Dep Radar logo

Dep Radar

Organization
vanillagreencom
dep-radar

Load to run or tune a dependency sweep.

Overview

Publishervanillagreencom
Repositorykendex
Skill namedep-radar
Stars
80
Forks
31
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 vanillagreencom on GitHub. Read the source before you install it.

Installation

Install the Dep Radar 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.
  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/vanillagreencom/kendex.git /tmp/kendex
mkdir -p .claude/skills
cp -r /tmp/kendex/skills/dep-radar .claude/skills/dep-radar
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dep Radar 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 Dep Radar 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 Dep Radar 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.

dep-radar

inventory → detect → research → classify → upgrade-with-fixes → report the owner tier.

Generic engine only: concrete package names, pinned binaries, and fork lists live in the per-repo inventory, never here.

Load github before Phase 4 (PR creation, CI status, merges). Load worktree when a run applies more than one surface, one working copy per surface branch.

Operating policy (the contract with the product owner)

Rule keys are the contract; an inventory owner-rule cites them. Dropping or renaming a key changes the contract.

RuleContract
auto-with-fixesThe default. Security fixes; patch/minor bumps; pinned-binary version+SHA refreshes from OFFICIAL manifests only; SDK, agent-tooling, and runtime-binary bumps and npm/cargo majors, doing the bump AND fixing its fallout (API migrations, re-vendored bundled-extension bridges, tests, CI) in the SAME per-surface workstream; bundled-extension fork updates and local patch rebases when the consuming repo's full test suite gates the sync.
report-never-autoModel-weight swaps; changes to durable/recorded data scope; anything an inventory owner-rule explicitly demotes. Nothing else is report-by-default.
uncertainAttempt the upgrade; report only what actually failed, with error output.
deferOnly on a strong concrete blocker you actually hit, such as a dropped capability with no migration path or a transitive that does not support the new version. Never a generic "it's a major" risk or any other anticipated one.
one-pr-per-surfaceOne PR per surface; never batch surfaces. A surface's fallout fixes go in THAT surface's PR.
upstream-check-requiredEvery pinned surface must have a wired upstream check command; a surface lacking one is an inventory defect the run must fix.
dated-reportEvery run ends with a dated report.
demote-onlyInventory owner-rules may demote auto→report, never promote report→auto.

Phase 0: inventory (self-maintaining)

docs/dep-radar/inventory.md carries one row per pinned surface: pin location, upstream check command, refresh procedure, verify command, risk tier, applicable playbook, and any repo-specific owner rules.

First run (no inventory): sweep the repo for pins in package manifests and lockfiles, vendor/ dirs, SHA-256 constants near download or pin code, model manifest scripts, and version constants referencing upstream releases. Write the inventory, wire an upstream check per surface, and have the owner review the tiers.

Every run: diff discovered pins against the inventory, add new surfaces (each with a check), drop removed ones, and note the change in the run report.

Phase 1: detect

Read docs/dep-radar/last-seen.json (create if absent) and run each surface's upstream check. If nothing moved since last-seen, update checked_at, write a one-line report, and stop.

Phase 2: research

For each changed surface, read the changelog or release notes, never infer from version numbers. Extract breaking changes, deprecations, security fixes, new capabilities, and anything touching a contract the inventory names for that surface.

Phase 3: classify

Sort every finding per the operating policy plus the inventory's per-surface tier and owner rules.

Phase 4: apply the auto tier

Apply the inventory's refresh procedure, then fix the fallout in that surface's PR: migrate changed APIs, re-vendor bundled-extension bridges, repair broken tests and CI. Run the verify command; open the PR only once it passes locally, following the repo's review and merge-queue conventions. PR body: old→new version, changelog summary with links, fallout fixed, what was verified.

A blocker mid-apply or a failed verification stops the surface and makes it a report item with the exact error output, never ship a partial bump.

Phase 5: report

Write docs/dep-radar/report-<YYYY-MM-DD>.md, committed with the last-seen update: auto-applied bumps with PR links; blocked bumps with exact error output; the owner-decision tier; new capabilities unlocked. Each awaiting-decision item names the capability, what it unlocks, estimated effort and risk, and a recommendation. Surface the report to the owner (PR description or handoff doc), not just the file.

Technology playbooks

The inventory records which apply and every concrete package, binary, and fork name.

SurfaceUpstream checkTier and handlingVerify
Pinned AI/agent SDKRegistry latest + release notesAuto-with-fixes, majors included: migrate changed auth, runtime, and tooling APIs in the same PR. New provider models a bump exposes are report-tier; the bump itself ships.Build + test suites; confirm expected models and features appear
Pinned runtime binary with SHA constantsOfficial release manifest for the exact version, never a third party, never hand-computed from a local download aloneAuto-with-fixes: migrate auth, protocol, and contract changesPin unit tests + a live download smoke on the host platform
npm/pnpm depspnpm -r outdated, pnpm auditAuto-with-fixes, including majors: fix the mechanical fallout (renamed APIs, config, broken tests) in the same PRTypecheck + tests
cargo depscargo update --dry-run, cargo audit when installedAuto-with-fixes, including majorsWorkspace tests at the repo's CI feature parity
Bundled-extension forks, a small upstream synced in by script, provenance tracked, local patches on topThe sync script's upstream refAuto-with-fixes only when the consuming repo's full test suite gates the sync: take the update, rebase the local patches, fix fallout in the same PR.That full test suite plus the sync script's own checks
Patched vendor forks of large upstreams, with no script-gated syncUpstream releasesReport, owner-decidednone
Model weights and artifact SHA pinsUpstream manifestReport, never swap weights automaticallyThe repo's own integrity-verify scripts
Pinned GitHub Actions SHAsTag → SHA for the same actionAuto for patch/minor tag moves, refreshing the SHA comment too; majors auto-with-fixes, migrating the workflow in the same PRWorkflow run

Guardrails

  • Migration-bearing dep bumps (DB or storage tooling) carry merge-order and version-gap hazards; check the repo's before merging.
  • Shell commands follow orch SKILL.md § Harness-Safe Shell.

Frequently asked questions

What does the Dep Radar AI skill do?

Load to run or tune a dependency sweep.

Why use Dep Radar on TypingMind?

Because you install it once and use it with any model. Dep Radar 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 Dep Radar in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vanillagreencom/kendex/tree/main/skills/dep-radar. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dep Radar?

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 Dep Radar?

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

Is the Dep Radar AI skill free?

Yes. It is published on GitHub by vanillagreencom 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 👇