Dependency Doctor logo

Dependency Doctor

Organization
Rune-kit
dependency-doctor

Dependency health management. Detects package manager, checks outdated packages and vulnerabilities, and produces a prioritized update plan.

Overview

PublisherRune-kit
Repositoryrune
Skill namedependency-doctor
Stars
88
Forks
26
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Rune-kit on GitHub. Read the source before you install it.

Installation

Install the Dependency Doctor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Rune-kit/rune/tree/master/skills/dependency-doctor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Rune-kit/rune.git /tmp/rune
mkdir -p .claude/skills
cp -r /tmp/rune/skills/dependency-doctor .claude/skills/dependency-doctor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dependency Doctor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dependency Doctor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dependency Doctor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

dependency-doctor

Purpose

Dependency health management covering outdated packages, known vulnerabilities, and update planning. Detects the package manager automatically, runs audit commands, analyzes breaking changes for major version bumps, and outputs a prioritized update plan with risk assessment.

Called By (inbound)

  • rescue (L1): Phase 0 dependency health assessment
  • audit (L2): Phase 1 vulnerability scan and outdated dependency check

Calls (outbound)

None — pure L3 utility using Bash for package manager commands.

Executable Instructions

Step 1: Detect Package Manager

Use Glob to find dependency files in the project root:

  • package.json → Node.js (npm, yarn, or pnpm)
  • requirements.txt or pyproject.toml → Python (pip or uv)
  • Cargo.toml → Rust (cargo)
  • go.mod → Go (go)
  • Gemfile → Ruby (bundler)

If multiple are found, process all of them. If none found, report NO_DEPENDENCY_FILES and stop.

For Node.js, further detect the package manager:

  • yarn.lock present → yarn
  • pnpm-lock.yaml present → pnpm
  • package-lock.json present → npm
  • None → default to npm

Step 2: List Dependencies

Use Read to parse the dependency file and extract:

  • Package name
  • Current version constraint
  • Whether it is a dev dependency or production dependency

For package.json, read both dependencies and devDependencies sections.

Step 3: Check Outdated

Run the appropriate command via Bash to find outdated packages:

npm:

bash
npm outdated --json

yarn:

bash
yarn outdated --json

pnpm:

bash
pnpm outdated

pip:

bash
pip list --outdated --format=json

cargo:

bash
cargo outdated

go:

bash
go list -u -m all

Parse the output to extract for each outdated package:

  • Current version
  • Latest version
  • Update type: patch | minor | major

Step 4: Check Vulnerabilities

Run the appropriate audit command via Bash:

npm:

bash
npm audit --json

yarn:

bash
yarn audit --json

pnpm:

bash
pnpm audit --json

pip:

bash
pip-audit --format json

cargo:

bash
cargo audit --json

If the audit tool is not installed, note it as TOOL_MISSING and skip this step (do not fail).

Parse the output to extract:

  • Package name + vulnerable version
  • CVE ID (if available)
  • Severity: critical | high | moderate | low
  • Fixed version (if available)

Step 5: Analyze Breaking Changes

For each package with a major version bump (e.g. v2 → v3):

Use rune:docs-seeker to look up migration guides if available, or note:

  • "Breaking change analysis required before updating [package] from v[X] to v[Y]"

Do not blindly recommend major updates without flagging migration risk.

Step 6: Generate Update Plan

Create a prioritized update plan:

Priority order:

  1. CRITICAL — packages with critical/high CVEs → update immediately
  2. SECURITY — packages with moderate/low CVEs → update in current sprint
  3. PATCH — patch version bumps, no breaking changes → safe to batch update
  4. MINOR — minor version bumps, new features added → update with testing
  5. MAJOR — major version bumps, breaking changes → plan migration separately

For each item in the plan, include:

  • Package name + current → target version
  • Update type and risk level
  • Migration notes (for major updates)
  • Suggested command to run the update

Step 7: Report

Output the following structure:

## Dependency Report: [project name]

- **Package Manager**: [npm|yarn|pnpm|pip|cargo|go]
- **Total Dependencies**: [count]
- **Outdated**: [count]
- **Vulnerable**: [count] ([critical] critical, [high] high, [moderate] moderate)

### Critical — CVEs (Fix Immediately)
- [package]@[current] — [CVE-ID] ([severity]): [description]
  Fix: npm update [package]@[fixed_version]

