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 Peiiii/nextclaw --skill opencligit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/opencli)<a href="https://agentmods.dev/skills/peiiii/nextclaw/opencli"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/opencli/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/peiiii/nextclaw/opencli"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/opencli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.01426 |
| Opus 5.5 | $0.00018 | $0.00570 |
| Sonnet 5.5 | $0.00009 | $0.00285 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
opencli 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 1mo 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCLI
Overview
Use this skill to help the user work through a local opencli installation from inside NextClaw.
This skill is intentionally decoupled:
- The skill owns explanation, onboarding, readiness checks, workflow choice, and risk handling.
opencliowns actual execution.
From the user's point of view, the experience should feel complete:
- install or update
opencliif needed, - guide the user through browser or app setup,
- verify readiness,
- then run the real task.
Do not pretend the environment is ready when it is not.
What This Skill Covers
- public read-only commands,
- browser tasks that reuse the user's Chrome login session,
- Electron or desktop app adapters that
openclialready supports, - passthrough to external CLIs through
opencli, - first-use setup and troubleshooting.
What This Skill Does Not Cover
- inventing commands that do not appear in
opencli list, - claiming support for a site or app that
openclidoes not actually expose, - silently bypassing missing setup,
- silently triggering destructive or write actions,
- treating third-party runtime behavior as native NextClaw behavior.
First-Use Workflow
When the user asks for an opencli-powered task, follow this order.
1. Classify the task
Classify the task into one of these:
- public read task,
- browser session task,
- desktop app task,
- external CLI passthrough task.
If the task does not fit any supported opencli shape, say so clearly.
2. Check whether opencli exists
Run:
command -v opencli
If missing, explain that opencli must be installed locally first.
Recommended install:
npm install -g @jackwener/opencli
After installation, continue with readiness checks instead of jumping straight into the user task.
3. Run readiness check
Run:
opencli doctor
Use this as the main readiness gate.
If doctor fails, do not proceed to the real task yet. Diagnose the failure first.
4. Apply task-specific prerequisites
What ships with it
1 file 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.
- 1mo ago First seen · 225 lines · 45 tokens per session scan A e9bb9cf6eda1
opencli is a skill published in the GitHub repository Peiiii/nextclaw (262 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,426 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
meeting-notes
Use when the user asks to capture, structure, or summarize meeting notes / call notes / 1:1 discussion / standup notes. Produces a standard template with attendees, agenda, decisions, action items (owner + deadline), and open questions.
ha-settings
Manage Hope Agent application settings through conversation. Use when the user wants to view or change any app configuration: theme, language, enhanced focus indicators, proxy, temperature, notifications, tool timeout, context compaction, automatic session titles, web search, GitHub issue reporting, memory, embedding…
session-done
Prepare a concise session handoff when the user asks to wrap up, capture continuation context, or use /done. Retain a Markdown file only when requested.
chief-of-staff
Act as the user's chief of staff, not a task-taker. Use for planning a day or week, triaging priorities, prepping for meetings or calls, drafting messages on the user's behalf, tracking commitments and follow-ups, reviewing what's in-flight, or any moment the user wants a trusted operator who knows their context.…
Abu-Browser
Browser controls for Abu's built-in visible web browser. They let an agent open pages, click, fill in forms, take screenshots, and extract information.