rajkumar-pendyala

Sandbox Mini Harness — Development skill for Claude Code

Development community

A small agent on the Claude Agent SDK that pulls a free public source through an MCP connector you write, scores or analyzes it, drafts an output, routes it through a human-approval step, and logs the.

How to install Sandbox Mini Harness

This entry records only its repository, not the path inside it, so there is no exact command to give. Open rajkumar-pendyala/sandbox-mini-harness and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Sandbox Mini Harness does

Alternatives in Development

Codex Prompt Handgepflegte Mega Und Mini Prompts — Codex-Prompt — Handgepflegte Mega- und Mini-Prompts fuer alle Plugins 1.5k ★
Tentacle Planner — You are the Tentacle Planner — a meta-agent that analyzes this codebase and creates department tentacles to or 1.4k ★
MiniCode Architecture — 简体中文 This document describes the lightweight architecture decisions behind mini-code 388 ★

README

Sandbox mini-harness

Five things, now with step 2 split into a 2-call chain:

Pulls a free public source via an MCP connector we wrote (mcp_server.py, wraps Grants.gov's no-auth search2)
Scores/analyzes it — chain step 1, run_scoring_step()
Drafts an output — chain step 2, run_drafting_step(), fed only step 1's result, no connector needed
Routes it through a human-approval step — human_approval_step(), now also captures a named approver
Logs the run (run_log.jsonl) — one entry per chain step plus the approval decision

No debra data or assets anywhere in this repo.

Setup

pip install claude-agent-sdk mcp httpx
export ANTHROPIC_API_KEY="your-key"   # set in your shell, never in this repo

Run

python3 sandbox_agent.py

You'll see the agent search Grants.gov, then a draft printed to the terminal, then a `y/n` prompt. Nothing sends anywhere either way — it just logs your decision.