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 jazelly/tokenless --skill tokenless-installgit clone --depth 1 https://github.com/jazelly/tokenlessWrote 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/jazelly/tokenless/tokenless-install)<a href="https://agentmods.dev/skills/jazelly/tokenless/tokenless-install"><img src="https://agentmods.dev/badge/skills/jazelly/tokenless/tokenless-install/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/jazelly/tokenless/tokenless-install"><img src="https://agentmods.dev/badge/skills/jazelly/tokenless/tokenless-install.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 MCP Rug Pull · line 27 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00043 | $0.01520 |
| Opus 5.5 | $0.00017 | $0.00608 |
| Sonnet 5.5 | $0.00009 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
tokenless-install 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tokenless API installation and maintenance
Install prepares software; setup changes user choices; upgrade replaces software while preserving those choices. Match the requested scope and report in the user's language; a check-only request stays read-only.
Select the installation channel
Identify the OS, architecture, and executable location before choosing commands.
| Installation | Route |
|---|---|
| Windows x64 (prerelease) | npm CLI in PowerShell or a terminal; no macOS menu app. |
| Apple Silicon macOS, npm CLI | npm CLI; the menu app is a separate optional install. |
| Apple Silicon macOS 13+, standalone app | Bundled Node, CLI, and daemon; use the app's own update action or embedded CLI. Global npm does not update this app. |
| Source-linked CLI | Refresh the selected checkout and preserve its development link; do not replace it with a published npm package. |
The standalone app needs no global Node/npm, but excludes browsers and the G4F Python environment. For a requested app install, use the matching release ZIP and SHA-256 checksum.
For a requested macOS app source build, use npm run install:macos-menu. Verify the menu and daemon afterward. Do not infer support for other platforms from browser artifacts alone.
Choose the workflow
| Request | Commands |
|---|---|
| Fresh npm CLI | Check Node.js 22.13+ and npm, then npm install --global tokenless@latest and tokenless --version; continue to setup, or run skill sync for a software-only install. |
| Interactive setup | tokenless setup |
| Setup with known browser/profile choices | tokenless setup --browser <browser> --profile <slug> --defaults --json |
| Check for updates | tokenless upgrade --check --json |
| Authorized upgrade | tokenless upgrade --yes --json through the selected installation channel. |
| Sync skills only | tokenless skills sync --json |
| Diagnose installation | tokenless doctor --json |
Use the installed tokenless command, never npx tokenless. Carry the selected --home through runtime commands; skill sync is user-global and takes no --home. Install missing prerequisites within the authorized scope or report what is missing.
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 Changed · -62 lines · -9 tokens per session a9f0aa0d1b95
- 1mo ago Changed · +45 lines · -4 tokens per session 4569f439d1e5
- 1mo ago First seen · 98 lines · 56 tokens per session scan A 7202873f32fe
tokenless-install is a skill published in the GitHub repository jazelly/tokenless (16 stars, last pushed 29d ago), licensed MIT. It adds 43 tokens to every session and 1,520 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 2026-08-30.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
agent-browser
Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
codebase-navigation
Use this skill when starting work in an unfamiliar codebase or area — finding where something is implemented, how a request flows, what depends on a piece of code, or where a change should go — before reading files one by one. Triggers: user says "where is", "how does this work", "find the code that", "explain this…
data-scraper
Use when data lives on a website with no usable API — listings, prices, public records — and the scrape must stay legal and not get blocked: legal gate, extraction path, durable selectors, pacing, resilience. NOT parsing bytes you already hold into fields (that is structured-extraction), NOT a documented API or key…