sandbox-doctor

sandbox-doctor is a skill for Claude Code from HomenShum/NodeBenchAI. It costs 43 tokens per session (358 once invoked), scanned A, original, MIT.

A diagnostic procedure for the NodeBench context sandbox, including its local database, search index, stored content, and configured hooks.

In plain words
What is it for?
Use it to check sandbox tables, full-text search availability, indexed chunks, sources, and hook configuration.
Why use it?
It helps identify whether the sandbox is installed, initialized, healthy, and connected to the expected session hooks.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the nodebench-mcp plugin — 2 skills, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/homenshum/nodebenchai/sandbox-doctor
Any agent
npx skills add HomenShum/NodeBenchAI --skill sandbox-doctor
Clone the repo
git clone --depth 1 https://github.com/HomenShum/NodeBenchAI

Made for: Claude Code.

Or install nodebench-mcp, the plugin that ships this one along with the rest of its 2 skills, 2 hooks.

Wrote 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.

agentmods badge for sandbox-doctor

README.md
[![agentmods](https://agentmods.dev/badge/skills/homenshum/nodebenchai/sandbox-doctor.svg)](https://agentmods.dev/skills/homenshum/nodebenchai/sandbox-doctor)
Your own site
<a href="https://agentmods.dev/skills/homenshum/nodebenchai/sandbox-doctor"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/sandbox-doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 358 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00358
Opus 5 $0.00022 $0.00179
Sonnet 5 $0.00009 $0.00072
Haiku 4.5 $0.00004 $0.00036

Measured 2d ago against content hash ec70e3943095, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sandbox-doctor 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.

packages/mcp-local/skills/sandbox-doctor/SKILL.md · 32 lines

What it actually says

Sandbox Doctor

Run diagnostics on the NodeBench context sandbox.

Instructions

  1. Call the NodeBench MCP tool sandbox_stats to check if the sandbox is initialized.
  2. Run this diagnostic shell command via Bash:
    node -e "const Database = require('better-sqlite3'); const db = new Database(require('os').homedir() + '/.nodebench/nodebench.db'); const tables = db.prepare(\"SELECT name FROM sqlite_master WHERE type='table' AND name LIKE 'sandbox%'\").all(); const fts = db.prepare(\"SELECT name FROM sqlite_master WHERE type='table' AND name='sandbox_fts'\").all(); console.log(JSON.stringify({ tables: tables.map(t=>t.name), fts5: fts.length > 0, chunks: db.prepare('SELECT COUNT(*) as c FROM sandbox_chunks').get() }, null, 2));"
    
  3. Display results as a checklist:
    ## NodeBench Sandbox Doctor
    - [x] SQLite: OK (~/.nodebench/nodebench.db)
    - [x] FTS5: Available (sandbox_fts table exists)
    - [x] Chunks indexed: N
    - [x] Sources: N
    - [x] Plugin: registered
    - [x] Hooks: PreToolUse + SessionStart configured
    
    Use [x] for PASS, [ ] for FAIL.
Changes

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.

  1. 2d ago First seen · 32 lines · 43 tokens per session scan A ec70e3943095

Subscribe to this mod's changes

sandbox-doctor is a skill published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 358 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

adk-debug

Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the adk run CLI and the adk web dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs…

google/adk-python · 191 tokens

typescript-testing

Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.

ComposioHQ/composio · 65 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

potpie-cli

Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.

potpie-ai/potpie · 50 tokens

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

trulens-diagnosis

Diagnose low evaluation scores and generate actionable improvement recommendations.

truera/trulens · 17 tokens