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 alivirgo/Major-AI-Skills --skill dependabot-configgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/dependabot-config)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/dependabot-config"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/dependabot-config/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/alivirgo/major-ai-skills/dependabot-config"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/dependabot-config.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 | $0.00022 | $0.00743 |
| Opus 5 | $0.00011 | $0.00371 |
| Sonnet 5 | $0.00004 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
dependabot-config 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependabot Configuration AI Skill Guide
Overview & Engine Architecture
Dependabot opens pull requests that bump dependency versions and alert on known vulnerabilities. Configuration lives in .github/dependabot.yml per ecosystem (npm, pip, docker, github-actions, terraform, etc.). Agents tune schedules, group related updates, ignore noisy packages deliberately, and require CI green before merge.
.github/dependabot.yml
-> GitHub Dependabot service
-> Version update PRs + security updates
-> CI checks -> human/auto merge
When to use this skill
- Enabling or retuning dependency update bots
- Reducing PR floods with groups and schedules
- Ignoring packages that must stay pinned
- Aligning security updates with SCA tools like
@snyk
Operational directives
- Commit a valid
dependabot.ymlunder.github/. - Prefer weekly schedules for apps; daily only if you can review volume.
- Group minor/patch updates where supported to cut PR noise.
- Never ignore all updates globally; ignore specific deps with reasons in comments/docs.
- Auto-merge only patch/minor with required status checks - never blind major auto-merge.
Config sketch
version: 2
updates:
- package-ecosystem: npm
directory: "/"
schedule:
interval: weekly
day: monday
open-pull-requests-limit: 10
groups:
production-patch:
dependency-type: production
update-types: ["minor", "patch"]
ignore:
- dependency-name: "legacy-sdk"
versions: [">=3.0.0"]
- package-ecosystem: github-actions
directory: "/"
schedule:
interval: weekly
- package-ecosystem: docker
directory: "/"
schedule:
interval: weekly
Tuning matrix
| Problem | Adjustment |
|---|---|
| Too many PRs | Groups + lower limit + weekly interval |
| Majors break CI constantly | Manual majors; group only minor/patch |
| Private registry fails | Configure registry credentials in Dependabot secrets |
| Lockfile conflicts | Smaller groups; rebase settings; keep CI fast |
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 Changed · -7 tokens per session 4f5fa97f189c
- 7d ago First seen · 98 lines · 29 tokens per session scan A d37c0d29f259
dependabot-config is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 743 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
android-playstore-builder
Build, sign, and publish Android apps to Google Play Store. Covers AAB builds, signing configs, Play Console, staged rollouts, and automated CI/CD.
mobile-ci-cd
Automate mobile app build, test, and deployment pipelines for iOS and Android using Fastlane, EAS Build, or GitHub Actions.
data-pipeline
Professional Data Pipeline Expert skill. Build robust, automated deployment pipelines and configure cloud infrastructure as code.
auto-scaler
Professional Auto Scaler Expert skill. Build robust, automated deployment pipelines and configure cloud infrastructure as code.
aws-architect
Professional Aws Architect skill. Build robust, automated deployment pipelines and configure cloud infrastructure as code.
azure-developer
Professional Azure Developer skill. Build robust, automated deployment pipelines and configure cloud infrastructure as code.