dep-sweep

dep-sweep is a skill for Claude Code from LucasSantana-Dev/sharekit. It costs 81 tokens per session (2,170 once invoked), scanned A, original, MIT.

A workflow for processing Dependabot, Renovate, and pre-commit-ci pull requests in batches. It classifies dependency updates by risk, merges updates considered safe, and leaves risky ones for human review.

In plain words
What is it for?
Use it to clean up a backlog of bot pull requests, check merge readiness, and group their changelog information.
Why use it?
It reduces the work of handling a large queue of automated dependency-update pull requests. Security advisories and major updates remain subject to review.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to clean up a backlog of bot pull requests, check merge readiness, and group their changelog information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lucassantana-dev/sharekit/dep-sweep
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 LucasSantana-Dev/sharekit --skill dep-sweep
Clone the repo
git clone --depth 1 https://github.com/LucasSantana-Dev/sharekit

Made for: Claude Code.

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 dep-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/dep-sweep/github.svg)](https://agentmods.dev/skills/lucassantana-dev/sharekit/dep-sweep)
Your own site
<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/dep-sweep"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/dep-sweep/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 dep-sweep

Your own site · 80×15
<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/dep-sweep"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/dep-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,170 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 $0.00081 $0.02170
Opus 5 $0.00041 $0.01085
Sonnet 5 $0.00016 $0.00434
Haiku 4.5 $0.00008 $0.00217

Measured 6d ago against content hash c80eedd4e8df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dep-sweep 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 6d 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.

sharekit-profile/.claude/skills/dep-sweep/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dep Sweep

Turn a wall of bot PRs into one decision pass. Auto-merges the safe class into the resolved base branch (main by default; a repo that's explicitly opted into the release-train exception uses its configured release_branch instead — see Resolve target below) and surfaces only the genuinely risky updates for human review. Reduces the daily/weekly drag of "20 dependabot PRs are open and I keep ignoring them".

Auto-invocation triggers

  • User says "deal with dependabot", "clean up renovate", "update deps", "merge the bot PRs"
  • ≥10 open PRs authored by dependabot[bot], renovate[bot], or pre-commit-ci[bot]
  • Weekly cadence if the repo has automated dep updates configured

Risk classification (always first)

For each open bot PR, classify into one of:

Evaluate HOLD conditions first, then REVIEW, then AUTO-MERGE — a patch bump with passing CI that's also a security advisory is HOLD, not AUTO-MERGE. Security advisories never qualify for AUTO-MERGE regardless of bump size or CI status; the "safe" heuristics below only apply once HOLD is ruled out.

Bucket Heuristic Default action
HOLD (risky) Security advisories, OR major bumps, OR bumps that fail CI, OR dependencies listed in always_hold in .claude/dep-sweep-config.json Comment on PR with reason; leave open
REVIEW (medium) Minor bumps of runtime deps, OR any bump that touches a known-sensitive package list (see project config) Surface to user with diff summary
AUTO-MERGE (safe) devDependencies only, OR patch bumps to any dep with passing CI, OR lockfile-only resyncs, OR pre-commit hook bumps — none of which are also a HOLD or REVIEW match Auto-merge into the resolved target

Sensitive package list defaults: react, next, vue, svelte, anything matching ^@types/node$, eslint, typescript, ORM packages (prisma, drizzle-orm, typeorm), test frameworks (vitest, jest, playwright), bundlers (vite, webpack, turbo, rollup).

Read the full file on GitHub · 204 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. 6d ago First seen · 204 lines · 81 tokens per session scan A c80eedd4e8df

Subscribe to this mod's changes

dep-sweep is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 2,170 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 2026-09-03.