agent-tool-use

agent-tool-use is a skill for Claude Code, Codex from vikasudasi/skill-vault. It costs 25 tokens per session (407 once invoked), scanned A, original, Apache-2.0.

A guide to designing AI agents that use tools to take actions. It covers small typed tool interfaces, multi-step state, structured errors, retries, planning, and checking results against what the tools actually returned.

In plain words
What is it for?
Use it when an AI agent must call APIs or other tools, coordinate several steps, handle failures, verify results, or restrict actions through clear schemas.
Why use it?
It helps prevent agents from making unsupported claims, getting stuck in loops, or failing when a tool returns an error.

Skill for Claude CodeCodex

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

Good fit Use it when an AI agent must call APIs or other tools, coordinate several steps, handle failures, verify results, or restrict actions through clear schemas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vikasudasi/skill-vault/agent-tool-use
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 vikasudasi/skill-vault --skill agent-tool-use
Clone the repo
git clone --depth 1 https://github.com/vikasudasi/skill-vault

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 agent-tool-use

README.md
[![agentmods](https://agentmods.dev/badge/skills/vikasudasi/skill-vault/agent-tool-use.svg)](https://agentmods.dev/skills/vikasudasi/skill-vault/agent-tool-use)
Your own site
<a href="https://agentmods.dev/skills/vikasudasi/skill-vault/agent-tool-use"><img src="https://agentmods.dev/badge/skills/vikasudasi/skill-vault/agent-tool-use.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 407 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00025 $0.00407
Opus 5 $0.00013 $0.00204
Sonnet 5 $0.00005 $0.00081
Haiku 4.5 $0.00003 $0.00041

Measured 7d ago against content hash c618e3f60fea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/minimal_tool_agent.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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_vault/data/skills/agent-tool-use/SKILL.md · 50 lines

What it actually says

Designing Agents that Use Tools

Use when an LLM should take actions via tools rather than just generate text.

Core loop

user -> plan -> [tool call] -> observe -> next step -> ... -> answer

Maintain an explicit state of what the agent has done and what it knows; don't let it freewheel.

Tool schema design

  • Narrow + typed tools; the schema is the contract the model reads.
  • One action per tool; compose complex behavior from small tools.
  • Return structured, machine-readable results the agent can act on (Skill Vault returns lightweight SkillCards, then a fetch tool for the body).

Error handling

Tools fail. Surface structured errors ({"error": "...", "code": "..."}) so the agent can react, retry, or report — never let a raised exception end the whole turn without a path forward. Add retry limits to prevent infinite loops.

Grounding

The agent's tool results are its ground truth — never let it assert a result it didn't observe. When a skill/registry returns content, have it verify integrity before trusting (Skill Vault's verify_skill + content hashes).

Pitfalls

  • Broad "do everything" tools encourage sloppy calls — split them.
  • Guard against loops: cap tool calls per turn, require progress each step.
  • Validate tool arguments before execution, not just after.
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 50 lines · 25 tokens per session scan A c618e3f60fea

Subscribe to this mod's changes

agent-tool-use is a skill published in the GitHub repository vikasudasi/skill-vault (0 stars, last pushed 22d ago), licensed Apache-2.0. It adds 25 tokens to every session and 407 once invoked, about $0.0001 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

drug-design

End-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.

synthetic-sciences/openscience · 44 tokens

llm-integration

LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.

yonatangross/orchestkit · 58 tokens

agent-engineering-expert

Build LLM agents that use tools safely: tool design, the agent loop, memory, MCP servers, multi-agent orchestration, sandboxing and prompt-injection defence. Use when the user mentions AI agents, tool use or function calling, MCP or Model Context Protocol, autonomous workflows, multi-agent systems, LangChain or…

personamanagmentlayer/pcl · 94 tokens

continual-learning

Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…

langchain-ai/open-swe · 89 tokens

nano-banana-pro-openrouter

Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.

opensquilla/opensquilla · 49 tokens

skill-creator-linter

Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.

opensquilla/opensquilla · 84 tokens