swiss-knife

swiss-knife is a skill for Claude Code, Codex from Lingtai-AI/lingtai. It costs 152 tokens per session (2,392 once invoked), scanned A, original, Apache-2.0.

A routing guide for choosing among small command-line utilities and integrations, such as image tools, audio tools, and vision tools.

In plain words
What is it for?
Use it to select the appropriate bundled tool for media generation, image understanding, audio analysis, or other command-line tasks.
Why use it?
It helps an agent find the right focused utility without loading every procedure or reference.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for aider. Also seen: mentions Claude Code; mentions Codex; built for aider.

Good fit Use it to select the appropriate bundled tool for media generation, image understanding, audio analysis, or other command-line tasks.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/swiss-knife"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/swiss-knife.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,392 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00152 $0.02392
Opus 5 $0.00076 $0.01196
Sonnet 5 $0.00030 $0.00478
Haiku 4.5 $0.00015 $0.00239

Measured 6d ago against content hash f4834f0bc7ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

swiss-knife 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 6d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (reference/academic-research/scripts/fetch_paper.py, reference/academic-research/scripts/test_authorized_publisher.py, reference/academic-research/scripts/test_fetch_paper.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.

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.

tui/internal/preset/skills/swiss-knife/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swiss Knife — Utility Toolkit Router

Swiss Knife is a top-level router for small, focused utility references. Enter through this file, choose exactly one nested reference from the catalog below, then read that nested SKILL.md for the actual procedure, examples, scripts, and assets.

Nested reference catalog

nested_references:
  - name: bash-cli-harnesses
    # Virtual cross-skill redirect, not a local reference/<name>/SKILL.md file.
    location: bash-manual reference/bash-*/SKILL.md
    description: >
      Coding-agent CLIs such as Claude Code, OpenAI Codex, OpenCode, Cursor
      Agent, MiMo Code, Qwen Code, Oh-My-Pi, Gemini CLI, Aider, Goose,
      OpenHands, and Crush are now owned by `bash-manual` because they run as
      long-lived shell subprocesses. Read `bash-manual` and then the matching
      nested `reference/bash-*/SKILL.md`; Swiss Knife only keeps non-bash utility
      references.
  - name: minimax-cli
    location: reference/minimax-cli/SKILL.md
    description: >
      Nested swiss-knife reference for the MiniMax `mmx` CLI. Read this for
      MiniMax-backed image, video, music, TTS, or ad-hoc shell vision tasks.
  - name: vision
    location: reference/vision/SKILL.md
    description: >
      Nested swiss-knife reference for image understanding. Read this when you
      need to describe, OCR, or critique an image and aren't sure which path
      applies — it routes between the built-in `vision` tool, the sibling
      `minimax-cli` reference, and a local Hugging Face VLM fallback.
  - name: listen
    location: reference/listen/SKILL.md
    description: >
      Nested swiss-knife reference for local audio analysis. Read this when the
      human asks you to transcribe a voice note, extract lyrics, critique
      generated music, or measure audio characteristics — all local, no API key
      (Whisper transcription and librosa music analysis).
  - name: academic-research
    location: reference/academic-research/SKILL.md
    description: >
      Nested swiss-knife reference for academic literature work. Read this to
      fetch full-text papers by DOI/arXiv-ID/PMID, trace citation networks, run
      scholar analysis, or write/compile LaTeX manuscripts — indexes 12 API
      references and 6 pipeline workflows.
  - name: dj
    location: reference/dj/SKILL.md
    description: >
      Nested swiss-knife reference for composing one music track from a project
      journal entry. Read this when the human asks for music for a journal day,
      project vibe, session mood, or a specific generated genre.
  - name: token-usage
    location: reference/token-usage/SKILL.md
    description: >
      Nested swiss-knife reference for network-wide token, cost, cache, and tool-call/API-call trend reports. Read
      this when the human asks about token usage, budget, model costs, spending, cache behavior, or tools per API call
      across agent ledgers.
  - name: html-report
    location: reference/html-report/SKILL.md
    description: >
      Nested swiss-knife reference for standalone HTML deliverables. Read this
      when the human asks for a polished browser-openable report, dashboard,
      memo, comparison, or any HTML artifact with MathJax equations.
  - name: xiaomi-mimo
    location: reference/xiaomi-mimo/SKILL.md
    description: >
      Nested swiss-knife reference for Xiaomi MiMo provider discovery. Read this
      when the human asks to use or configure Xiaomi MiMo / 小米MiMo, or when you
      need to understand the MiMo model family and compatible endpoints.
  - name: zhipu-coding-plan
    location: reference/zhipu-coding-plan/SKILL.md
    description: >
      Nested swiss-knife reference for the Zhipu / Z.AI / BigModel coding-plan
      subscription. Read this when the human asks about Zhipu credentials or the
      plan's vision, web search, web-read, and zread MCP capabilities.
  - name: headless-bot
    location: reference/headless-bot/SKILL.md
    description: >
      Nested swiss-knife reference for creating and operating headless LingTai
      bot projects from `lingtai-tui spawn`. The current helper provisions a
      Telegram MCP bot, and the workflow also covers preset-policy replication,
      addon wiring, secret hygiene, refresh/relaunch, and verification.
  - name: find-something-to-do
    location: reference/find-something-to-do/SKILL.md
    description: >
      Nested swiss-knife reference for idle curiosity practice. Read this when
      you have no pending task, no human waiting, and want a reflective way to
      notice quiet impulses or choose a small autonomous exploration.
  - name: preset-health
    location: reference/preset-health/SKILL.md
    description: >
      Nested swiss-knife reference for read-only saved-preset health checks.
      Read this when the human asks whether saved presets still work, which one
      is expired or misconfigured, or why `system(action="presets")` shows a bad
      connectivity status. It enumerates saved presets, classifies failures
      (expired key, missing credentials, unreachable endpoint, invalid
      model/config, connectivity failure), and reports actionable fixes without
      printing or mutating any secret.

