upgrading-runtime-dependencies

upgrading-runtime-dependencies is a skill for Claude Code, Codex from dork-labs/dorkos. It costs 44 tokens per session (2,397 once invoked), scanned A, original, MIT.

A guide for evaluating upgrades to the software libraries that run an AI agent. It covers reading changelogs, finding affected code, and deciding which new features are worth adopting.

In plain words
What is it for?
Use it when upgrading an agent SDK or other runtime dependency behind an abstraction such as a shared interface.
Why use it?
Runtime library upgrades can change behavior beyond the files being updated, so a simple version bump may miss breaking changes or useful improvements.

Skill for Claude CodeCodex

Part of the flow plugin — 33 skills, 42 commands, 5 agents, 4 hooks, 5 plugins 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 skills/dork-labs/dorkos/upgrading-runtime-dependencies
Any agent
npx skills add dork-labs/dorkos --skill upgrading-runtime-dependencies
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code, Codex.

Or install flow, the plugin that ships this one along with the rest of its 33 skills, 42 commands, 5 agents, 4 hooks, 5 plugins.

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 upgrading-runtime-dependencies

README.md
[![agentmods](https://agentmods.dev/badge/skills/dork-labs/dorkos/upgrading-runtime-dependencies.svg)](https://agentmods.dev/skills/dork-labs/dorkos/upgrading-runtime-dependencies)
Your own site
<a href="https://agentmods.dev/skills/dork-labs/dorkos/upgrading-runtime-dependencies"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/upgrading-runtime-dependencies.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,397 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 $0.00044 $0.02397
Opus 5 $0.00022 $0.01198
Sonnet 5 $0.00009 $0.00479
Haiku 4.5 $0.00004 $0.00240

Measured yesterday against content hash 99a3a138d44b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

upgrading-runtime-dependencies 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 yesterday.

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/skills/upgrading-runtime-dependencies/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upgrading Runtime Dependencies

This skill teaches the judgment calls needed when upgrading dependencies that power agent runtimes. Unlike routine dependency bumps, runtime SDK upgrades require understanding what new capabilities to adopt, not just what breaks.

Core Principle

Runtime dependencies sit behind abstraction boundaries (e.g., the AgentRuntime interface). Changes to the SDK affect a confined set of files, but the implications ripple outward through the features those files enable. Your job is to trace both the direct code impact and the strategic value.

Changelog Categorization

Ambiguous Entries

Changelog entries are often vague. Use these heuristics:

Entry Pattern Likely Category Why
"refactored X internals" internal Unless X is a public API you call
"improved X performance" performance But check if our usage pattern benefits
"updated X types" Could be breaking Type changes can break compilation
"X now accepts Y" feature Additive API change
"X no longer does Y" breaking Subtractive behavior change
"deprecated X in favor of Y" deprecated Even if X still works
"fixed X when Y" fix Check if we hit condition Y

Version Significance

Not all versions deserve equal attention:

  • Major bumps (0.x → 1.0, 1.x → 2.0): Read every entry. These are intentional breaking points.
  • Minor bumps with many changes: Skim for features and deprecations. These accumulate API surface.
  • Patch bumps: Only scan for fixes that match known issues or workarounds in our code.
  • Pre-1.0 minors (0.2 → 0.3): Treat like majors. SemVer allows breaking changes before 1.0.

Read the full file on GitHub · 158 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. yesterday First seen · 158 lines · 44 tokens per session scan A 99a3a138d44b

Subscribe to this mod's changes

upgrading-runtime-dependencies is a skill published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 2,397 once invoked, about $0.0002 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 2026-09-03.