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 Ares960826/luffy-arm --skill luffy-arm-fullpower-ongit clone --depth 1 https://github.com/Ares960826/luffy-armWrote 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/ares960826/luffy-arm/luffy-arm-fullpower-on)<a href="https://agentmods.dev/skills/ares960826/luffy-arm/luffy-arm-fullpower-on"><img src="https://agentmods.dev/badge/skills/ares960826/luffy-arm/luffy-arm-fullpower-on/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/ares960826/luffy-arm/luffy-arm-fullpower-on"><img src="https://agentmods.dev/badge/skills/ares960826/luffy-arm/luffy-arm-fullpower-on.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 20 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 23 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00087 | $0.00784 |
| Opus 5 | $0.00044 | $0.00392 |
| Sonnet 5 | $0.00017 | $0.00157 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
luffy-arm-fullpower-on 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 12d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
luffy-arm full-power ON
This is the explicit ON companion operation for luffy-arm. Read the sibling luffy-arm skill's
Full-power mode section first; its invariants remain authoritative.
Operation
-
Confirm the user explicitly asked to enable full-power. Never infer consent from a task that merely needs write access.
-
Check before re-arming. Run the main skill's
bash scripts/fullpower.sh statusfrom the siblingluffy-armdirectory before showing any ON command. If the agent runtime is known to sandbox SSH or ssh-agent, request narrowly scoped, user-approved host execution for this first check immediately; do not run a known-blocked sandbox probe first.DEDICATED GATE: ON: do not ask the user to re-enter the passphrase. Report the verified state. If the same request also contains an authorized remote task, continue it under the siblingluffy-armskill instead of stopping at the switch.DEDICATED GATE: UNKNOWN: do not ask the user to re-enable Full Power. Retry with approved host execution; if that is unavailable, ask the user to runluffy fullpower statusin their normal login terminal and report the result.DEDICATED GATE: OFFplusEFFECTIVE USER ACCESS: AVAILABLE: an alternate credential already reachesADMIN_USER. Do not claim Safe Mode or require re-arming merely to obtain the same remote user capability. Ask for the dedicated gate only if the user explicitly wants that credential path armed.DEDICATED GATE: OFFplus no effective user access: continue to step 3.
-
Only after verified
OFF, do not execute the ON wrapper on the user's behalf. Show the user this command from this skill directory and wait for them to run it in their own interactive login terminal:bash scripts/fullpower-on.sh [seconds]The wrapper delegates to the main
luffy-arm/scripts/fullpower.sh on; it checks the admin key and SSH alias, then the user types the key passphrase directly intossh-add. ON publishes a stable reference to that time-limited agent so other conversations can use the same gate without inheriting the sameSSH_AUTH_SOCK. Never request, capture, paste, or store that passphrase. -
After the user confirms the command completed, repeat the same host-first status check.
-
Report exactly one of these outcomes:
DEDICATED GATE: ON: independently confirmed.UNKNOWN: approved host execution was unavailable, or the host could not inspect the login-session ssh-agent/SSH channel. State that the user reported ON but it is not independently visible; never translate UNKNOWN to OFF.DEDICATED GATE: OFFor an error: report the separate effective-access layer before saying which capabilities remain. Never equate gate OFF with Safe Mode by itself.
What ships with it
2 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.
- 12d ago First seen · 54 lines · 87 tokens per session scan A e4c2323c96e5
luffy-arm-fullpower-on is a skill published in the GitHub repository Ares960826/luffy-arm (19 stars, last pushed 16d ago), licensed MIT. It adds 87 tokens to every session and 784 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
netcatty-tool-cli
Use this skill when an external agent needs to operate on Netcatty sessions through Skills + CLI instead of the netcatty-remote-hosts MCP server.
vibeshell
Control SSH and SFTP through VibeShell's visible Agent Gateway. Use for shared terminal sessions, remote commands, logs, files, and transfers.
file-ops
Read, write, list, move, and inspect files and directories on a remote host via QuickDesk. Use when the user needs to browse folders, view file contents, create or edit files, rename or relocate files, or check file metadata (size, permissions, modification time) on a remote machine.
cis-aws-foundations-6.2
Ensure no Network ACLs allow ingress from 0.0.0.0/0 to remote server administration ports.
cis-aws-foundations-6.4
Ensure no security groups allow ingress from ::/0 to remote server administration ports.
huawei-cloud-ascend-remote-connect
Provides temporary SSH remote connection for Huawei Cloud Ascend devices with dynamic host/port/user/password input (in-memory only), disk management, NPU monitoring, container management, security auditing and log analysis; sensitive operations require user confirmation before execution Use this skillthis skill to…