cd /news/ai-tools/deadweight-what-your-claude-code-set… Β· home β€Ί topics β€Ί ai-tools β€Ί article
[ARTICLE Β· art-172464] src=github.com β†— pub= topic=ai-tools verified=true sentiment=Β· neutral

Deadweight: What your Claude Code setup costs on every request

A tool called deadweight, installed via `cargo install deadweight` or a prebuilt binary for macOS, Linux or Windows, audits Claude Code session history to measure the token overhead that plugins, skills, MCP servers and hooks add to every request before the user types anything. In the example run, each request carried 61.2k tokens (median of recent sessions 63.8k), of which ~19.4k came from the user's setup and ~41.8k from Claude Code itself, with deferred tool names (412) at ~7.1k tokens and skill listings (214) at ~6.2k the largest contributors. The tool reports that Claude Code caps the skill listing at roughly 30,000 characters, so 151 of 214 skills were listed by name only without descriptions, and it offers a `deadweight fix` command that disables 6 unused plugins and hides 11 unused skills to save ~6.8k tokens per request.

key takeaway

Claude Code resends installed plugins, skills, MCP servers and hooks on every request β€” 19.4k of a 61.2k-token baseline in the example β€” and once the skill listing passes roughly 30,000 characters, extra skills appear by name only, so hiding unused ones with `deadweight fix` saved ~6.8k tokens per r

read7 min views4 publishedNov 19, 2026
Deadweight: What your Claude Code setup costs on every request
Image: Michielbdejong (auto-discovered)

Find the dead weight in your Claude Code setup.

Every plugin, skill, MCP server and hook you install adds text to every single request Claude Code sends, before you type a word. deadweight measures that overhead from your own session history, tells you exactly where it comes from, shows what you never actually use, and removes it with one undoable command.

An example run. Yours will look different, and that's the point.

Same output as text #

$ deadweight

  Before you type a word, every request carries 61.2k tokens
  measured from your latest session; median of recent sessions 63.8k
  ~19.4k from your setup Β· ~41.8k from Claude Code itself (system prompt + 18 tools)

  WHAT YOUR SETUP ADDS
  Deferred tool names (412)            ~7.1k  β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ
  Skill listings (214)                 ~6.2k  β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ
  Hook injections (3)                  ~3.4k  β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ
  MCP server instructions (4)          ~2.1k  β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–
  Agent listings (12)                   ~600  β–ˆβ–ˆ

  BIGGEST SOURCES
  name                           type           tokens    used  contents
  github                         mcp server      ~3.9k    212Γ—  91 tools
  kitchen-sink                   plugin          ~3.6k   never  64 tools Β· 22 skills
  workflow-kit                   plugin          ~2.6k     14Γ—  hooks 2.2k Β· 11 skills
  playwright                     mcp server      ~1.4k   never  33 tools
  devops-pack                    plugin          ~1.3k      3Γ—  hooks 1.2k Β· 6 skills
  marketing-suite                plugin          ~1.1k   never  18 tools Β· 14 skills
  linear                         mcp server       ~810     37Γ—  41 tools

  PROBLEMS
  βœ— 151 of 214 skills are listed without a description: the skill listing is full
      (~30.0k characters). Claude sees only their names, so it can't tell when to use them.
      Including 4 you actually use: pdf-tools:extract, review-pr, workflow-kit:plan, +1 more
      Make room: hide what you don't use (deadweight fix), or set "skillListingBudgetFraction": 0.02 in settings.json
      (default 0.01; the extra room costs up to ~8.3k tokens per request).
  βœ— 2 MCP servers failed to connect at startup
  ! 9 MCP servers never signed in, still listing 18 auth-only tools
  ! 3 skill names are listed more than once
  ! 198 of 214 listed skills were not used in 30 days (~5.1k per request)

  Run deadweight fix to disable 6 unused plugins and hide 11 unused skills and save ~6.8k tokens per request.

  UNUSED, BUT YOURS TO REMOVE
  mcp server playwright              ~1.4k   claude mcp remove "playwright"

  LOADED IN EVERY PROJECT, USED IN ONE OR TWO
  mcp server linear                  ~810    37Γ— in /home/you/code/app (of 9 projects)
    in .claude.json, move "linear" from the top-level mcpServers into projects > "/home/you/code/app" > mcpServers
  • Your usage limit drains faster. The overhead is resent on every turn of every session.
  • Your context window fills sooner , so sessions compact earlier and Claude loses track of your actual work.
  • Claude gets worse at picking the right skill. This one surprised us: Claude Code caps the skill listing at roughly 30,000 characters. Once you go past it, skills are listedby name only, without their descriptions . With a few hundred skills installed, most of them end up as bare names, and Claude has no way to tell when to use them. Unused skills crowd out the ones you rely on.

