advanced-tool-use

advanced-tool-use is a skill for Claude Code, Codex from Hoja-Solutions/agent-stdlib. It costs 178 tokens per session (692 once invoked), scanned A, original, MIT.

Patterns for giving an AI agent access to many tools without placing every tool description in its working context at once.

In plain words
What is it for?
Use it to discover tools when needed, call several tools through code, filter results before returning them, and manage large or changing tool collections.
Why use it?
A long list of tool instructions uses space and can make the agent choose the wrong tool.

Skill for Claude CodeCodex

Part of the agent-stdlib plugin — 14 skills, 2 commands, 1 agent, 2 hooks, 2 MCP servers 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/hoja-solutions/agent-stdlib/advanced-tool-use
Any agent
npx skills add Hoja-Solutions/agent-stdlib --skill advanced-tool-use
Clone the repo
git clone --depth 1 https://github.com/Hoja-Solutions/agent-stdlib

Made for: Claude Code, Codex.

Or install agent-stdlib, the plugin that ships this one along with the rest of its 14 skills, 2 commands, 1 agent, 2 hooks, 2 MCP servers.

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 advanced-tool-use

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoja-solutions/agent-stdlib/advanced-tool-use.svg)](https://agentmods.dev/skills/hoja-solutions/agent-stdlib/advanced-tool-use)
Your own site
<a href="https://agentmods.dev/skills/hoja-solutions/agent-stdlib/advanced-tool-use"><img src="https://agentmods.dev/badge/skills/hoja-solutions/agent-stdlib/advanced-tool-use.svg" alt="Measured on agentmods" height="20"></a>
Per session 178 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 692 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 $0.00178 $0.00692
Opus 5 $0.00089 $0.00346
Sonnet 5 $0.00036 $0.00138
Haiku 4.5 $0.00018 $0.00069

Measured 3d ago against content hash 23639e178bca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

advanced-tool-use 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 3d 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.

skills/advanced-tool-use/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advanced tool use

Source: Advanced tool use on the Claude Developer Platform. Community packs cover writing one good tool; none package the patterns for reaching many tools through a few. This pack ships the runnable side under mcp-servers/tool-gateway/ (search and call) and mcp-servers/code-execution/ (tools as code); this skill is the judgment for when to reach for each.

Tool definitions are context

Loading every tool's schema up front spends tokens before the agent does any work, and a long menu makes the model choose worse. Past a couple dozen tools, the definitions crowd out the task. The three patterns below each cut a different part of that cost.

Discover tools on demand

Register one search tool in place of the full catalog. The agent describes what it needs, the search tool returns the few matching definitions, and only those enter the context. This pack's tool-gateway server does this with search_tools and call_tool over a larger catalog. Reach for it when the catalog is large or shifts between sessions.

Call tools from code

Let the model write code that invokes tools, chains several calls, and applies control flow in one block, in place of one round-trip per call. The code runs in a sandbox and returns only what the model keeps. Two wins follow: a result with ten thousand rows gets filtered to the five the model needs before any of it crosses into the context, and a five-step sequence costs one turn rather than five. This pack's code-execution server presents tools as importable functions for this pattern. It runs model-written code, so isolate it first (see sandboxing-agentic-systems).

Show a worked invocation

Add example calls to a tool's definition. A worked invocation teaches the right argument shape faster than prose, and it costs little context next to a paragraph of caveats. Use it on tools with fiddly inputs the model keeps getting wrong.

Combine them

Read the full file on GitHub · 41 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. 3d ago First seen · 41 lines · 178 tokens per session scan A 23639e178bca

Subscribe to this mod's changes

advanced-tool-use is a skill published in the GitHub repository Hoja-Solutions/agent-stdlib (1 stars, last pushed 1mo ago), licensed MIT. It adds 178 tokens to every session and 692 once invoked, about $0.0009 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

unified_meta_agent_skill

A foundational meta-agent skill for generating Multi-Agent Systems (MAS). It systematically drives the process from conceptual task decomposition to agent engineering, and finally to workflow orchestration.

linhh29/Skill_MAS · 39 tokens

controlflow-verify

Use after /controlflow-claude-code:controlflow-plan produces a plan, before implementation. Runs adversarial pre-execution verification inline in the main context (zero subagents): structural audit, assumption/mirage detection, and executability cold-start simulation. Emits APPROVED / NEEDSREVISION / REJECTED with…

Smithbox-ai/ControlFlow · 73 tokens

controlflow-planning

Use when a repository task needs a strict ControlFlow-style implementation plan before coding, especially for small, medium, or large scope, cross-file edits, risky migrations, architectural uncertainty, or any work that should produce a saved Markdown plan artifact in plans/.

Smithbox-ai/ControlFlow · 55 tokens

controlflow-router

Use when a task broadly matches ControlFlow for Codex and you need to decide whether to start with spec capture, strict workflow, strict planning, pre-execution plan review, orchestration, code review, or memory hygiene, or whether to combine several of those skills in sequence.

Smithbox-ai/ControlFlow · 60 tokens

controlflow-plan

Use when a repository task needs a high-quality ControlFlow plan before coding — small, medium, or large scope, cross-file edits, risky migrations, architectural uncertainty, or any work that should produce a saved Markdown plan artifact in plans/. Single-sources the plan format from schemas/planner.plan.schema.json…

Smithbox-ai/ControlFlow · 69 tokens

controlflow-spec

Use before planning non-trivial Codex work when the requirements, acceptance criteria, boundaries, constraints, or success measures are not yet clear enough for a safe implementation plan.

Smithbox-ai/ControlFlow · 38 tokens