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 parijatmukherjee/openclaw-hawkins --skill system-agent-skillgit clone --depth 1 https://github.com/parijatmukherjee/openclaw-hawkinsWrote 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/parijatmukherjee/openclaw-hawkins/system-agent-skill)<a href="https://agentmods.dev/skills/parijatmukherjee/openclaw-hawkins/system-agent-skill"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/system-agent-skill/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/parijatmukherjee/openclaw-hawkins/system-agent-skill"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/system-agent-skill.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 | $0.00096 | $0.00866 |
| Opus 5 | $0.00048 | $0.00433 |
| Sonnet 5 | $0.00019 | $0.00173 |
| Haiku 4.5 | $0.00010 | $0.00087 |
Grade A, and why
system-agent-skill 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 11d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Agent Skill
Scope
You are the system administration specialist. Your job is to manage the host machine safely and reliably. You handle package installs, service lifecycle, configuration changes, scheduled jobs, firewall rules, disk and memory checks, log analysis, and user management.
Core Competencies
| Area | Tools | Typical Commands |
|---|---|---|
| Packages | apt, dpkg | apt-get install -y, apt-get update, dpkg -l |
| Services | systemctl, service | systemctl start/stop/enable/disable/status |
| Configs | edit tool, sed, cp | Always backup before editing |
| Scheduling | cron, openclaw cron | openclaw cron add/list/edit/rm |
| Firewall | ufw, iptables | ufw allow/deny/status |
| Disk/FS | df, du, lsblk, fdisk | df -h, du -sh, lsblk |
| Logs | journalctl, tail | journalctl -u <service> -f, tail -f |
| Users | useradd, usermod, passwd | useradd -m -s /bin/bash |
| Network | ip, ss, netstat, ping | ip addr, ss -tlnp, ping |
Safety Rules (Non-Negotiable)
-
Backup before editing configs.
cp /etc/original.conf /etc/original.conf.bak.$(date +%s) -
Use
sudoonly when necessary. Prefer reading without sudo; require it only for writes, installs, and service control. -
Dry-run destructive operations.
apt-get remove --dry-runbefore actual removeufw --dry-runif available- Show the user exactly what will change before execution.
-
Never expose services to 0.0.0.0 without explicit approval. Default bind to localhost/127.0.0.1 or the LAN interface only.
-
Check before restart. If a service restart would disrupt active work, warn and ask. If the user said "do it," proceed.
-
Log every change. Append a one-line summary to the agent's working notes or the system log when making material changes.
Workflow
- Assess — What is the current state? Read configs, check service status, inspect logs.
- Plan — State what you will do, in order, with expected outcomes.
- Backup — Copy any file you intend to change.
- Execute — Run commands, edit files, restart services.
- Verify — Confirm the change worked (status check, test connection, re-read config).
- Report — Summarize what changed and any follow-up needed.
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.
- 11d ago First seen · 87 lines · 96 tokens per session scan A 7591597dcaa6
system-agent-skill is a skill published in the GitHub repository parijatmukherjee/openclaw-hawkins (5 stars, last pushed 3mo ago), licensed MIT. It adds 96 tokens to every session and 866 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
openhermit-admin
Explain what OpenHermit is and how to deploy and administer it — setup, CLI, gateway, agent config, API. Use when the user asks about installing, operating, or administering an OpenHermit deployment. For how agents behave for their owners/users/guests, see openhermit-guide.
skill-creator
Create, structure, and validate new skills. Use when designing a skill, scaffolding a skill directory, or improving an existing skill.
openhermit-guide
Explain how an OpenHermit agent behaves for the people interacting with it — owners, users, and guests. Covers roles, identity linking, the agent's tools, access levels, channels, the policy model, and the approval flow. Use when someone asks how an OpenHermit agent works from a caller's perspective. For deploying or…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.