sandbox-environment

sandbox-environment is a skill for Claude Code, Codex from pssah4/vault-operator. It costs 17 tokens per session (2,141 once invoked), scanned A, original, Apache-2.0.

A reference for a sandbox environment, including APIs for reading and writing files and making limited HTTPS requests.

In plain words
What is it for?
Use it when building or evaluating code that accesses vault files, downloads approved resources, or works with binary data.
Why use it?
It shows which operations are available and what restrictions apply, so code can be written for the actual environment.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when building or evaluating code that accesses vault files, downloads…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pssah4/vault-operator/sandbox-environment
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.

Any agent
npx skills add pssah4/vault-operator --skill sandbox-environment
Clone the repo
git clone --depth 1 https://github.com/pssah4/vault-operator

Made for: Claude Code, Codex.

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-environment

README.md
[![agentmods](https://agentmods.dev/badge/skills/pssah4/vault-operator/sandbox-environment.svg)](https://agentmods.dev/skills/pssah4/vault-operator/sandbox-environment)
Your own site
<a href="https://agentmods.dev/skills/pssah4/vault-operator/sandbox-environment"><img src="https://agentmods.dev/badge/skills/pssah4/vault-operator/sandbox-environment.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,141 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00017 $0.02141
Opus 5 $0.00009 $0.01071
Sonnet 5 $0.00003 $0.00428
Haiku 4.5 $0.00002 $0.00214

Measured 7d ago against content hash 98d583ff3121, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sandbox-environment scanned grade A with 2 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 7d 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.

- `fetch(url)` -- fetch not available. Use ctx.requestUrl

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

Buffer (Node.js), require(), dynamic import(), process, fs, path, __dirname, __filename, child_process, WebAssembly, eval(), new Function()
bundled-skills/sandbox-environment/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandbox Environment Reference

Available APIs

ctx.vault

  • ctx.vault.read(path: string): Promise<string> -- Read text file
  • ctx.vault.readBinary(path: string): Promise<ArrayBuffer> -- Read binary file
  • ctx.vault.write(path: string, content: string): Promise<void> -- Write text (max 10MB, no writes to .obsidian/)
  • ctx.vault.writeBinary(path: string, content: ArrayBuffer): Promise<void> -- Write binary (max 10MB)
  • ctx.vault.list(path: string): Promise<string[]> -- List folder contents

ctx.requestUrl

  • ctx.requestUrl(url: string, options?: {method?: string, body?: string}): Promise<{status: number, text: string}>
  • HTTPS only. Allowed domains: esm.sh, cdn.jsdelivr.net, unpkg.com, registry.npmjs.org
  • Rate limit: 5 requests/minute

Standard Globals

Promise, JSON, Math, Date, Object (full), Array, Map, Set, RegExp, Number, String, Boolean, Symbol, setTimeout, clearTimeout, TextEncoder, TextDecoder, parseInt, parseFloat, isNaN, isFinite, encodeURIComponent, decodeURIComponent, Error, TypeError, RangeError

TypedArrays (for binary data)

Uint8Array, Int8Array, Uint16Array, Int16Array, Uint32Array, Int32Array, Float32Array, Float64Array, ArrayBuffer, DataView

NOT Available (will cause errors)

Buffer (Node.js), require(), dynamic import(), process, fs, path, __dirname, __filename, child_process, WebAssembly, eval(), new Function()

require, import(), process, globalThis, eval, new Function and WebAssembly are not merely absent: the AstValidator rejects the script BEFORE it compiles if the source so much as contains them, and its comment stripper deliberately keeps string literals. A script that searches for these tokens must therefore assemble them at runtime ('pro' + 'cess'), or it rejects itself. new RegExp is allowed.

The one rule that has no error message

A skill script is a single, self-contained file. No import, no require.

A static import x from './y.js' passes every check: the AstValidator only blocks require( and import(, and the repo has no other gate. But esbuild.transform (no bundling) rewrites it to require(), and there is no require here. The script dies on the user's first call, with an error that names none of this. Put everything in one file.

Read the full file on GitHub · 137 lines

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. 7d ago First seen · 137 lines · 17 tokens per session scan A 98d583ff3121

Subscribe to this mod's changes

sandbox-environment is a skill published in the GitHub repository pssah4/vault-operator (249 stars, last pushed 6d ago), licensed Apache-2.0. It adds 17 tokens to every session and 2,141 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

obsidian-bases

Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.

AgriciDaniel/claude-obsidian · 69 tokens

save

Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…

AgriciDaniel/claude-obsidian · 80 tokens

wiki-fold

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…

AgriciDaniel/claude-obsidian · 76 tokens

wiki-mode

Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…

AgriciDaniel/claude-obsidian · 83 tokens

wiki-cli

Detect and use the official Obsidian command-line interface for read-only vault access; use for wiki-cli, Obsidian CLI, Obsidian read, Obsidian search, vault transport, which transport, transport detection, backlinks, tags, or Obsidian command line. Mutations always go through the claude-obsidian transaction core.

AgriciDaniel/claude-obsidian · 74 tokens