runtime-upgrade

A command for studying changes in a runtime software package and assessing how a new version could affect the codebase. A runtime SDK is a package used to run or control an application at runtime.

In plain words
What is it for?
Use it for major runtime SDK upgrades, especially when you want upgrade notes, compatibility analysis, or ideas for using new capabilities.
Why use it?
It adds impact analysis and feature discovery to a dependency upgrade, helping decide what new version features are worth adopting.

Command for Claude Code

Part of the flow plugin — 17 skills, 37 commands, 5 agents shipped together

Install

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.

agentmods
npx agentmods add commands/dork-labs/dorkos/runtime-upgrade
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 17 skills, 37 commands, 5 agents.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.05187
Opus 5 $0.00010 $0.02593
Sonnet 5 $0.00004 $0.01037
Haiku 4.5 $0.00002 $0.00519

Measured 3d ago against content hash 7c0dbdc5d79c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runtime-upgrade 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 3d 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.

.claude/commands/app/runtime-upgrade.md · 639 lines

How it starts

The opening of the file, as written. The whole thing — 639 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runtime Dependency Upgrade

Strategic upgrade workflow for agent runtime dependencies. Unlike /app:upgrade (which treats all deps uniformly — "can we safely bump?"), this command performs deep changelog analysis, impact assessment, and feature discovery — "what should we build on top of the new version?"

When to Use This vs /app:upgrade

Scenario Use
Routine patch/minor bumps across all deps /app:upgrade
Security-driven update to a runtime SDK /app:upgrade
New major version of a runtime SDK with new features /app:runtime-upgrade
Want to discover what new SDK capabilities to adopt /app:runtime-upgrade
Upgrading a dep that wraps our AgentRuntime interface /app:runtime-upgrade

Arguments

Parse $ARGUMENTS for:

Required

  • <package-name> — The npm package to analyze. The three production runtime SDKs (all pre-configured in .claude/config/runtime-deps.json): @anthropic-ai/claude-agent-sdk, @openai/codex-sdk, @opencode-ai/sdk

Options

Flag Effect
--to=<version> Target version (default: latest)
--from=<version> Override current version detection

Modes (mutually exclusive, default: interactive)

Mode Description
analyze Fetch changelogs + produce impact assessment only (no specs)
plan Analyze + generate specs for upgrade and feature adoption
interactive Full guided workflow with decisions at each phase (default)

Examples

/app:runtime-upgrade @anthropic-ai/claude-agent-sdk
/app:runtime-upgrade @anthropic-ai/claude-agent-sdk --to=0.3.0
/app:runtime-upgrade @openai/codex-sdk analyze
/app:runtime-upgrade @openai/codex-sdk plan --to=0.143.0
/app:runtime-upgrade @opencode-ai/sdk

Read the full file on GitHub · 639 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. 3d ago First seen · 639 lines · 19 tokens per session scan A 7c0dbdc5d79c

Subscribe to this mod's changes

runtime-upgrade is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 5,187 once invoked, about $0.0001 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.