agent-kernel: Skill for Claude Code

.agents/skills/ak-dev-new-multimodal-storage/SKILL.md

ak-dev-new-multimodal-storage is a skill for Claude Code, Codex from yaalalabs/agent-kernel. It costs 73 tokens per session (3,812 once invoked), scanned A, original, Apache-2.0.

A development guide for adding a service that stores images and file attachments used by agents. It describes the existing in-memory, Redis, and DynamoDB storage options as references.

In plain words
What is it for?
Use it to implement a new attachment store, register it with the storage factory, and add its configuration and package dependencies.
Why use it?
It provides the structure needed to make attachment storage persistent or shared across processes while keeping it compatible with Agent Kernel.

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 yaalalabs/agent-kernel's own configuration. It tells Claude Code and Codex how to work on agent-kernel 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 agent-kernel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yaalalabs/agent-kernel. 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/yaalalabs/agent-kernel/develop/.agents/skills/ak-dev-new-multimodal-storage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yaalalabs/agent-kernel

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 ak-dev-new-multimodal-storage

README.md
[![agentmods](https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-new-multimodal-storage.svg)](https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-new-multimodal-storage)
Your own site
<a href="https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-new-multimodal-storage"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-new-multimodal-storage.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,812 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00073 $0.03812
Opus 5 $0.00036 $0.01906
Sonnet 5 $0.00015 $0.00762
Haiku 4.5 $0.00007 $0.00381

Measured 4d ago against content hash 71c3417342b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ak-dev-new-multimodal-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 4d 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/ak-dev-new-multimodal-storage/SKILL.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding a New Multimodal Storage Backend

This guide walks through adding a new attachment storage backend to Agent Kernel's multimodal subsystem. Use the existing Redis (ak-py/src/agentkernel/core/multimodal/storage/redis.py) and DynamoDB (ak-py/src/agentkernel/core/multimodal/storage/dynamodb.py) implementations as reference.

Existing Backends

Backend Config value Features Extras
In-memory in_memory Ephemeral ClassVar dict, zero setup, single-process only None
Redis redis Persistent, TTL, shared RedisDriver (lazy connect, retry, ping/reconnect), distributed agentkernel[multimodal,redis]
DynamoDB dynamodb Serverless/AWS, TTL via expiry_time, fully managed agentkernel[multimodal,aws]
Session cache session_cache Legacy — stores in session nv_cache (causes bloat, not recommended) None

To run multimodal end-to-end (hooks/tools), you typically need agentkernel[multimodal] plus the backend-specific extra shown above (for example: agentkernel[multimodal,redis] or agentkernel[multimodal,aws]).

Architecture Overview

The multimodal storage system uses a simple pluggable pattern:

  1. AttachmentStore (storage/base.py) — abstract base class with save(), get(), delete()
  2. AttachmentData (storage/base.py) — dataclass representing a stored attachment (id, type, data, name, mime_type, description, timestamp, url)
  3. AttachmentStorageManager (storage/storage_manager.py) — high-level API that reads configuration, instantiates the correct AttachmentStore via _build_driver(), and provides save_attachment() / get_attachment_data() methods
  4. Callers: MultimodalPreHook saves attachments; AnalyzeAttachmentsTool retrieves them
MultimodalPreHook / AnalyzeAttachmentsTool
    → AttachmentStorageManager(session_id)
        → _build_driver(session_id)          # reads config.multimodal.storage_type
            → InMemoryAttachmentStore        # or Redis, DynamoDB, etc.
        → save_attachment() / get_attachment_data()
            → AttachmentStore.save() / .get()

Read the full file on GitHub · 380 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. 4d ago Changed · +5 lines 71c3417342b7
  2. 8d ago First seen · 375 lines · 73 tokens per session scan A b1ec87654a77

Subscribe to this mod's changes

ak-dev-new-multimodal-storage is a skill published in the GitHub repository yaalalabs/agent-kernel (166 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 3,812 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

google-firebase-ninja

Master orchestrator for 18+ Firebase agent skills from official Google repositories. Use when working with Firebase, Firestore, Firebase Auth, Firebase Hosting, Cloud Functions, Firebase Extensions, or any Firebase backend task. Routes to the optimal specialized skill based on context. Triggers: Firebase, Firestore…

fabricioctelles/jump-skills · 98 tokens

b00t

Identify integration points, data flow via redis, suggest how to bridge VSCode plugin to b00t jobs, and outline k0s/podman/docker-agnostic redis interface. Include how ralph should be wrapped as b00t job with redis exchange + Azure access, and call out where integration tests are required. ONLY do this analysis. Reply…

elasticdotventures/_b00t_ · 0 tokens

django-migration-psql

Reviews Django migration files for PostgreSQL best practices specific to Prowler. Trigger: When creating migrations, running makemigrations/pgmakemigrations, reviewing migration PRs, adding indexes or constraints to database tables, modifying existing migration files, or writing data backfill migrations. Always use…

prowler-cloud/prowler · 96 tokens

azure-postgres-ts

Connect to Azure Database for PostgreSQL Flexible Server from Node.js/TypeScript using the pg (node-postgres) package. Use for PostgreSQL queries, connection pooling, transactions, and Microsoft Entra ID (passwordless) authentication. Triggers: "PostgreSQL", "postgres", "pg client", "node-postgres", "Azure PostgreSQL…

microsoft/skills · 94 tokens

notion

Notion workspace integration for searching pages, managing databases, creating postmortems, and exporting RCA findings.

Arvo-AI/aurora · 23 tokens

datadog

Datadog monitoring integration for querying logs, metrics, monitors, events, traces, hosts, and incidents during RCA investigations.

Arvo-AI/aurora · 28 tokens