Home / naman10parikh / agentgrid · GitHub

agent-runtime SKILL.md skillC

agent-runtime from naman10parikh/agentgrid is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add naman10parikh/agentgrid/agent-runtime@git:20260526.f887f6c

Pins git:20260526.f887f6c in mdr.lock. Pin the fingerprint instead.

Audit grade: C, 14 of 17 checks passed
Kind: SKILL.md skill
Repository: naman10parikh/agentgrid
Path: .claude/skills/agent-runtime/SKILL.md
Versions recorded: 1
Latest version: git:20260526.f887f6c, committed May 26, 2026
Size: 5,449 bytes
Repository stars: 9
License: MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Skill: Agent Runtime Adapter (~1,000 Lines)

Build the Energy agent runtime adapter wrapping Claude Agent SDK. This is the core of Phase 1.

## Architecture (From NanoClaw Study)

The adapter has TWO processes:

### 1. Host Process (~500 lines) — Orchestration

Runs on the server. Routes messages, manages sessions, spawns sandboxes.

```
src/runtime/
├── gateway.ts          # HTTP + WebSocket server, message routing
├── session-manager.ts  # Per-user session isolation, SQLite state
├── sandbox-runner.ts   # E2B sandbox spawning, volume mounts, streaming
├── ipc.ts              # File-based IPC (host ↔ sandbox), atomic writes
├── channel-router.ts   # Channel abstraction (web, WhatsApp, API)
├── task-scheduler.ts   # Cron/interval scheduled tasks (HEARTBEAT.md)
├── concurrency.ts      # Max concurrent sandboxes, per-user queuing
└── types.ts            # Shared type definitions
```

### 2. Sandbox Process (~500 lines) — Agent Intelligence

Runs inside E2B sandbox. Calls Claude Agent SDK, executes tools.

```
src/sandbox/
├── agent-loop.ts       # Claude SDK query(), MessageStream for multi-turn
├── tool-registry.ts    # Custom tools via createSdkMcpServer()
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add naman10parikh/agentgrid/agent-runtime@sha256:fb250b1a7739b8d1

The line at the top of this page pins the label git:20260526.f887f6c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_xq7v5rrsxaefcmlc.svg)](https://markdownregistry.com/a/art_xq7v5rrsxaefcmlc)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on May 26, 2026.

version	committed	commit	size	audit
git:20260526.f887f6c latest	2026-05-26	f887f6c	5,449 B	C	view

Audit of the latest version

C 14 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

fail: Frontmatter block present
fail: Frontmatter declares a name
fail: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5449 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

naman10parikh/agentgrid · 9 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_xq7v5rrsxaefcmlc
GET https://markdownregistry.com/api/v1/resolve?ref=naman10parikh/agentgrid/agent-runtime
GET https://markdownregistry.com/api/v1/blob/fb250b1a7739b8d136cb252db6bcff88fa0f40a0eaa4332fd88cecf3cdeba09a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from naman10parikh/agentgrid

frontend-design SKILL.md skill

naman10parikh/agentgrid · .claude/skills/anthropic-frontend-design/SKILL.md · Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to…