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/deeryang/server-security-init-skill/server-security-initnpx skills add DeerYang/server-security-init-skill --skill server-security-initgit clone --depth 1 https://github.com/DeerYang/server-security-init-skillWhat 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 | $0.00057 | $0.02064 |
| Opus 5 | $0.00028 | $0.01032 |
| Sonnet 5 | $0.00011 | $0.00413 |
| Haiku 4.5 | $0.00006 | $0.00206 |
Grade A, and why
server-security-init scanned grade A 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 2d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
description: "Use when safely initializing or hardening a newly installed or rebuilt Ubuntu/Debian server over SSH, including SSH keys, a non-root sudo user, SSH policy, server timezone, UFW, fail2ban, local SSH config, Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Server Security Init
Purpose and Scope
Harden a fresh Ubuntu/Debian server without locking the operator out. Treat SSH, firewall, fail2ban, and service-manager changes as high-risk: inspect first, add and verify a parallel access path, then remove old access paths.
This workflow targets OpenSSH with systemd. UFW and fail2ban are optional. For another distribution, firewall, init system, or SSH implementation, stop before mutation, explain the differences, and obtain agreement on an adapted plan.
Intake
Collect the bootstrap facts before touching the server. Infer values from prior context or local SSH config when safe, but show inferred values and obtain confirmation before high-risk mutations.
| Parameter | Meaning |
|---|---|
root_public_key_installed |
Whether the selected public key already works for the initial login user |
target_host |
Server IP, hostname, or existing SSH alias |
initial_user |
Current login user, often root |
initial_port |
Current SSH port, often 22 |
admin_user |
Non-root human administrator account to create or verify |
public_key_source |
Local .pub file, existing authorized key, or pasted public key |
local_key_name |
Local key basename, usually derived from the server alias |
identity_file |
Matching local private-key path used for every access-path gate |
ssh_config_alias |
Local SSH alias to create or update |
new_ssh_port |
Final SSH port |
target_timezone |
Desired IANA timezone such as UTC or Asia/Shanghai, or keep-current |
recovery_access |
Available provider console, VNC, rescue panel, or other out-of-band recovery path |
external_firewall_ready |
Whether provider/security-group rules permit the temporary and final SSH ports |
Collect these choices at the same intake gate:
| Parameter | Default |
|---|---|
disable_root_login |
true; when false, retain root public-key login rather than enabling root passwords |
disable_password_login |
true |
enable_ufw |
true |
rebuild_ufw |
false; preserve existing rules unless the user explicitly approves rebuilding them |
allowed_tcp_ports |
No additional ports; new_ssh_port is handled separately |
enable_fail2ban |
Ask; do not infer consent |
management_ips |
Required only when enabling fail2ban; current and usual admin egress IPs/CIDRs |
fail2ban_maxretry |
3 |
fail2ban_findtime |
86400 |
fail2ban_bantime |
86400 |
generate_local_keypair |
Ask if no usable key exists |
local_key_comment |
Server alias or user-specified comment |
local_key_passphrase |
Ask; do not assume an empty passphrase |
What ships with it
3 files 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.
- 2d ago First seen · 116 lines · 57 tokens per session scan A ee3087289e3c
server-security-init is a skill published in the GitHub repository DeerYang/server-security-init-skill (38 stars, last pushed 8d ago), licensed MIT. It adds 57 tokens to every session and 2,064 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.