Portless is a local development proxy that replaces changing port numbers with stable, named .localhost URLs for running applications. People and coding agents use it to start and access local web apps through automatically assigned ports, with support for common frameworks and optional HTTPS.
Borrowing it
Nothing to install: this file belongs to vercel-labs/portless. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vercel-labs/portless/main/AGENTS.mdgit clone --depth 1 https://github.com/vercel-labs/portlessWrote 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/instructions/vercel-labs/portless/agents-md)<a href="https://agentmods.dev/instructions/vercel-labs/portless/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/portless/agents-md/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/instructions/vercel-labs/portless/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/portless/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01550 | $0.01550 |
| Opus 5.5 | $0.00620 | $0.00620 |
| Sonnet 5.5 | $0.00310 | $0.00310 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
portless AGENTS.md 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 2d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Rules
Package Manager
Use pnpm for all package management commands (not npm or yarn).
Exception: End-user install instructions should use npm install -g (global) or npm install -D (project dev dependency) since npm is universal.
Dependencies
Always check for the latest npm version when adding dependencies. Use pnpm add <package> (without version) to get the latest, or verify with npm view <package> version first.
No Emojis
Do not use emojis anywhere in this repository (code, comments, output, docs).
Dashes
Never use -- as a dash in prose, comments, or user-facing output. Use an em dash (\u2014) when a dash is needed, but prefer rephrasing to avoid dashes entirely. The only exception is CLI flags (e.g. --port).
Boolean Environment Variables
Document boolean env vars using only 0 and 1 in CLI help, SKILL.md, docs pages, and README. Code accepts true/false as well (and skip for PORTLESS), but these alternatives are not documented.
Docs Updates
When a change affects how humans or agents use portless (new/changed/removed commands, flags, behavior, or config), update all of these:
README.md(user-facing documentation)skills/portless/SKILL.md(agent skill for using portless)packages/portless/src/cli.ts(--helpoutput)packages/portless/src/mcp.ts(MCP tools andportless mcp --helpoutput)
MCP Tools
Any change to a CLI command, flag, output, or environment variable must update the MCP tools in packages/portless/src/mcp.ts in the same change. mcp.test.ts reads portless --help and each tool command's --help, and fails when a command or flag is neither handled by a tool nor listed as omitted.
Releasing
Releases are manual, single-PR affairs. The maintainer controls the changelog voice and format.
To prepare a release:
- Create a branch (e.g.
prepare-v1.2.0) - Bump the version in
packages/portless/package.json - Write the changelog entry in
CHANGELOG.md, wrapped in<!-- release:start -->and<!-- release:end -->markers - Remove the
<!-- release:start -->and<!-- release:end -->markers from the previous release entry (only the latest release should have markers) - Add a matching entry to
apps/docs/content/docs/changelog.mdx - Open a PR and merge to
main
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.
- 2d ago Changed · +5 lines · +106 tokens per session cf27f13c6694
- 1mo ago Changed · -1 tokens per session 8b8246c505b4
- 1mo ago First seen · 156 lines · 1,445 tokens per session scan A 5211786a1523
portless AGENTS.md is an instructions file published in the GitHub repository vercel-labs/portless (12,752 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,550 tokens to every session, about $0.0062 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.