reclaim-disk

reclaim-disk is a skill for Claude Code, Codex from fmind/dot. It costs 37 tokens per session (665 once invoked), scanned A, original, MIT.

A safety-focused workflow for freeing disk space by finding and removing tool caches and other rebuildable files. It checks for running coding agents and uncommitted work before cleanup.

In plain words
What is it for?
Use it to inspect large directories, preview cleanup, remove shared caches, clean development-tool storage, and verify how much space was recovered.
Why use it?
It reduces the risk of deleting active session data or project changes while cleaning a full or nearly full disk. It also provides a preview and a final space check.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/fmind/dot/reclaim-disk
Any agent
npx skills add fmind/dot --skill reclaim-disk
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

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 reclaim-disk

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/reclaim-disk.svg)](https://agentmods.dev/skills/fmind/dot/reclaim-disk)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/reclaim-disk"><img src="https://agentmods.dev/badge/skills/fmind/dot/reclaim-disk.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 665 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.00665
Opus 5 $0.00018 $0.00332
Sonnet 5 $0.00007 $0.00133
Haiku 4.5 $0.00004 $0.00067

Measured yesterday against content hash 4a1c20b3649e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reclaim-disk 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 yesterday.

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.

skills/reclaim-disk/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reclaim Disk

Free disk space in safety order: the big shared caches first through dot prune, project directories last; dot-cli owns the dot prune flag reference.

Workflow

  1. Measure: duf for the filesystem, then dust -d 2 ~ and dust -d 1 ~/.cache ~/.local/share for the largest directories.
  2. Check for running agents: pgrep -af "claude|codex|agy|opencode|copilot|grok"; never delete the working directory, .agents/tmp, or session store of a live session.
  3. Preview: dot prune --dry-run --all=deep lists what the configured targets would remove (agent sessions, Go, uv, npm, mise, Docker, tool caches).
  4. Prune: dot prune --all=deep, or one target at a time (dot prune --go=module, dot prune --docker=system) when a cache still serves an active project.
  5. Tool-specific extras when still short: mise prune -y, pnpm store prune, go clean -modcache, uv cache clean, nvim --headless '+Lazy! clean' +qa.
  6. Project directories last: .venv, node_modules, target, dist, tmp in inactive projects; they rebuild from lockfiles.
  7. Verify and report: duf again; list the freed space per target and anything skipped because an agent was using it.

Gotchas

  • Never delete keys or secrets: ~/.config/chezmoi/key.txt (the age key), ~/.ssh, any secrets.fish or *.age file.
  • Uncommitted work: check git status before removing anything inside a repository.
  • Docker volumes: docker volume ls shows data volumes; remove one only when the user names it.
  • k3d cluster: dot prune --docker=system deletes stopped k3d clusters; stop and keep the cluster only when the user needs its state.

Documentation

  • dust · duf
  • Companion skills: dot-cli (every dot prune target and depth), k8s-local (the local cluster --docker=system can remove).

Read the full file on GitHub · 37 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. yesterday Changed 4a1c20b3649e
  2. yesterday First seen · 37 lines · 37 tokens per session scan A 220d73b1e1fe

Subscribe to this mod's changes

reclaim-disk is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 665 once invoked, about $0.0002 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 2026-09-03.