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 skills add jimmyken793/claude-spectator --skill sandboxed-executiongit clone --depth 1 https://github.com/jimmyken793/claude-spectatorWrote 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/skills/jimmyken793/claude-spectator/sandboxed-execution)<a href="https://agentmods.dev/skills/jimmyken793/claude-spectator/sandboxed-execution"><img src="https://agentmods.dev/badge/skills/jimmyken793/claude-spectator/sandboxed-execution/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/skills/jimmyken793/claude-spectator/sandboxed-execution"><img src="https://agentmods.dev/badge/skills/jimmyken793/claude-spectator/sandboxed-execution.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 | $0.00062 | $0.00540 |
| Opus 5 | $0.00031 | $0.00270 |
| Sonnet 5 | $0.00012 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
sandboxed-execution scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sandbox-run curl https://example.com # network denied What it actually says
Sandboxed Command Execution
When to Use
ALWAYS prefix read-only commands with sandbox-run. This is the DEFAULT for any Bash command that does not modify state:
sandbox-run <command> [args...]
The permission hook automatically rewrites this to use the plugin's own binary, so sandbox-run does not need to be on PATH.
What the Sandbox Enforces (OS-level)
- File reads: allowed (except credential paths)
- Credential reads: blocked (
~/.ssh,~/.aws,~/.gnupg,~/.kube,~/.docker, etc.) - File writes: blocked (EPERM — kernel-enforced)
- Network access: blocked
Examples
# Exploration and inspection
sandbox-run git status
sandbox-run git log --oneline -20
sandbox-run python3 -c "import os; print(os.getcwd())"
sandbox-run find . -name '*.py' -type f
sandbox-run wc -l src/**/*.ts
sandbox-run du -sh node_modules/
# These will fail inside the sandbox (as expected)
sandbox-run git commit -m "test" # EPERM — can't write .git/
sandbox-run npm install # EPERM — can't write node_modules/
sandbox-run curl https://example.com # network denied
When NOT to Use
Do not sandbox commands that need to write files or access the network:
git add,git commit,git pushnpm install,pip install,brew installmake,npm run build(if writing output files)curl,wget,npm publish
These should go through the normal permission flow.
Important Rules
sandbox-runis auto-approved — no permission prompt will appear. This is safe because the OS kernel enforces the read-only and no-network constraints regardless of what command is run inside.- Only use
sandbox-runonce, at the very start of the command. Everything after it runs inside the sandbox. Do NOT repeatsandbox-runin chained commands — writesandbox-run ls && cat file, notsandbox-run ls && sandbox-run cat file.
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.
- 10d ago First seen · 57 lines · 62 tokens per session scan A ce4acf4df631
sandboxed-execution is a skill published in the GitHub repository jimmyken793/claude-spectator (4 stars, last pushed 6mo ago), licensed MIT. It adds 62 tokens to every session and 540 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…