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.
npx skills add causify-ai/helpers --skill system.analyze_disk_space_usegit clone --depth 1 https://github.com/causify-ai/helpersWrote 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.
[](https://agentmods.dev/skills/causify-ai/helpers/system.analyze_disk_space_use)<a href="https://agentmods.dev/skills/causify-ai/helpers/system.analyze_disk_space_use"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/system.analyze_disk_space_use/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.
<a href="https://agentmods.dev/skills/causify-ai/helpers/system.analyze_disk_space_use"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/system.analyze_disk_space_use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00012 | $0.01469 |
| Opus 5.5 | $0.00005 | $0.00588 |
| Sonnet 5.5 | $0.00002 | $0.00294 |
| Haiku 4.5 | $0.00001 | $0.00147 |
Grade C, and why
system.analyze_disk_space_use 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 28d 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.
# rm -rf ~/.cache/uv How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Find what is consuming the most disk space, identify what is safely reclaimable (unused container/VM images, caches, logs) versus what needs manual review, and report the findings
- Never delete, move, or modify anything: analysis only
Workflow
Check Overall Disk Usage
- Run
df -hto see total/used/available space per volume - On macOS, the volume that actually holds user data is
/System/Volumes/Data, not/: use itsCapacity/Availcolumns to judge how urgent the situation is
Survey the Home Directory
-
List top-level home directory usage, largest first:
> du -sh ~/* 2>/dev/null | sort -rh -
Recurse one level at a time into whichever directory dominates (on macOS this is typically
~/Library), always sorting by size, until you reach the actual large items instead of just a big parent directory name:> /usr/bin/du -sh ~/Library/* 2>/dev/null | sort -rh | head -30 -
Track every directory measured along the way: it feeds the top-10 list in "Rank Findings And Write The Report"
Check Container and VM Engines First
- On a dev machine these are usually the single biggest consumer, because they cache every pulled/built image and rarely self-prune
- For every engine that is installed, check its own usage report before digging into
raw directory sizes:
- Docker: if
dockerexists, rundocker system df -vfor a per-image/per-volume breakdown; images withCONTAINERS= 0 are unused and reclaimable - Apple
containerCLI (native macOS containers): ifcontainerexists, runcontainer system df; its data lives under~/Library/Application Support/com.apple.containerand Docker's VM disk lives under~/Library/Containers/com.docker.docker - Other engines present (
podman,colima,lima,nerdctl): use their equivalentsystem df/ usage-report command
- Docker: if
- A builder container (e.g. Docker's
buildxstate volume, Apple'sbuildkitbuilder container) can be reported as "active" and excluded fromRECLAIMABLEby the tool even when it has grown very large- Size it directly with
/usr/bin/du -sh <PATH>and report it as a manual candidate, along with the reset command that would reclaim it (docker buildx prune --all, orcontainer builder stop && container builder delete)
- Size it directly with
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 28d ago Changed · +1 lines 1b183c2c929d
- 1mo ago Changed · +20 lines 229065bbeedc
- 1mo ago Changed · -1 lines 6238510340cb
- 1mo ago First seen · 116 lines · 12 tokens per session scan C 5d1002207660
system.analyze_disk_space_use is a skill published in the GitHub repository causify-ai/helpers (150 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 1,469 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…