A guided command for updating an application's software packages and checking them for security problems. It can inspect outdated packages, create an upgrade plan, or carry out upgrades by version range.

Use it to check, audit, plan, or interactively perform patch, minor, major, or security-only dependency upgrades.

It brings package checks, security review, prioritization, and validation into one workflow. This reduces the chance of missing an outdated or risky dependency.

upgrade — Command for Claude Code by dork-labs/dorkos

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/dork-labs/dorkos

agentmods

npx agentmods add commands/dork-labs/dorkos/upgrade

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 43 skills, 45 commands, 5 agents, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/dork-labs/dorkos/upgrade/github.svg)](https://agentmods.dev/commands/dork-labs/dorkos/upgrade)

Your own site

<a href="https://agentmods.dev/commands/dork-labs/dorkos/upgrade"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/upgrade/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/dork-labs/dorkos/upgrade"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 9,087 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.09087
Opus 5.5	$0.00020	$0.03635
Sonnet 5.5	$0.00010	$0.01817
Haiku 4.5	$0.00005	$0.00909

Measured 1mo ago against content hash 1370eb58346f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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/upgrade.md · 744 lines

How it starts

The opening of the file, as written. The whole thing — 744 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Application Upgrade

Dependency maintenance for the whole workspace, built to run unattended on a schedule. A plain /app:upgrade reads the GitHub security tab and the local tree, fixes what a machine can safely fix, opens one small PR per kind of change, files a ticket for what needs a person, and reports. It asks nothing.

Load the maintaining-dependencies skill before Phase 1 — it holds the judgment this command's steps depend on (direct vs. transitive fixes, override scoping, cooldown policy, how to read a red Dependabot PR, when a CodeQL alert may be dismissed). This file is the procedure; the skill is the reasoning.

Arguments

Parse $ARGUMENTS.

Modes (mutually exclusive)

Mode	Effect
(none)	`auto` — run every lane, open PRs, file tickets, dismiss what the rules allow, report. Never asks.
`check`	Outdated packages and open alerts, counted by lane. Changes nothing.
`audit`	Security only: Dependabot alerts ∪ `pnpm audit`, code/secret scanning, Dependabot pipeline health. Changes nothing.
`plan`	Everything `auto` would do, printed instead of done. Same as `--dry-run`.
`interactive`	The lanes of `auto`, with a question at every decision that changes a PR, a ticket, or an alert. The old default.

Flags

Flag	Effect
`--lanes=a,b`	Run only these lanes: `security`, `dependabot`, `routine`, `majors`, `scanning`, `pipeline`. Default: all.
`--security`	Shorthand for `--lanes=security,scanning,pipeline`.
`--patch`	Routine lane takes patch bumps only.
`--minor`	Routine lane takes patch + minor (the default).
`--major`	Routine lane may also take majors — `interactive` only; ignored under `auto` with a line in the report saying so.
`--no-cooldown`	Skip the 21-day cooldown in the routine lane. Security fixes never wait for cooldown, so this flag is not needed there.
`--dry-run`	Do the reads and the local work, but no push, no PR, no ticket, no dismissal, no comment. Print what would have happened.
`[package...]`	Restrict the security and routine lanes to these packages.

Read the full file on GitHub · 744 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.

1mo ago Changed 1370eb58346f
1mo ago Changed · +1 lines 622462cc405a
1mo ago Changed · +143 lines · +36 tokens per session fc2c5f5fc2df
1mo ago Changed · +1 lines 628625cae5fe
1mo ago Changed 66def9cf9d9f
1mo ago First seen · 599 lines · 13 tokens per session scan A b1635653f77a

Subscribe to this mod's changes

upgrade is a command published in the GitHub repository dork-labs/dorkos (12 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 9,087 once invoked, about $0.0002 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.

Autonomous Agents Claude Code Security agent-sdk ai-agents anthropic application claude

scout-meta-review

Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.

Raven-Scout/Scout · 61 tokens

upgrade

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Application Upgrade

Arguments

Modes (mutually exclusive)

Flags

What this file has done since we first saw it

Other commands, from other repositories

scout-meta-review

check

test-feature

ir

revise-claude-md

review-issue