An audit workflow for open Dependabot pull requests. Dependabot is a service that proposes dependency updates, and a pull request is a proposed code change for review.

Use it to inspect open Dependabot requests, assess each one's risk, recommend whether to merge it, and order the merges.

It helps compare update risks and decide a merge order that reduces conflicts between changes. It stops at recommendations and does not merge or publish anything.

How garfiec/Librechat-Mobile configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to garfiec/Librechat-Mobile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/garfiec/Librechat-Mobile/develop/.claude/skills/audit-deps/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/garfiec/Librechat-Mobile

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/garfiec/librechat-mobile/audit-deps/github.svg)](https://agentmods.dev/skills/garfiec/librechat-mobile/audit-deps)

Your own site

<a href="https://agentmods.dev/skills/garfiec/librechat-mobile/audit-deps"><img src="https://agentmods.dev/badge/skills/garfiec/librechat-mobile/audit-deps/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/skills/garfiec/librechat-mobile/audit-deps"><img src="https://agentmods.dev/badge/skills/garfiec/librechat-mobile/audit-deps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,418 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00086	$0.02418
Opus 5	$0.00043	$0.01209
Sonnet 5	$0.00017	$0.00484
Haiku 4.5	$0.00009	$0.00242

Measured 10d ago against content hash a7790a0d7274, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

audit-deps 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 10d 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/skills/audit-deps/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Dependabot PRs

Audit open dependabot PRs and propose a safe merge order.

You are the team lead. You orchestrate. You do NOT read source code or run grep yourself during investigation — every codebase walk goes through a sub-agent inside a per-PR investigator. You handle GitHub queries, worktree setup, synthesis, and the merge-order proposal.

The skill is audit-only. It never merges, pushes, comments on PRs, or removes worktrees. It ends by presenting findings + a proposed sequence and asking the user what to do next.

Phase 0 — Discovery

Args: an optional list of PR numbers (/audit-deps 77 78 79). If omitted, audit every open dependabot PR.

Run once:

gh pr list --state open --json number,title,headRefName,author,createdAt,mergeable,statusCheckRollup \
  --jq '.[] | select(.author.login=="app/dependabot" or (.headRefName | startswith("dependabot/")))'

If args were passed, narrow to those PR numbers. From each PR object extract:

PR number, title, head ref
mergeable state (MERGEABLE / CONFLICTING / UNKNOWN)
statusCheckRollup — count and roll up to "all green" / "N failing"
Age in days (today − createdAt)

If the result is empty, exit early with a one-line message — no work to do.

If any PR has CONFLICTING AND age > 7 days, note it as "stale-conflict — rebase candidate" but do NOT trigger a rebase. Rebase decisions belong to Phase 4 (user authorization).

State briefly to the user what you found before moving on:

Found N open dependabot PRs: #77 paging, #78 AGP 9.2.1, #79 kotlinx-datetime. Setting up worktrees.

Phase 1 — Worktree setup

Project worktree convention: .claude/worktrees/deps/pr-<N> on a local branch named pr-<N>.

For each PR:

# fetch dependabot branch as local pr-<N>
git fetch origin <head-ref>:pr-<N>

# create worktree (or refresh if it exists from a prior audit run)
if [ -d ".claude/worktrees/deps/pr-<N>" ]; then
  git -C .claude/worktrees/deps/pr-<N> fetch origin
  git -C .claude/worktrees/deps/pr-<N> reset --hard pr-<N>
else
  git worktree add .claude/worktrees/deps/pr-<N> pr-<N>
fi

Read the full file on GitHub · 201 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.

10d ago First seen · 201 lines · 86 tokens per session scan A a7790a0d7274

Subscribe to this mod's changes

audit-deps is a skill published in the GitHub repository garfiec/Librechat-Mobile (89 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 2,418 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 2026-08-30.

Code review ai-assistant ai-chat android anthropic chat-bot chatgpt

human-review

Produce a plain-English review of the files you just edited and gate the changes behind an explicit Approve/Undo choice. Use when the Stop hook from the human-review-skill plugin asks for a review (you'll see a prompt referencing an edit log), OR when the developer's most recent message is "1", "2", "approve", or…

IrtezaAsadRizvi/claude-human-review · 83 tokens

simplify-code

Parallel 4-agent cleanup of recent code changes.

NousResearch/hermes-agent · 14 tokens

requesting-code-review

Pre-commit review: security scan, quality gates, auto-fix.

NousResearch/hermes-agent · 20 tokens

opencode

Delegate coding to OpenCode CLI (features, PR review).

NousResearch/hermes-agent · 15 tokens

security-review

Complete a security review of the pending changes on the current branch.

asgeirtj/system_prompts_leaks · 15 tokens

code-review

Review the current diff, or a PR number/branch/path target, for correctness bugs and reuse/simplification/efficiency cleanups at the given effort level (low/medium: fewer, high-confidence findings; high→max: broader coverage, may include uncertain findings; ultra: deep multi-agent review in the cloud); with no level…

asgeirtj/system_prompts_leaks · 0 tokens

Librechat-Mobile: Skill for Claude Code