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.
npx skills add joaquimscosta/arkhe-claude-plugins --skill dependabot-reviewgit clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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.
[](https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/dependabot-review)<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/dependabot-review"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/dependabot-review/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.
<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/dependabot-review"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/dependabot-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00090 | $0.02277 |
| Opus 5.5 | $0.00036 | $0.00911 |
| Sonnet 5.5 | $0.00018 | $0.00455 |
| Haiku 4.5 | $0.00009 | $0.00228 |
Grade A, and why
dependabot-review 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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependabot PR Review
Triage, classify, and merge open Dependabot PRs with risk-based assessment.
Auto-Invoke Triggers
This skill activates when:
- Keywords: "dependabot", "dependabot PRs", "dependency updates", "merge dependabot", "review dependabot", "dependency PRs", "bump PRs", "update dependencies"
- Command:
/dependabot-review
Arguments
- (no args) — Triage mode: list all open Dependabot PRs with risk classification
--merge-safe— Merge all PRs classified as SAFE TO MERGE (asks for target branch first)--pr <number>— Deep-dive analysis of a single Dependabot PR--base <branch>— Target branch for retargeting PRs before merge (skips the prompt)
Prerequisites
- GitHub CLI (
gh) authenticated with repo access - Repository must have open Dependabot PRs
Verify:
gh auth status
Workflow
Step 1: Fetch Open Dependabot PRs
gh pr list \
--author "app/dependabot" \
--state open \
--json number,title,labels,headRefName,baseRefName,mergeable,isDraft,createdAt,statusCheckRollup \
--limit 50
If --pr <number> was provided, fetch that single PR instead:
gh pr view <number> \
--json number,title,body,labels,headRefName,baseRefName,mergeable,isDraft,createdAt,statusCheckRollup,additions,deletions
If no Dependabot PRs are found, report "No open Dependabot PRs found" and stop.
Step 2: Enrich Each PR
For each PR, gather additional data:
Files changed (for lockfile-only detection):
gh pr diff <number> --name-only
CI status: Extract from statusCheckRollup in the JSON. Classify as:
pass— all checks SUCCESS or SKIPPEDfail— any check FAILUREpending— any check IN_PROGRESS or QUEUEDnone— no checks ran
Step 3: Classify Each PR
Apply the risk matrix to each PR:
Parse version info from PR title:
Dependabot titles follow: build(deps): bump <package> from <old> to <new> in <path>
For grouped updates: build(deps): bump the <group> group across N directory with M updates
What ships with it
3 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.
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.
- yesterday First seen · 256 lines · 90 tokens per session scan A 4ec310c101de
dependabot-review is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 2,277 once invoked, about $0.0004 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 2026-10-16.
Other skills, from other repositories
git-workflow
Git branching, commits, and PR workflow following GitFlow conventions.
pr-creator
Create well-structured pull requests with proper descriptions and labels.
diff-project
Shows what changed in dotforge since the project's last sync, to decide whether running /forge sync is worthwhile.
finish
Ship phase — merge, PR, keep, or discard with pre-merge verification.
dev-finish
Close out a session — summarise what changed, capture what was learned, and prepare the commit.
dev-rc
The last gate before merge — QA, security audit, review and changelog, with objective pass conditions.