toolbox

toolbox is a skill for Claude Code, Codex from psyd3x/d3x-san. It costs 43 tokens per session (1,567 once invoked), scanned A, original, MIT.

An on-demand loader that reads a catalog of available tools and loads only the tool context needed for the current task.

In plain words
What is it for?
Use it before or during a plan to scan for required tools, load a selected tool, or check which tools are already loaded.
Why use it?
It reduces unnecessary context and helps choose between tools that serve the same category, while avoiding tools marked for manual selection.

Skill for Claude CodeCodex

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/psyd3x/d3x-san/skill
Any agent
npx skills add psyd3x/d3x-san --skill skill
Clone the repo
git clone --depth 1 https://github.com/psyd3x/d3x-san

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 toolbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/psyd3x/d3x-san/skill.svg)](https://agentmods.dev/skills/psyd3x/d3x-san/skill)
Your own site
<a href="https://agentmods.dev/skills/psyd3x/d3x-san/skill"><img src="https://agentmods.dev/badge/skills/psyd3x/d3x-san/skill.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 1,567 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 $0.00043 $0.01567
Opus 5 $0.00022 $0.00783
Sonnet 5 $0.00009 $0.00313
Haiku 4.5 $0.00004 $0.00157

Measured 5d ago against content hash 1984fc9a3afe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toolbox 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 5d 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.

skill/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Toolbox Loader

On-demand tool loader for your toolbox. Reads ~/.claude/toolbox.yml catalog, enforces one-tool-per-category gates, and loads tool context only when needed.

Modes

/toolbox scan — Plan-Aware Loading

Use BEFORE executing a plan. Scans plan steps for tool needs.

  1. Read the current plan file (from ~/.claude/plans/ or as specified)
  2. Read ~/.claude/toolbox.yml
  3. For each category, check if any plan step text matches that category's keywords
  4. Collect all matched categories
  5. For each matched category:
    • If user_gated: trueskip entirely (never auto-suggest)
    • If pick_one: false (single tool) → auto-load it
    • If pick_one: true (multiple tools) → present choice to user:
      • List all tools in the category with their why field
      • Mark the highest-weight tool as (Recommended)
      • Use AskUserQuestion with the tools as options
      • Wait for user's choice
  6. Load each selected tool (see Loading Protocol below)
  7. Update state file (see State Protocol below)
  8. Report: "Loaded N tools across M categories. Ready to execute."

/toolbox load <target> — Reactive Loading

Use during execution when a task needs a tool not yet loaded.

<target> can be a category name OR a specific tool name.

  1. Read ~/.claude/toolbox.yml
  2. Read state file /tmp/.toolbox-session
  3. Resolve target:
    • If target is a tool name → find its category
    • If target is a category name → use category
  4. Check state file:
    • If category already loaded → report which tool is active, use it. Do NOT re-ask.
    • If category not loaded → proceed to selection
  5. Selection:
    • If user_gated: true → only proceed if user explicitly requested this tool
    • If pick_one: false → auto-load the single tool
    • If pick_one: true → present choice with AskUserQuestion (same as scan mode)
  6. Load selected tool (see Loading Protocol below)
  7. Update state file

/toolbox status — Check What's Loaded

  1. Read /tmp/.toolbox-session
  2. If file doesn't exist or is empty → report "No tools loaded this session"
  3. Otherwise → list each loaded category and tool name

Read the full file on GitHub · 162 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. 5d ago First seen · 162 lines · 0 tokens per session scan A 1984fc9a3afe

Subscribe to this mod's changes

toolbox is a skill published in the GitHub repository psyd3x/d3x-san (5 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,567 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens