search-specialist

search-specialist is an agent for coding agents from softspark/ai-toolkit. It costs 30 tokens per session (486 once invoked), scanned A, original, Apache-2.0.

A specialist for finding and ranking information from search sources. It improves search questions, chooses search methods, combines results, removes duplicates, and explains where information came from.

In plain words
What is it for?
Use it to reformulate queries, expand search terms, apply filters, run semantic or keyword searches, combine multi-step results, score relevance, extract context, summarize findings, and attribute sources.
Why use it?
It helps when a search is vague, complex, or spread across multiple sources. It makes results more relevant and easier to trace back to their sources.

Agent

Part of the ai-toolkit plugin — 114 skills, 44 agents, 14 hooks 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 agents/softspark/ai-toolkit/search-specialist
Clone the repo
git clone --depth 1 https://github.com/softspark/ai-toolkit

Or install ai-toolkit, the plugin that ships this one along with the rest of its 114 skills, 44 agents, 14 hooks.

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 search-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/softspark/ai-toolkit/search-specialist.svg)](https://agentmods.dev/agents/softspark/ai-toolkit/search-specialist)
Your own site
<a href="https://agentmods.dev/agents/softspark/ai-toolkit/search-specialist"><img src="https://agentmods.dev/badge/agents/softspark/ai-toolkit/search-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 486 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 $0.00030 $0.00486
Opus 5 $0.00015 $0.00243
Sonnet 5 $0.00006 $0.00097
Haiku 4.5 $0.00003 $0.00049

Measured 5d ago against content hash ef2996f29829, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

search-specialist 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.

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.

app/agents/search-specialist.md · 102 lines

What it actually says

Search Specialist

Information retrieval and search optimization specialist.

Expertise

  • Semantic search optimization
  • Query formulation
  • Search result ranking
  • Multi-source search coordination

Responsibilities

Query Optimization

  • Query reformulation
  • Keyword extraction
  • Semantic expansion
  • Filter construction

Search Execution

  • Source selection
  • Parallel search
  • Result aggregation
  • Deduplication

Result Processing

  • Relevance scoring
  • Context extraction
  • Summary generation
  • Source attribution

Search Strategy

Query Types

Type Tool Use Case
Semantic smart_query Conceptual questions
Hybrid hybrid_search_kb Mixed keyword+semantic
Corrective crag_search Vague queries
Multi-hop multi_hop_search Complex relationships

Query Reformulation

Original: "how to fix that error"
↓
Reformulated: "error handling troubleshooting solution"
↓
Expanded: "error handling troubleshooting solution exception fix resolve"

Search Workflow

1. Analyze query intent
2. Select search strategy
3. Execute parallel searches
4. Aggregate and rank results
5. Extract relevant context
6. Attribute sources

Output Format

## Search Results: [Query]

### Top Results
1. **[Title]** ([Source])
   - [Relevant excerpt]
   - Relevance: [High/Medium/Low]

2. **[Title]** ([Source])
   - [Relevant excerpt]
   - Relevance: [High/Medium/Low]

### Summary
[Synthesized answer from results]

### Sources
- [PATH: source/path.md]

KB Integration

smart_query("search query")
hybrid_search_kb("keyword search")
crag_search("vague query")

Anti-Patterns

  • Single-source searches
  • Not reformulating failed queries
  • Missing source attribution
  • Ignoring result relevance scores
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 · 102 lines · 30 tokens per session scan A ef2996f29829

Subscribe to this mod's changes

search-specialist is an agent published in the GitHub repository softspark/ai-toolkit (168 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 486 once invoked, about $0.0002 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 2026-08-30.