Tool Selector

Tool Selector is a skill for Claude Code from Razaib-khan/ForgeWeave. It costs 22 tokens per session (581 once invoked), scanned A, original, MIT.

A decision guide that determines which tools, APIs, MCP actions, or system capabilities a task requires.

In plain words
What is it for?
It is for selecting tools for complex tasks, checking tool availability, and defining the required configuration and permissions.
Why use it?
It prevents an agent from starting with unsuitable or missing tools and clarifies the setup needed before work begins.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions OpenCode.

Good fit It is for selecting tools for complex tasks, checking tool availability, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/razaib-khan/forgeweave/tool-selector
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 Razaib-khan/ForgeWeave --skill tool-selector
Clone the repo
git clone --depth 1 https://github.com/Razaib-khan/ForgeWeave

Made for: Claude Code.

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 Tool Selector

README.md
[![agentmods](https://agentmods.dev/badge/skills/razaib-khan/forgeweave/tool-selector.svg)](https://agentmods.dev/skills/razaib-khan/forgeweave/tool-selector)
Your own site
<a href="https://agentmods.dev/skills/razaib-khan/forgeweave/tool-selector"><img src="https://agentmods.dev/badge/skills/razaib-khan/forgeweave/tool-selector.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 581 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 $0.00022 $0.00581
Opus 5 $0.00011 $0.00291
Sonnet 5 $0.00004 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 6d ago against content hash a2dd5c98de5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Tool Selector 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/select_tools.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.

src/forgeweave/templates/claude/.claude/skills/tool-selector/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool Selector

Purpose

Analyze a task and determine the optimal set of tools, MCP actions, APIs, and system capabilities needed to complete it. Prevents using the wrong tool for the job and ensures all required capabilities are available before execution starts.

When to Use

  • Starting a complex task that may need multiple tools
  • The user asks "what tool should I use for X?"
  • A skill or agent needs to determine its tooling requirements
  • Before invoking the workflow-orchestrator to plan execution

When Not to Use

  • The tool is obvious from the task description
  • Only one tool type is relevant (e.g., always "read" for documentation)
  • The task is already executing and tools are already selected

Inputs

Input Type Required Description
task_description string Yes What needs to be done
available_tools array Yes Tools, MCP actions, and capabilities available
constraints string No Any restrictions on tool usage

Expected Outputs

Output Description
Required tools Ordered list of tools needed
Tool configuration Parameters, permissions, or setup needed per tool
Missing tools Any required capabilities not available

Exact Workflow Steps

  1. Analyze the task to determine what operations are needed (read, write, search, execute, etc.)
  2. Map each operation to the appropriate available tool
  3. Verify each selected tool has the required permissions
  4. Identify any gaps where no available tool covers a needed operation
  5. Return the tool list with ordering suggestions

Required Checks

  • Every required operation has a corresponding tool
  • Selected tools have necessary permissions
  • No tool is selected for operations it cannot perform

Failure Modes

Failure Condition Response
No tool available for a needed operation Report gap and suggest creating a new tool
Tool permissions insufficient Report what permissions need to be added
Task is too vague to analyze Ask clarifying questions

Read the full file on GitHub · 81 lines

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. 6d ago First seen · 81 lines · 22 tokens per session scan A a2dd5c98de5a

Subscribe to this mod's changes

Tool Selector is a skill published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 581 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

pr-writing-review

Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…

evalstate/fast-agent · 64 tokens

session-investigator

Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…

evalstate/fast-agent · 68 tokens

harbor-daytona

Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.

av/harbor · 67 tokens

boost-modules

Skill "boost-modules" from av/harbor, covering harbor boost custom modules, module structure, quick reference, output methods and stream text to client.

av/harbor · 0 tokens

langgraph

LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph…

yonatangross/orchestkit · 80 tokens

lc-curate-context

Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…

cyberchitta/llm-context.py · 90 tokens