Read the full file on GitHub · 182 lines

Files

What ships with it

50 files 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 Changed · -5 lines · -79 tokens per session f4834f0bc7ce
  2. 9d ago First seen · 187 lines · 231 tokens per session scan A 534694b2fc29

Subscribe to this mod's changes

swiss-knife is a skill published in the GitHub repository Lingtai-AI/lingtai (677 stars, last pushed yesterday), licensed Apache-2.0. It adds 152 tokens to every session and 2,392 once invoked, about $0.0008 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 2026-09-03.

Related

Other skills, from other repositories

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit calls, or resolve the link-prefetch-partial and instant-shell-url-data…

sanity-io/next-sanity · 92 tokens

sanity-live-cache-components

Integrates Sanity Live with Next.js Cache Components in next-sanity v13+ apps. Sets up sanityFetch, a shared cachedSanity 'use cache' boundary, , Visual Editing, Presentation Tool, draft mode handling, and the three-layer (Page/Dynamic/Cached) component pattern with explicit perspective/stega prop-drilling. Sequences…

sanity-io/next-sanity · 155 tokens

pnpm

Node.js package manager with strict dependency resolution. Use when running pnpm specific commands, configuring workspaces, or managing dependencies with catalogs, patches, or overrides.

sanity-io/next-sanity · 35 tokens

weather

Get current weather and forecasts.

initializ/forge · 7 tokens

biomed-skill-creator

Create new biomedical skills or improve existing ones for the OpenBioMed toolkit. Use this skill when: (1) Creating a new skill from scratch, (2) Capturing a workflow as a reusable skill, (3) Automating a biomedical task, (4) Improving an existing skill. This skill guides through an interactive process: define intent…

PharMolix/OpenBioMed · 89 tokens

biomed-skill-router

Find the most suitable skill for a given biomedical task. Use this skill when: (1) You are unsure which skill to use for a specific biomedical task, (2) You want to discover available skills for a particular domain, (3) You need to compare multiple skills for a given use case.

PharMolix/OpenBioMed · 67 tokens