MemOS is a memory operating system that stores, retrieves, and manages long-term memory for large language models and AI agents. It supports context-aware interactions by organizing text, images, tool traces, personas, and knowledge bases for reuse across tasks.
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 agentmods add skills/memtensor/memos/safe-file-deletionnpx skills add MemTensor/MemOS --skill safe-file-deletiongit clone --depth 1 https://github.com/MemTensor/MemOSWrote 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/memtensor/memos/safe-file-deletion)<a href="https://agentmods.dev/skills/memtensor/memos/safe-file-deletion"><img src="https://agentmods.dev/badge/skills/memtensor/memos/safe-file-deletion.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00293 |
| Opus 5 | $0.00023 | $0.00147 |
| Sonnet 5 | $0.00009 | $0.00059 |
| Haiku 4.5 | $0.00005 | $0.00029 |
Grade C, and why
safe-file-deletion 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 5d 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` (directories) What it actually says
Safe File Deletion
Rule
Before deleting ANY file, you MUST:
- Call
request_file_permissionwithoperation: "delete" - For multiple files, use
filePathsarray (not multiple calls) - Wait for response
- Only proceed if "allowed"
- If "denied", acknowledge and do NOT delete
Applies To
rmcommands (single or multiple files)rm -rf(directories)unlink,fs.rm,fs.rmdir- Any script or tool that deletes files
Examples
Single file:
{
"operation": "delete",
"filePath": "/path/to/file.txt"
}
Multiple files (batched into one prompt):
{
"operation": "delete",
"filePaths": ["/path/to/file1.txt", "/path/to/file2.txt"]
}
No Workarounds
Never bypass deletion warnings by:
- Emptying files instead of deleting
- Moving to hidden/temp locations
- Using obscure commands
The user will see a prominent warning. Wait for explicit approval.
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.
- 5d ago First seen · 51 lines · 46 tokens per session scan C 38cdb761ecfb
safe-file-deletion is a skill published in the GitHub repository MemTensor/MemOS (11,188 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 293 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
agent-memory-onboarding
On-demand provisioning guide for a Memmy GUI task that fully connects an explicitly named local Agent: discover its active history store, install or remove its rendered Memmy Skill, bootstrap a scan boundary, persist a validated automatic-sync recipe, and verify GUI-visible readiness.
update-setup
One-time setup wizard for the memmy upgrade skill. Triggers: setup update, configure update, 切设置更新, 初始化更新.
skill-creator
Create, edit, improve, tidy, review, audit, or restructure memmy-agent skills and SKILL.md files.
ui-craft
Design, build, redesign, or modify browser-visible web interfaces with product-quality composition, visual systems, interaction states, responsive behavior, accessibility, and browser visual QA. Use for HTML, CSS, JavaScript, React, Vue, or Svelte pages and components, landing pages, dashboards, admin tools, settings…
memmy-memory
Use the memmy-memory CLI when an agent needs to check the Memory service, open or close agent sessions, start or complete turns, search, add, read, or delete memories, or call uncommon HTTP routes through raw requests.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.