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 instructions/sky32/mcport/agents-mdgit clone --depth 1 https://github.com/sky32/mcportWhat 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 | $0.01831 | $0.01831 |
| Opus 5 | $0.00915 | $0.00915 |
| Sonnet 5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
mcport 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCPort — Agent Guide
This repository implements a generic local Workspace MCP Runtime plus an Electron Desktop shell.
Product model
- Desktop owns Workspace registration, Runtime lifecycle (Electron
utilityProcess), Tunnel lifecycle, managed tunnel binaries (cloudflared/frpc), proxy settings, secure secrets, tray/login integration, health checks, and UI. - Runtime owns MCP transport, tools, Workspace safety, command execution, Git, project history, authentication, and SQLite runtime state.
- AI clients own reasoning and project-specific knowledge.
- Project-specific instructions and Skills live in target Workspaces, not in this server.
Invariants
- Runtime executes as the local OS user.
- File and cwd operations remain inside the selected Workspace after realpath/symlink validation.
- Commands use executable + args[] with
shell: false. - Executables are plain command names (no
/or\) and must pass Allowed Commands with exact-name matching. - The command allowlist is not an OS sandbox; child processes inherit the Runtime user's permissions.
- Single-Workspace MCP endpoints may infer Workspace; ambiguous multi-Workspace endpoints require an explicit Workspace.
- Desktop automatically manages Runtime startup and recovery; users control Tunnel exposure, not Runtime lifecycle.
- Public Workspaces share one hostname and route by
/w/<workspace>/...on the default listener's non-loopback Host path. - Public authentication is per Workspace: built-in OAuth or Bearer Token. There is no unauthenticated public access.
- Built-in OAuth uses
oidc-provider; application code supplies Workspace policy, interaction UI, persistence adapter, and MCP resource binding. - Runtime configuration belongs in SQLite; Desktop routing/preferences belong in Desktop settings; secrets use
safeStorage. - Tool tiers (
readonly/standard/full) are part of the public MCP API and must stay internally consistent withtools/listandsrc/tool-tier-smoke.ts. - Project history is model-mediated; Desktop never records chat text in the background.
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 First seen · 172 lines · 1,831 tokens per session scan A 8fe51855cac4
mcport AGENTS.md is an instructions file published in the GitHub repository sky32/mcport (3 stars, last pushed 2d ago), licensed MIT. It adds 1,831 tokens to every session, about $0.0092 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 2026-08-31.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.