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 openclaw-hawkinsgit 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/openclaw-hawkins)<a href="https://agentmods.dev/skills/parijatmukherjee/openclaw-hawkins/openclaw-hawkins"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/openclaw-hawkins/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/openclaw-hawkins"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/openclaw-hawkins.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 | $0.00167 | $0.10771 |
| Opus 5 | $0.00084 | $0.05386 |
| Sonnet 5 | $0.00033 | $0.02154 |
| Haiku 4.5 | $0.00017 | $0.01077 |
Grade B, and why
openclaw-hawkins-installer scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
mkdir -p "$HOME/.openclaw/secrets" && chmod 700 "$HOME/.openclaw/secrets" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
command -v curl >/dev/null # required for the fallback clone path How it starts
The opening of the file, as written. The whole thing — 896 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: install openclaw-hawkins
You are installing the openclaw-hawkins multi-agent pattern on the host you have shell access to. The end state: one orchestrator (the Nexus — agent:main, typically yourself) coordinating six isolated specialist agents (the Tendrils: system-agent, code-agent, research-agent, data-agent, comm-agent, vision-agent), with optional VINES (durable orchestration state) and VECNA (Hive knowledge sharing).
Once started, this skill runs mostly unattended — every routine decision point has a documented default, and where a default is wrong the failure mode is loud and recoverable. It is not unsupervised carte blanche: it must get the operator's go-ahead before it begins making changes, and it stops to ask before anything outside the documented defaults.
⚠️ Before you start — what this install changes on the host. Surface this to the operator and get an explicit go-ahead before Phase 1:
- Writes persistent files under
$HOME/.openclaw(agent workspaces,AGENTS.mdoverlays, backups).- Installs a user systemd service and an
EnvironmentFile, and restarts the OpenClaw gateway.- Handles a database password (read from 1Password or the env into a
0600file; never written toopenclaw.json).- Enables a plugin that activates on every gateway startup and registers VINES/VECNA tools — this is an ongoing capability, not a one-shot script.
- VECNA stays disabled unless the operator explicitly opts in; when enabled it reads from and writes to a shared knowledge store outside this host.
If the operator hasn't clearly agreed to these, confirm before proceeding.
Trigger phrases
This is a high-impact installer. Trigger it only on an explicit, unambiguous request to install / set up / upgrade openclaw-hawkins (or its named components) on this host — for example:
- "Install openclaw-hawkins on this host"
- "Set up the openclaw-hawkins multi-agent orchestration"
- "Bootstrap / upgrade openclaw-hawkins"
- "Deploy the openclaw-hawkins Tendrils / agent swarm"
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 · 896 lines · 167 tokens per session scan B 147e0da387c8
openclaw-hawkins-installer is a skill published in the GitHub repository parijatmukherjee/openclaw-hawkins (5 stars, last pushed 3mo ago), licensed MIT. It adds 167 tokens to every session and 10,771 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). 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.