/{category}/{YYYY-MM}/{uuid}.{ext}, writes bytes
  • Parent dirs created with mkdir(parents=True, exist_ok=True)

Read the full file on GitHub · 71 lines

Changes

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.

  1. 2mo ago First seen · 71 lines · 21 tokens per session scan A d64fd01ccc74

Subscribe to this mod's changes

storage-patterns is a skill published in the GitHub repository systemowiec/ai-agents-workspace-starter (2 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 631 once invoked, about $0.0001 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.

Related

storage-patterns compared with skills from other repositories

storage-patterns next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
storage-patternssystemowiec/ai-agents-workspace-starterSkill27mo agoMITA21Claude Code, Codex
orbit-notionnexu-io/open-designSkill106ktodayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35ktodayApache-2.0A123Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49kyesterdayMITA48Claude Code
legal-holdanthropics/claude-for-legalSkill9.9ktodayApache-2.0A68Claude Code
report-to-pdfasgeirtj/system_prompts_leaksSkill71kyesterdayCC0-1.0A17Claude Code, Codex
artifact-template-minimal-letterheadasgeirtj/system_prompts_leaksSkill71kyesterdayCC0-1.0A54Claude Code, Codex