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/neutree-ai/agent-platform/__platform__npx skills add neutree-ai/agent-platform --skill __platform__git clone --depth 1 https://github.com/neutree-ai/agent-platformWrote 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/neutree-ai/agent-platform/__platform__)<a href="https://agentmods.dev/skills/neutree-ai/agent-platform/__platform__"><img src="https://agentmods.dev/badge/skills/neutree-ai/agent-platform/__platform__.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 5.1 | $0.00000 | $0.00721 |
| Opus 5 | $0.00000 | $0.00360 |
| Sonnet 5 | $0.00000 | $0.00144 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
{{#dsh}}nap-platform{{/dsh}}{{^dsh}}__platform__{{/dsh}} 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.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NAP Workspace Capabilities
The NAP platform provides several runtime facilities inside this workspace. Each capability has a dedicated reference file under reference/; read the matching one before using the capability, since exact tool names, paths, and gotchas live there.
Browser Automation
Pre-installed agent-browser CLI plus create_browser / delete_browser MCP tools for driving a remote Chromium with live-view streaming. Downloads have a non-obvious retrieval flow.
→ When the user wants to fill forms, scrape pages, click through a UI, or share a live view — see reference/browser.md.
Sandbox
create_sandbox MCP tools for isolated code execution and web-app preview URLs. Use it instead of polluting /workspace with throwaway runtimes.
→ When running untrusted code, exotic runtimes, or previewing a dev server — see reference/sandbox.md.
File Sharing
Shared folders mounted at /mnt/afs/<name> let agents hand off files without inlining them in call_agent payloads.
→ When passing files between agents, or when a target agent should read directly from disk — see reference/file-sharing.md.
Memory
Persistent, cross-session storage mounted under /mnt/memory/<store_id>/. Workspaces opt in by attaching memory stores; when attached, the entries are listed in the platform reminder. Use ordinary file tools — there are no dedicated memory tools.
→ Before reading or writing any file under /mnt/memory/, or when deciding what to persist — see reference/memory.md for the on-disk schema (frontmatter, type, index), recall workflow, and the conventions a background consolidation pass relies on.
Skills
skill_create_draft / skill_enter_edit / skill_publish lifecycle for user-authored skills (this {{#dsh}}nap-platform{{/dsh}}{{^dsh}}__platform__{{/dsh}} skill itself is platform-managed and not user-editable).
→ When the user wants to create, edit, or publish a skill — see reference/skills.md.
Builder Mode
workspace_*_propose / _apply (and <resource>_*_propose / _apply for the prompt library) let you propose configuration changes — system prompt, schedules, slash commands, skills, model/provider, prompt library — that the user approves via an in-chat card before they apply. Read tools (list_*, get_*) are always on whenever any Builder cap is enabled.
What ships with it
7 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.
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.
- 6d ago First seen · 54 lines · 0 tokens per session scan A 189c287efd88
{{#dsh}}nap-platform{{/dsh}}{{^dsh}}__platform__{{/dsh}} is a skill published in the GitHub repository neutree-ai/agent-platform (60 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 721 tokens. 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
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
memory-bridge
Browse and compare wiki knowledge by which AI tool originally produced it. Use this skill when the user says "/memory-bridge", "browse codex memory", "what did codex know about X", "show me claude knowledge", "cross-tool memory", "what does hermes know that claude doesn't", "show me knowledge from ", "compare my AI…
serper-search
Search the public web through Serper instead of the built-in WebSearch tool. Use when an agent needs current information, general web sources, or URLs not available from local files and project APIs. SERPERAPIKEY is available in the environment.
p5.js
Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems…
browse-now
Control the user's actual browser through the browse-now CLI when a task needs authenticated pages, dynamic interaction, form filling, screenshots, or other browser automation that web search cannot reach. Prefer it whenever the task depends on the user's real browser state rather than a generic fetch.