Absolute Prune logo

Absolute Prune

Community
dhruvjainin
absolute-prune

Dead code and dependency cleanup, repo-wide: unused deps, unreferenced exports, unreachable code, orphaned files — removed only with tool evidence, in reversible waves. Runs on green main. For diff-scoped cleanup use absolute-simplify. Triggers on "absolute prune", "remove dead code", "find unused deps/exports", "what can we delete", "clean up orphaned files".

Overview

Publisherdhruvjainin
Repositoryabsolute
Skill nameabsolute-prune
Stars
223
Forks
30
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by dhruvjainin on GitHub. Read the source before you install it.

Installation

Install the Absolute Prune 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/dhruvjainin/absolute/tree/main/skills/absolute-prune
  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/dhruvjainin/absolute.git /tmp/absolute
mkdir -p .claude/skills
cp -r /tmp/absolute/skills/absolute-prune .claude/skills/absolute-prune
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Absolute Prune 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 Absolute Prune 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 Absolute Prune 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.

Start your first response with the ✂️ emoji.

Absolute Prune

Cut dead growth from the repo: unused dependencies, unreferenced exports, unreachable code, orphaned files. Evidence-based — every removal is backed by a tool that proves nothing references it — applied in safe waves with tests green after each.

Runs the shared engine in references/health-engine.md — read it for the DETECT → SCAN → TRIAGE → FIX → VERIFY → REPORT loop and the safety contract. This file covers only what's specific to pruning.


When to use

  • "Remove dead code", "clean up unused deps", "what can we delete?".
  • Bundle/install bloat from packages nothing imports anymore.
  • Post-refactor orphans: files and exports left behind after a feature was rerouted.

prune vs simplify: simplify polishes your working git diff. prune sweeps the whole committed repo for things that are dead repo-wide. Use simplify mid-change; prune as standing cleanup on green main.


What it scans

Dead dependencies — declared but never imported (and missing deps that are imported but undeclared):

EcosystemTool
JS/TSdepcheck or knip (knip also covers exports/files)
Pythondeptry
Gogo mod tidy (diff), unused module detection

Dead code — unreferenced exports, unreachable branches, orphaned files:

EcosystemTool
JS/TSknip (exports/files), ts-prune, eslint no-unused-vars
Pythonvulture, ruff unused rules
Godeadcode ./..., staticcheck (U1000)

Prefer tools already in the project. Treat results as candidates — verify each isn't reached via dynamic import, reflection, DI, public API, or a config string before removing.


Risk ranking (TRIAGE)

WaveRemovalDefault
1unused devDeps, unreferenced local exports/functionsfix now — lowest risk
2unused runtime deps, orphaned internal filesfix this pass after confirming no dynamic ref
3anything reachable via public API, plugin system, dynamic require, reflection, or configgated / usually defer — high false-positive risk

Static tools miss dynamic references. Anything in wave 3, or anything a tool flags but you can't prove is dead, gets confirmed with the user or deferred — never auto-removed.


Fix & verify

  • Remove in small, reversible waves. One category per wave (e.g. "unused devDeps", then "orphaned files").
  • After each wave: full test + build + typecheck. A green typecheck/build is the proof the removed symbol truly had no references. If anything goes red, the symbol wasn't dead — revert and reclassify.
  • Removing a dep: drop it from the manifest, regenerate the lockfile, rebuild.
  • Don't delete: generated files, vendored code, public-API surface, or anything load-bearing for a config/plugin you can't trace. Report those as "suspected dead, needs human call". Treat preferences.health.protectedPaths from config as never-delete globs — anything matching is out of scope even if a tool flags it.

Gotchas

  1. Trusting the tool blindly. Dynamic imports, DI containers, reflection, and string-keyed lookups defeat static analysis. Confirm before deleting.
  2. Removing public API. A library's unused-internally export may be its whole point. Check the package entry points / exports map.
  3. Deleting generated or vendored files. They look orphaned but are rebuilt/checked-in on purpose.
  4. Big-bang prune. Deleting everything flagged in one commit makes regressions un-bisectable. Wave it.
  5. Scope creep into refactor. prune removes dead things; it does not restructure live code. Restructuring → simplify or work.

Companion commands

  • /absolute simplify — for restructuring/clarity of live code in your diff.
  • /absolute upgrade — pairs well: prune unused deps, then upgrade what remains.
  • /absolute debt — pruning often clears a batch of lint/unused-var warnings too.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Absolute Prune AI skill do?

Dead code and dependency cleanup, repo-wide: unused deps, unreferenced exports, unreachable code, orphaned files — removed only with tool evidence, in reversible waves. Runs on green main. For diff-scoped cleanup use absolute-simplify. Triggers on "absolute prune", "remove dead code", "find unused deps/exports", "what can we delete", "clean up orphaned files".

Why use Absolute Prune on TypingMind?

Because you install it once and use it with any model. Absolute Prune 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 Absolute Prune in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dhruvjainin/absolute/tree/main/skills/absolute-prune. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Absolute Prune?

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 Absolute Prune?

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

Is the Absolute Prune AI skill free?

Yes. It is published on GitHub by dhruvjainin 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 👇