mcp-server: Skill for Claude Code

.claude/skills/recreate-dependabot-pr/SKILL.md

recreate-dependabot-pr is a skill for Claude Code from keboola/mcp-server. It costs 125 tokens per session (1,658 once invoked), scanned A, original, MIT.

A workflow for recreating outdated Dependabot pull requests as one fresh branch from the main branch. Dependabot is GitHub’s automated tool for proposing dependency updates.

In plain words
What is it for?
Use it to update Python dependencies managed by uv, refresh the lock file, edit GitHub Actions workflows, and prepare a clean pull request for keboola/mcp-server.
Why use it?
It avoids conflicts between old update branches and combines dependency and security updates that would otherwise interfere with one another.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is keboola/mcp-server's own configuration. It tells Claude Code how to work on mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to keboola/mcp-server. 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/keboola/mcp-server/main/.claude/skills/recreate-dependabot-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/keboola/mcp-server

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 recreate-dependabot-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/keboola/mcp-server/recreate-dependabot-pr.svg)](https://agentmods.dev/skills/keboola/mcp-server/recreate-dependabot-pr)
Your own site
<a href="https://agentmods.dev/skills/keboola/mcp-server/recreate-dependabot-pr"><img src="https://agentmods.dev/badge/skills/keboola/mcp-server/recreate-dependabot-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,658 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00125 $0.01658
Opus 5 $0.00063 $0.00829
Sonnet 5 $0.00025 $0.00332
Haiku 4.5 $0.00013 $0.00166

Measured 8d ago against content hash 66adda773d3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

recreate-dependabot-pr 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 8d 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/recreate-dependabot-pr/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recreate Dependabot PR (keboola/mcp-server)

Recreate stale/conflicting Dependabot PRs as one clean branch from main. This is a Python/uv repo: dependencies live in pyproject.toml (dependencies / optional groups) and are locked in uv.lock; CI is GitHub Actions. There is no composer here.

Two modes:

  • Single — recreate one PR (mirrors the connection skill; re-invoke for the next).
  • Batch (preferred here) — every bump touches uv.lock and requires a pyproject.toml version bump, so N separate PRs mutually conflict. Fold all open Dependabot PRs + open security alerts into one PR.

We do NOT close the original Dependabot PRs. Once the equivalent bump is merged to main, Dependabot detects it and closes its own PRs automatically. Do not gh pr close them.

Workflow

Step 1: List the work

# Open Dependabot PRs
gh pr list --repo keboola/mcp-server --author "app/dependabot" \
  --json number,title,headRefName,url --limit 50
# Open security alerts (these may have NO corresponding PR — often transitive deps)
gh api repos/keboola/mcp-server/dependabot/alerts \
  --jq '.[] | select(.state=="open") | {number, pkg:.dependency.package.name,
        severity:.security_advisory.severity, scope:.dependency.scope,
        first_patched:.security_vulnerability.first_patched_version.identifier}'

If nothing is open, tell the user and stop.

Step 2: Classify each package

For each PR title "bump <package> from <old> to <new>" and each security alert, determine how it must be updated:

  • Direct dep pinned in pyproject.toml with == (e.g. fastmcp == 3.4.2) → the pin must be edited to the new version, then re-locked.
  • Direct dep with a compatible-release range (~= X.Y) → if <new> is already inside the range, no pyproject edit is needed — just re-lock. If <new> exceeds the range (e.g. cryptography ~= 48.049.0.0), edit the range (~= 49.0).
  • Transitive dep (appears only in uv.lock, not in pyproject.toml; typical for security alerts like urllib3, pydantic-settings) → no pyproject edit; bump via uv lock --upgrade-package <pkg>.
  • GitHub Action (ecosystem github-actions, e.g. actions/checkout 6 → 7) → edit every uses: line under .github/workflows/. No lock file involved.

Read the full file on GitHub · 146 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. 8d ago First seen · 146 lines · 125 tokens per session scan A 66adda773d3b

Subscribe to this mod's changes

recreate-dependabot-pr is a skill published in the GitHub repository keboola/mcp-server (86 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 1,658 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

polish-docs-meta

Finalize documentation and project metadata for a ship-ready release. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.

cyanheads/git-mcp-server · 53 tokens

release-and-publish

Ship a release end-to-end across every registry this project targets (npm, MCP Registry). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already complete — this skill is the post-wrapup…

cyanheads/git-mcp-server · 83 tokens

memory-commit

Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.

n24q02m/mnemo-mcp · 72 tokens

feedback-nudge

Use when the user wants to report a bug, request a feature, or send feedback to the Zooza engineering team. Also offer proactively after a successful commit operation (max once per week).

zooza-dev/zooza-mcp-server · 38 tokens

publish-release

Releases a new McpOrchestrator version end to end — version bump PR, tag, and the automated deploy to GitHub Releases, NuGet, and the MCP Registry. Use when asked to release, publish, deploy, ship, or bump the version of McpOrchestrator.

Byggarepop/dotnet-mcp-orchestrator · 63 tokens

release-notes

Writes user-facing release notes from a git commit range. Use when asked to draft release notes, a changelog entry, or "what's new" text for a release.

Byggarepop/dotnet-mcp-orchestrator · 39 tokens