A read-only disk-space survey and cleanup plan. It finds large files and captures, checks available storage and network storage, and proposes verified copies to a NAS, which is shared storage on a network, before any deletion.

Use it to inspect local and LiDAR storage, find large or unused worktrees, plan transfers to the NAS, and confirm that copied data has a recorded verification result.

It helps recover space without silently moving or deleting data. Verification and a user-controlled deletion step reduce the risk of losing captures, results, or media.

How banshee-data/velocity.report configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to banshee-data/velocity.report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/banshee-data/velocity.report/main/.claude/skills/free-space/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/banshee-data/velocity.report

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/banshee-data/velocity.report/free-space/github.svg)](https://agentmods.dev/skills/banshee-data/velocity.report/free-space)

Your own site

<a href="https://agentmods.dev/skills/banshee-data/velocity.report/free-space"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/free-space/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/banshee-data/velocity.report/free-space"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/free-space.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,109 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.01109
Opus 5.5	$0.00017	$0.00444
Sonnet 5.5	$0.00008	$0.00222
Haiku 4.5	$0.00004	$0.00111

Measured 19d ago against content hash 220d061e4284, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

free-space scanned grade C with 1 finding 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 19d ago.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

result, and let the user run the real thing. Do not run `rm -rf` yourself.

.claude/skills/free-space/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: free-space

Survey the internal disk and the lidar volume, then propose a short, reviewable list of moves to the NAS (arrow.local). The scan never changes anything. Copies come second, and deleting originals is always the user's step.

Usage

/free-space
/free-space --min-mb 500

Procedure

1. Scan

scripts/free-space-scan.sh                  # threshold 1000 MB
scripts/free-space-scan.sh --min-mb 500     # pass the skill's --min-mb through unchanged

It reports free space, NAS mount state, large items under the home folder, ~/Library, ~/code, the lidar volume, idle git worktrees (scripts/worktree-sweep.sh, dry run) and files over 1 GiB. Each candidate carries a class, a suggested destination and whether a verified NAS copy is already on record.

The record check is a name match against validate_*.txt, so it can be wrong both ways: a similarly named folder can match a different tree, and a tree copied under another name shows "no PASS record". Treat it as a lead and confirm against the manifests before proposing deletion.

If a NAS share is missing, the scan prints the remount command. Do not start copies until all three shares are mounted.

2. Sort candidates into four groups

Group	What	Action
Regenerable	build caches, `DerivedData`, `node_modules`, `.gocache`, logs	Propose deletion (the user runs it)
Worktrees	idle agent worktrees	`scripts/worktree-sweep.sh` dry run, then the user runs it with `--apply`
NAS-bound	`captures` -> `banshee-captures`, `results` -> `banshee-results`, `media` -> `media`	Copy, verify, then hand over a guarded delete
Review	anything else	Ask; never guess

Read the full file on GitHub · 100 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.

19d ago First seen · 100 lines · 42 tokens per session scan C 220d061e4284

Subscribe to this mod's changes

free-space is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,109 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.

Productivity lidar radar road-safety street-safety traffic-analysis urban-analytics

free-space next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
free-spacebanshee-data/velocity.report	Skill	11	today	Apache-2.0	C	42	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex
mochi-remindkirodotdev/KiroCrew	Skill	4.8k	yesterday	Apache-2.0	A	20	Claude Code, Codex

velocity.report: Skill for Claude Code