None of this shows up anywhere in the UI. Plugins get installed one at a time and the total is never visible.

cargo install deadweight

Or grab a prebuilt binary for macOS, Linux or Windows from Releases. It's a single binary with no runtime dependencies.

deadweight                 # audit: what every request carries and where it comes from
deadweight --all           # list every source, not just the biggest
deadweight --days 60       # count anything used in the last 60 days as "used"
deadweight --json          # machine-readable output

deadweight fix --dry-run   # show what would change
deadweight fix             # disable unused plugins, hide unused skills (asks first)
deadweight undo            # put everything back

deadweight card            # save your totals as a PNG to share (no names on it)

fix options:

flag effect
--keep NAME never touch this plugin or skill, or connectors (repeatable)
--park-skills move unused skills into the backup folder instead of hiding them
--include-hooked also disable unused plugins that run hooks
--yes don't ask for confirmation
--force run even with fewer than 5 sessions of history

Restart Claude Code after fix or undo to load the new setup.

deadweight card writes deadweight-card.png: your total, how much of it is your setup, unused skills, and what fix would save. It shows totals only, never a plugin, skill or server name. --output card.svg gives you the SVG instead.

Post yours. I'd like to see the biggest one.

deadweight ships as a Claude Code plugin too, so you can ask Claude to audit its own setup:

/plugin marketplace add msertdev/deadweight
/plugin install deadweight@deadweight
/deadweight

The plugin needs the deadweight binary on your PATH (see Install). It adds a single short line to the skill listing, about 18 tokens.

Claude Code keeps a transcript of every session in ~/.claude/projects/. Alongside the conversation it records what was loaded at startup: the skill listing, the deferred tool names, MCP server instructions, the agent listing, hook output, and the token usage the API billed for each request.

deadweight reads those records:

  1. Measure. The total comes from the API usage of the first request of your latest session (input + cache write + cache read tokens). This number is measured, not estimated.
  2. Attribute. Each skill line, tool name, instruction block, agent and hook injection is traced to the plugin, skill, MCP server or connector that added it. Hook commands are matched against each plugin'shooks.json . Sizes are converted to tokens from text length; whatever your setup doesn't explain is Claude Code's own system prompt and tools.
  3. Check usage. Every transcript from the last 30 days (including subagents) is scanned forSkill calls, MCP tool calls, agent launches and slash commands.
  4. Diagnose. Failed and never-authenticated MCP servers, duplicate skill names, skills that lost their description, and single skills with very large descriptions.
  5. Scope. A user-scope MCP server loads in every project. If its tools were only ever called from one or two projects, deadweight says which ones, so you can move it to those projects and stop paying for it everywhere else. (A project's.mcp.json works too, if the team should share it.)

On the author's machine, 1.4 GB of transcripts (41 sessions, 400+ subagent runs) are scanned in about a second, in parallel.

  • Read-only by default. Onlyfix andundo write anything, and both ask first.
  • No secrets are read. From.claude.json deadweight takes only MCP servernames , never commands, environment variables or headers. A test checks that secret values never reach the output.
  • Nothing is deleted. Plugins are disabled insettings.json (enabledPlugins: false ), not uninstalled. Unused user skills are hidden from the model withskillOverrides ("user-invocable-only" ), so/name still runs them;--park-skills moves them into the backup folder instead. If none of your claude.ai connectors was used,disableClaudeAiConnectors switches them off in Claude Code (they stay connected on claude.ai).
  • Everything is backed up. Eachfix writes a manifest and a copy ofsettings.json to~/.claude/deadweight/backups/<timestamp>/ .undo reverts the latest one.
  • Conservative. Plugins that run hooks may be doing useful work deadweight can't see (memory, safety checks), so they are skipped unless you pass--include-hooked .fix refuses to run with fewer than 5 sessions of history.
  • No network. deadweight never makes a network request.

MCP servers in .claude.json are never edited, and neither is a single claude.ai connector while you still use others; deadweight prints the command that removes them, or where to move them, instead.

Does it work with CLAUDE_CONFIG_DIR? Yes, and you can also pass --config-dir.

Why does fix skip a plugin I never use? It runs hooks. Review it, then run deadweight fix --include-hooked, or disable it yourself with /plugin.

My usage looks wrong. Claude Code deletes transcripts older than cleanupPeriodDays (30 by default), so deadweight can't see further back than that. Use --keep for anything you use rarely but want to keep.

Is it affiliated with Anthropic? No. It's an independent open-source tool that reads files Claude Code writes on your machine.

Issues and pull requests are welcome. Start with CONTRIBUTING.md and the good first issues; the whole codebase is about 2,600 lines of Rust.

If deadweight misattributes something in your setup, run deadweight --json, remove anything private, and open an issue with the relevant part.

If deadweight saved you tokens, a star helps other people find it. If you'd like to chip in, you can donate via PayPal. Thank you!

MIT Β© Murat Sert

── more in #ai-tools 4 stories Β· sorted by recency
── more on @deadweight 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain β€” perfect for shipping the agent you just read about.

$git push zahid main
β†’ Live at https://your-agent.zahid.host βœ“
Get free account β†’ Pricing
from €0/mo Β· no card required
LIVE [news/deadweight-what-your…] indexed:0 read:7min 2026-11-19 Β· β€”