Single Search

Single Search is a skill for Claude Code from Razaib-khan/ForgeWeave. It costs 90 tokens per session (867 once invoked), scanned A, original, MIT.

A lightweight research workflow that searches a small number of authoritative web pages for a focused answer.

In plain words
What is it for?
It is for checking API signatures, verifying software versions and features, finding code examples, and investigating error messages.
Why use it?
It fills in missing technical context before an agent writes code or relies on an uncertain API, library version, command-line option, or configuration setting.

Skill for Claude Code

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

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/razaib-khan/forgeweave/quick-research
Any agent
npx skills add Razaib-khan/ForgeWeave --skill quick-research
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 Single Search

README.md
[![agentmods](https://agentmods.dev/badge/skills/razaib-khan/forgeweave/quick-research.svg)](https://agentmods.dev/skills/razaib-khan/forgeweave/quick-research)
Your own site
<a href="https://agentmods.dev/skills/razaib-khan/forgeweave/quick-research"><img src="https://agentmods.dev/badge/skills/razaib-khan/forgeweave/quick-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 867 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 5.1 $0.00090 $0.00867
Opus 5 $0.00045 $0.00434
Sonnet 5 $0.00018 $0.00173
Haiku 4.5 $0.00009 $0.00087

Measured 5d ago against content hash c28dddadbe6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Single Search 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch_and_extract.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/quick-research/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Get fast, focused answers by crawling a small set of authoritative URLs and extracting the relevant information. No multi-agent pipeline, no planning phase, no validation stage. This is the default research mode — use it whenever you lack context about any technology.

When to Use (Auto-Detect)

Always call websearch or load this skill when:

  • You are about to write code using an API/library you're not 100% confident about
  • You encounter an unfamiliar function signature, parameter, or return type
  • You need to verify a library version, feature availability, or deprecation status
  • You need a quick code example for a specific API method
  • You encounter an error and need to look up the error message or fix
  • You need to confirm a configuration option, CLI flag, or environment variable
  • The question can be answered from 1-3 sources
  • You are short on context for any technology usage — stop and search before coding

When NOT to Use

  • The topic requires comparing multiple sources or perspectives — use deep-research
  • You need to understand a new framework from scratch (3+ subtopics) — use deep-research
  • The question is about code in the current project — answer directly from the codebase
  • The user explicitly asked for "deep research" or "comprehensive report"
  • The project will need this knowledge repeatedly — research and convert to skill

Inputs

Input Type Required Description
query string Yes The specific question to answer
seed_urls array of string No Suggested URLs to check (auto-discovered if omitted)

Expected Outputs

A concise answer with:

  • Direct answer to the question
  • 1-3 code examples if applicable
  • Source URLs for each claim

Exact Workflow Steps

  1. Determine 1-3 authoritative URLs (official docs, API refs)
  2. Fetch them using webfetch
  3. For JS-rendered pages or incomplete responses, use Playwright MCP tools:
    • browser_navigate to load the page
    • browser_snapshot to extract structured content via element refs
  4. Extract the specific information requested
  5. Return a concise answer with sources

Read the full file on GitHub · 100 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. 5d ago First seen · 100 lines · 90 tokens per session scan A c28dddadbe6b

Subscribe to this mod's changes

Single Search is a skill published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 867 once invoked, about $0.0005 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

web-search-tool

Web search tool. Queries the public internet via the Brave Search API. Use when: researching current events, finding documentation, fact-checking, or fetching ranked search results.

xuiltul/animaworks · 38 tokens

x-search-tool

X (Twitter) search tool for keyword search and fetching tweets from a specified account. Use when: searching X for topics, reading a user timeline, or tracking trends and posts.

xuiltul/animaworks · 40 tokens

openacme-platform

How OpenAcme is laid out — data dir, agents, skills, MCP servers, tasks, memory, the peer-notes convention. Read this when the user asks you to manage their workforce, set up an agent, install a skill, configure an MCP server, or explain how the platform works.

sandydasari/openacme · 66 tokens

Web Search

Keeps lightweight public-web discovery available for prompts, scheduled jobs, and follow-up research.

agentic-in/elephant-agent · 21 tokens

knowledge-discovery

Discover relevant skills and knowledge using tiered approach. SKIP for simple tasks, QUICK for single-skill, STANDARD for multi-skill, DEEP for full feature implementation. Auto-selects tier based on task complexity.

thapaliyabikendra/ai-artifacts · 48 tokens

pilot-service-agents-reference

Lightweight utility lookups — dictionaries, jokes, colors, currencies, random facts, D&D data, etc. Use this skill when: 1. Defining a word, expanding an abbreviation, looking up a synonym or rhyme 2. Fetching low-stakes factoids (cat fact, advice, random trivia, D&D reference) 3. Currency codes and latest/historical…

TeoSlayer/pilot-skills · 149 tokens