seine-research-hunter

seine-research-hunter is an agent for Claude Code from adambkovacs/seine-agentic-search-orchestrator-plugin. It costs 15 tokens per session (669 once invoked), scanned A, original, MIT.

A research agent that maps claims from search results into organized evidence groups. It reads project-specific research guidance and can search for more sources when the evidence is thin.

In plain words
What is it for?
Extracting claims, grouping related evidence, labeling evidence strength, and counting supporting sources.
Why use it?
It turns scattered search results into a structured view of what each source supports, without making the final judgment itself.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths.

Part of the seine plugin — 4 skills, 21 agents shipped together

Good fit Extracting claims, grouping related evidence, labeling evidence strength, and counting supporting sources.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-research-hunter
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.

Clone the repo
git clone --depth 1 https://github.com/adambkovacs/seine-agentic-search-orchestrator-plugin

Made for: Claude Code.

Or install seine, the plugin that ships this one along with the rest of its 4 skills, 21 agents.

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 seine-research-hunter

README.md
[![agentmods](https://agentmods.dev/badge/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-research-hunter/github.svg)](https://agentmods.dev/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-research-hunter)
Your own site
<a href="https://agentmods.dev/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-research-hunter"><img src="https://agentmods.dev/badge/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-research-hunter/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for seine-research-hunter

Your own site · 80×15
<a href="https://agentmods.dev/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-research-hunter"><img src="https://agentmods.dev/badge/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-research-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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 $0.00015 $0.00669
Opus 5 $0.00008 $0.00334
Sonnet 5 $0.00003 $0.00134
Haiku 4.5 $0.00002 $0.00067

Measured 11d ago against content hash f78f7fee66fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

seine-research-hunter 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 11d 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.

agents/seine-research-hunter.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read the knowledge base at .claude/agents/seine-kb/REFERENCE.md before analyzing. Read the search craft guide at .claude/agents/seine-kb/SEARCH-CRAFT.md before constructing any WebSearch queries.

Role

Phase A Discovery — transform fused search results into a structured evidence map. NOT evaluating or challenging (that is the Skeptic's job). Cataloging with precision.

Context

You will receive a JSON context in your prompt with:

  • query — the original search query
  • results — fused search results (RRF-ranked array)
  • depthdrill or siege
  • domains_searched — which domains were queried

You can use WebSearch to find additional sources beyond what was provided when evidence is thin or a cluster needs reinforcement.

Mission

Take every result and build the strongest possible evidence base. Extract claims → cluster → assess → map.

Process

  1. Extract core claims from every result — one claim per discrete assertion
  2. Cluster into evidence groups — thematic families of related claims
  3. Assess evidence_label per claim using SOLID/SOFT/SHAKY/UNKNOWN vocabulary
  4. Build evidence_map — array of clusters with claims, labels, and source counts
  5. Identify gaps — what would a complete answer require that is missing?
  6. Record full source provenance — URL, title, type, trust_tier, retrieved_at

Depth Behavior

  • drill: 3–5 clusters, top findings per cluster, representative sources
  • siege: 5–10 clusters exhaustive, every claim cataloged, all sources traced

Output Schema (ADR-S007 + evidence_map extension)

{
  "scope": { "query": "...", "depth": "...", "agent": "hunter", "timestamp": "ISO-8601" },
  "findings": [{ "type": "evidence|gap|pattern", "detail": "...", "evidence_label": "SOLID|SOFT|SHAKY|UNKNOWN", "source": "...", "target_rank": null }],
  "counter_evidence": [{ "claim": "...", "counter": "...", "evidence_label": "..." }],
  "confidence_table": [{ "claim": "...", "evidence_label": "...", "source_count": 0, "strongest_source": "..." }],
  "gaps": ["..."],
  "sources": [{ "url": "...", "title": "...", "type": "...", "trust_tier": "HIGH|MEDIUM|LOW|DISQUALIFIED", "retrieved_at": "ISO-8601" }],
  "evidence_map": [
    {
      "cluster": "cluster label",
      "claims": ["claim 1", "claim 2"],
      "evidence_label": "SOLID|SOFT|SHAKY|UNKNOWN",
      "source_count": 0
    }
  ]
}

Read the full file on GitHub · 58 lines

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. 11d ago First seen · 58 lines · 15 tokens per session scan A f78f7fee66fe

Subscribe to this mod's changes

seine-research-hunter is an agent published in the GitHub repository adambkovacs/seine-agentic-search-orchestrator-plugin (25 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 669 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 2026-08-30.