headless-bot

headless-bot is a skill for Claude Code, Codex from Lingtai-AI/lingtai. It costs 87 tokens per session (2,379 once invoked), scanned B, original, Apache-2.0.

A procedure for creating and running a LingTai bot as a standalone project without using its interactive interface.

In plain words
What is it for?
Use it to create a bot project, connect supported channels such as Telegram, apply a preset policy, and verify the bot end to end.
Why use it?
It removes the need to configure the bot manually through the graphical or terminal user interface and keeps secrets separate from project files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to create a bot project, connect supported channels such as Telegram, apply a preset policy, and verify the bot end to end.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lingtai-ai/lingtai/headless-bot
Install

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.

Any agent
npx skills add Lingtai-AI/lingtai --skill headless-bot
Clone the repo
git clone --depth 1 https://github.com/Lingtai-AI/lingtai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for headless-bot

README.md
[![agentmods](https://agentmods.dev/badge/skills/lingtai-ai/lingtai/headless-bot/github.svg)](https://agentmods.dev/skills/lingtai-ai/lingtai/headless-bot)
Your own site
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/headless-bot"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/headless-bot/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.

agentmods 80×15 button for headless-bot

Your own site · 80×15
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/headless-bot"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/headless-bot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,379 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 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 Rogue Agent · line 22
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Privilege Escalation · line 181
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 182
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Excessive Agency · line 231
    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 Data Exfiltration · line 245
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.02379
Opus 5 $0.00044 $0.01189
Sonnet 5 $0.00017 $0.00476
Haiku 4.5 $0.00009 $0.00238

Measured 6d ago against content hash fb0e83f331f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

headless-bot 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/create_telegram_bot_project.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

chmod 700 "<agent_dir>/.secrets"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

import json, os, urllib.request
tui/internal/preset/skills/swiss-knife/reference/headless-bot/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Headless Bot Project

Use this reference when a human asks for a LingTai-backed bot that should run as its own project without stepping through the interactive TUI. The pattern is channel-agnostic:

  1. Create a normal LingTai project with lingtai-tui spawn.
  2. Write channel secrets into sidecar files under the agent directory.
  3. Activate the required addon/MCP entries in init.json.
  4. Copy or construct the agent's preset policy (manifest.preset) by referencing the intended saved/template presets.
  5. Refresh or relaunch the agent and verify the channel end-to-end.

Do not fabricate .lingtai/ by hand. The supported bootstrap entrypoint remains lingtai-tui spawn. The helper bundled here currently provisions Telegram bots; future helpers for other chat surfaces should live under this same generic reference rather than creating channel-specific top-level skill names.

Inputs

Common inputs:

  • PROJECT_DIR: new project directory. It must not already contain .lingtai/.
  • PRESET: saved or template preset name for the initial lingtai-tui spawn.
  • AGENT_NAME: agent directory/name to create under .lingtai/.
  • LANGUAGE: one of en, zh, or wen.
  • Optional source agent init.json if the new bot should inherit the same manifest.preset policy as an existing orchestrator.

Telegram-specific inputs:

  • TELEGRAM_BOT_TOKEN: bot token from @BotFather. Keep it in the environment or a local prompt, never in shell history, logs, git, issues, or docs.
  • ALLOWED_USERS: comma-separated Telegram numeric user IDs allowed to talk to the bot.

Preferred Telegram Helper

Run the bundled helper. Use the installed-bundle path ~/.lingtai-tui/utilities/swiss-knife/reference/headless-bot/scripts/create_telegram_bot_project.py, or the source-checkout path tui/internal/preset/skills/swiss-knife/reference/headless-bot/scripts/create_telegram_bot_project.py:

read -rsp 'Telegram bot token: ' TELEGRAM_BOT_TOKEN; export TELEGRAM_BOT_TOKEN; echo
python3 <helper-path>/create_telegram_bot_project.py \
  --project-dir /path/to/new-project \
  --preset minimax \
  --agent-name my-bot-agent \
  --language en \
  --allowed-users 123456789 \
  --preset-policy-from /path/to/source-agent/init.json

Read the full file on GitHub · 274 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 274 lines · 87 tokens per session scan B fb0e83f331f2

Subscribe to this mod's changes

headless-bot is a skill published in the GitHub repository Lingtai-AI/lingtai (670 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 2,379 once invoked, about $0.0004 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 2026-09-03.