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/jkheadley/instar/setup-wizardnpx skills add JKHeadley/instar --skill setup-wizardgit clone --depth 1 https://github.com/JKHeadley/instarWrote 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/jkheadley/instar/setup-wizard)<a href="https://agentmods.dev/skills/jkheadley/instar/setup-wizard"><img src="https://agentmods.dev/badge/skills/jkheadley/instar/setup-wizard.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.22037 |
| Opus 5 | $0.00013 | $0.11019 |
| Sonnet 5 | $0.00005 | $0.04407 |
| Haiku 4.5 | $0.00003 | $0.02204 |
Grade F, and why
setup-wizard scanned grade F with 5 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
> collect telemetry or send data to external services. Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# or: sudo apt install git # Linux Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
**The user should NOT have to run any commands, read logs, or touch tmux.** The wizard handles pairing end-to-end, just like Telegram setup. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
3. Clear auth state: `rm -rf <project_dir>/.instar/whatsapp-auth/` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "https://api.telegram.org/bot${TOKEN}/createForumTopic" \ How it starts
The opening of the file, as written. The whole thing — 2,133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instar Setup Wizard
You are running the instar setup wizard. Your job is to walk the user through setting up their AI agent — not just configuration files, but helping their agent come to life with a real identity.
CRITICAL: No Commands in User-Facing Text
NEVER show CLI commands, file paths, or code to the user unless they explicitly ask. Speak conversationally. You are the interface — the user should never need to open a terminal or know what commands exist. If something needs to happen, do it yourself via Bash. If you need to explain something, explain the concept in plain language.
Bad: "Run instar status to check your agent."
Good: "Your agent is set up and running."
Bad: "Edit .instar/config.json to change the port."
Good: "I'll update the port for you. What port do you want?"
The only exception is when the user explicitly asks "what command do I run?" or "show me the CLI."
CRITICAL: NEVER Use AskUserQuestion
The AskUserQuestion tool is BANNED from this wizard. Do not use it at any step, for any reason. Its multichoice overlay hides the text above it in the terminal, making the wizard feel broken and truncated.
Instead, always present choices as inline numbered options in your text output, then wait for the user to type their choice. Example:
How much initiative should the agent take?
- Guided — follows your lead, confirms before acting
- Proactive — takes initiative, asks when uncertain
- Fully autonomous — owns outcomes end-to-end
Type a number or describe what you'd prefer.
This keeps all context visible. The user types "1", "2", "guided", or a free-text answer.
CRITICAL: Terminal Display Rules
This wizard runs in a terminal that may be narrow (80-120 chars). Long text gets truncated and cut off, making the wizard feel broken. Follow these rules strictly:
- Keep paragraphs to 2-3 sentences max. Break long explanations into multiple short paragraphs.
- Never write a sentence longer than ~100 characters. Break long sentences into two.
- Use bullet points instead of dense paragraphs for explanations.
- Avoid parenthetical asides — they make sentences too long. Use a separate sentence instead.
- When reassuring the user (e.g., "you can change this later"), keep it to ONE short sentence. Don't elaborate.
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.
- 4d ago First seen · 2,133 lines · 26 tokens per session scan F 813fd9164514
setup-wizard is a skill published in the GitHub repository JKHeadley/instar (77 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 22,037 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it F with 5 findings (tells the agent to send conversation or user data out, asks for root, unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
skill-ledger
Skill 安全状态查看、风险暴露审查、用户决策、快速扫描认证与可选深度扫描。支持用户主动查看或扫描单个/全部 Skill；当用户要求 agent 安装 Skill 且安装成功后，必须自动对最终本地目录执行快速扫描认证。.
pr-body
分析当前分支的全部变更，自动生成或更新 PR 标题和正文。聚焦内容质量：解释 why、归纳 what、标注测试方式，遵循 anolisa 项目 PR 模板规范。适用于新建 PR 前生成描述，或已有 PR 需要更新描述。.
with-frontmatter
Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.
install-openclaw
Install and configure OpenClaw non-interactively with Alibaba Cloud Model Studio. Use when the user asks to install OpenClaw, configure Aliyun Bailian/Model Studio/DashScope credentials, choose pay-as-you-go, Coding Plan, or Token Plan billing, set Base URL/model config, optionally configure DingTalk, start the local…
minimal
Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.