### Security — CVEs (Fix This Sprint)
- [package]@[current] — [CVE-ID] ([severity]): [description]

### Outdated — Patch (Safe to Update)
- [package]@[current] → [latest] (patch)

### Outdated — Minor (Update with Testing)
- [package]@[current] → [latest] (minor)

### Outdated — Major (Plan Migration)
- [package]@[current] → [latest] (major) — migration guide required

### Unused Dependencies
- [package] — no imports found in src/

### Update Plan (Ordered by Risk)
1. [command] — fixes [CVE-ID]
2. [command] — patch updates (safe batch)
3. [command] — requires migration: [notes]

### Dependency Health Score
- Score: [0-100]
- Grade: A (80-100) | B (60-79) | C (40-59) | D (<40)
- Score basis: -10 per critical CVE, -5 per high CVE, -2 per outdated major, -1 per outdated minor

Upgrade Campaign Mode

When health score < 60 OR CRITICAL/SECURITY items exist, dependency-doctor can orchestrate a full upgrade campaign — not just report, but execute. Triggered by: user says "upgrade all", "fix deps", "run the update plan", or health score triggers.

Campaign Chain

1. TRIAGE     → Run Steps 1-7 (standard report). Identify upgrade order.
2. CHECKPOINT → Save current lock file state: `cp package-lock.json .rune/dep-backup/`
3. PER-PACKAGE LOOP (CRITICAL → SECURITY → PATCH → MINOR, skip MAJOR):
   a. Upgrade one package at a time: `npm install pkg@latest`
   b. Call `rune:verification` — run tests + build
   c. If PASS → commit: `feat(deps): upgrade {pkg} {old} → {new}`
   d. If FAIL → rollback package: `npm install pkg@{old}`, log as BLOCKED
4. MAJOR BUMPS → present to user: breaking change notes + migration guide link. Never auto-upgrade.
5. REPORT     → final health score delta, packages upgraded/skipped/blocked

One package at a time — bulk upgrades make it impossible to identify which package broke the build.

MAJOR upgrades require:

  • User confirmation
  • Breaking change summary (from npm docs or package CHANGELOG)
  • Migration checklist before upgrading

Calls (outbound — Campaign Mode only)

  • verification (L3): test + build after each package upgrade
  • fix (L2): when a minor/patch upgrade breaks tests and fix is straightforward

Output Format

Dependency Report with package manager, counts, CVE findings by severity, outdated packages by risk level, unused dependencies, ordered update plan, and health score (0-100). See Step 7 Report above for full template.

Constraints

  1. MUST check for known vulnerabilities — not just version freshness
  2. MUST NOT auto-upgrade major versions without user confirmation — breaking changes
  3. MUST verify project still builds after any dependency change
  4. MUST show what changed (added, removed, upgraded) in a clear diff format

Sharp Edges

Known failure modes for this skill. Check these before declaring done.

Failure ModeSeverityMitigation
Recommending major version update without flagging migration riskCRITICALConstraint 2: breaking changes need explicit migration notes and user confirmation
Silently skipping vulnerability check when tool not installedHIGHReport TOOL_MISSING explicitly — never skip without logging it
Missing dependency health score (0-100)MEDIUMScore is mandatory in every report — it gives callers a quick health signal
Reporting unused dependencies without verifying (false positive)MEDIUMCheck actual import patterns in src/ before flagging as unused

Done When

  • Package manager detected (npm/yarn/pnpm/pip/cargo/go)
  • Outdated packages listed with current → latest versions and update type
  • Vulnerability audit run (or TOOL_MISSING noted explicitly)
  • Breaking changes flagged for all major version bumps
  • Prioritized update plan generated (CRITICAL → SECURITY → PATCH → MINOR → MAJOR order)
  • Dependency health score (0-100) calculated
  • Dependency Report emitted in output format

Cost Profile

~300-600 tokens input, ~200-500 tokens output. Haiku. Most time spent in package manager commands.

Frequently asked questions

What does the Dependency Doctor AI skill do?

Dependency health management. Detects package manager, checks outdated packages and vulnerabilities, and produces a prioritized update plan.

Why use Dependency Doctor on TypingMind?

Because you install it once and use it with any model. Dependency Doctor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dependency Doctor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Rune-kit/rune/tree/master/skills/dependency-doctor. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dependency Doctor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dependency Doctor?

As many as you like. As long as a model supports skills, you can use Dependency Doctor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dependency Doctor AI skill free?

Yes. It is published on GitHub by Rune-kit under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