package-updater-updating-packages

package-updater-updating-packages is a skill for Claude Code, Codex from tony/skills. It costs 38 tokens per session (2,920 once invoked), scanned A, original, MIT.

A package-maintenance workflow for finding outdated dependencies and tool versions across repositories, then updating them in separate commits.

In plain words
What is it for?
It helps update dependencies, refresh uv.lock files, change version pins, check vendor release notes, and record follow-up changes or deliberate holds.
Why use it?
It reduces the risk of mixing unrelated upgrades and warns against a memory-intensive outdated-package command that can crash a constrained machine.

Skill for Claude CodeCodex

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

Good fit It helps update dependencies, refresh uv.lock files, change version pins, check vendor release notes, and record follow-up changes or deliberate holds.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tony/skills/package-updater-updating-packages
View source ↗ tony/skills
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.

Any agent
npx skills add tony/skills --skill package-updater-updating-packages
Clone the repo
git clone --depth 1 https://github.com/tony/skills

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 package-updater-updating-packages

README.md
[![agentmods](https://agentmods.dev/badge/skills/tony/skills/package-updater-updating-packages/github.svg)](https://agentmods.dev/skills/tony/skills/package-updater-updating-packages)
Your own site
<a href="https://agentmods.dev/skills/tony/skills/package-updater-updating-packages"><img src="https://agentmods.dev/badge/skills/tony/skills/package-updater-updating-packages/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 package-updater-updating-packages

Your own site · 80×15
<a href="https://agentmods.dev/skills/tony/skills/package-updater-updating-packages"><img src="https://agentmods.dev/badge/skills/tony/skills/package-updater-updating-packages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,920 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 $0.00038 $0.02920
Opus 5 $0.00019 $0.01460
Sonnet 5 $0.00008 $0.00584
Haiku 4.5 $0.00004 $0.00292

Measured 11d ago against content hash 0b912425a293, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

package-updater-updating-packages 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 11d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/package-updater-updating-packages/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Updating packages

Find what is actually out of date, research each move against the vendor's own release notes, and land it as commits that separate the toolchain from the dependencies from their fallout.

Six references carry the parts that must not drift between this skill and the plugin's commands:

  • references/repo-scope.md — deciding which repositories are yours to commit to, and when to stop and ask.
  • references/ecosystems.md — how to detect each ecosystem, its discovery and apply commands, and the supply-chain cooldown that can hide a release from the resolver.
  • references/commit-conventions.md — the four commit tracks, subject grammar, body anatomy, and the empty-body rule.
  • references/upstream-links.md — which URLs each tool's bump cites, and how to verify them.
  • references/follow-ups.md — which bumps need a second commit, and how to declare a knowingly-red intermediate.
  • references/holds.md — deliberately staying behind on a package, and releasing the hold when its condition is met.

Never run cargo-outdated

It allocates around 18 GB resident and the OOM killer takes the whole host down with it on a memory-constrained machine. The cost is paid by starting the process, so there is no safe probe: do not run it to check whether the problem still reproduces, and do not offer it as an option.

cargo update --dry-run reports the same thing safely. This holds until someone explicitly lifts the restriction — see the Rust section of the ecosystems reference.

Core principle

A dependency commit's value is its reasoning, and reasoning does not survive bundling. Keep the toolchain, the named bumps, the bulk refresh, and the fallout in separate commits, and each one reverts on its own years later when someone needs exactly that.

Scope

Repositories you maintain. Follow references/repo-scope.md before any sweep that walks a directory: skip worktrees and duplicate clones, ask the forge for isFork and viewerPermission, and fall back to the remote owner plus trunk authorship only when it cannot answer.

Read the full file on GitHub · 302 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 302 lines · 38 tokens per session scan A 0b912425a293

Subscribe to this mod's changes

package-updater-updating-packages is a skill published in the GitHub repository tony/skills (2 stars, last pushed 6d ago), licensed MIT. It adds 38 tokens to every session and 2,920 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 2026-08-31.

Related

Other skills, from other repositories

branch-and-worktree-workflow

Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…

cbrock84/headcount · 70 tokens

commit-push-pr

Use when asked to commit, push a feature branch, and open or update a pull request with gh in one pass. Not for a push with no PR: use commit-push. Not for a PR body alone: use create-pull-request.

OutlineDriven/odin-claude-plugin · 55 tokens

commit

Use when asked to commit changes, create a typed branch, format history for a changelog, or rewrite messages of HEAD or an unpushed range. Not for pushing or a PR: use commit-push or commit-push-pr.

OutlineDriven/odin-claude-plugin · 50 tokens

git-branchless

Use when asked for multi-commit stack edits, rebases, fixups, or stacked-PR publishing with branchless git idioms. Not for plain-git workflows in repos without branchless.

OutlineDriven/odin-claude-plugin · 45 tokens

publish-branch

Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.

OutlineDriven/odin-claude-plugin · 60 tokens

commit-push

Use when asked to commit and push to a feature branch off the default branch, with no pull request. Not for a PR: use commit-push-pr. Not for the checked-out branch: use commit-push-current.

OutlineDriven/odin-claude-plugin · 49 tokens