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.
npx skills add Razaib-khan/ForgeWeave --skill tool-selectorgit clone --depth 1 https://github.com/Razaib-khan/ForgeWeaveWrote 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.
[](https://agentmods.dev/skills/razaib-khan/forgeweave/tool-selector)<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>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.
| Model | Per session | Once 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 |
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.
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.
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
- Analyze the task to determine what operations are needed (read, write, search, execute, etc.)
- Map each operation to the appropriate available tool
- Verify each selected tool has the required permissions
- Identify any gaps where no available tool covers a needed operation
- 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 |
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.
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.
- 6d ago First seen · 81 lines · 22 tokens per session scan A a2dd5c98de5a
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.
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…
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…
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.
boost-modules
Skill "boost-modules" from av/harbor, covering harbor boost custom modules, module structure, quick reference, output methods and stream text to client.
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…
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…