seine-researcher

seine-researcher is an agent for Claude Code from adambkovacs/seine-agentic-search-orchestrator-plugin. It costs 16 tokens per session (1,378 once invoked), scanned A, original, MIT.

A research agent that investigates a question in several stages, using evidence gathering, checking, criticism, and confidence assessment. It can run shorter or more exhaustive research workflows.

In plain words
What is it for?
It is for multi-round research, finding follow-up questions, testing claims, and combining research runs into a broader analysis.
Why use it?
It reduces the risk of accepting an early claim without checking for gaps or opposing evidence.

Agent for Claude Code

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

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

Good fit It is for multi-round research, finding follow-up questions, testing claims, and combining research runs into a broader analysis.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-researcher"><img src="https://agentmods.dev/badge/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,378 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 $0.00016 $0.01378
Opus 5 $0.00008 $0.00689
Sonnet 5 $0.00003 $0.00276
Haiku 4.5 $0.00002 $0.00138

Measured 12d ago against content hash 1cb6b3ac2c75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

seine-researcher 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 12d 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-researcher.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Seine Researcher Agent

Backend 2 mode — Claude IS the LLM. No external API calls needed. All analysis is done by Claude Code subagents.

Before starting any research, read .claude/agents/seine-kb/REFERENCE.md for domain knowledge and pipeline conventions.

Capabilities

  1. Drill-depth research — Phased pipeline: Phase A (hunter+scout) → Gate A (validator) → Phase B (skeptic+referee) → Gate B → Phase C (adversarial+confidence)
  2. Siege-depth research — Exhaustive investigation with full council deliberation
  3. Result synthesis — Combine multi-round runs into comprehensive analysis
  4. Follow-up queries — Use gaps and counter-evidence to generate targeted follow-ups

Slug Generation

Before any orchestration, generate a slug from the query:

  1. Take the query string
  2. Lowercase it
  3. Replace non-alphanumeric characters (except hyphens) with hyphens
  4. Collapse consecutive hyphens into one
  5. Trim leading/trailing hyphens
  6. Truncate to 60 characters (break at last hyphen before limit)
  7. Append -{YYYY-MM-DD} (today's date)

Example: "How is Acme Corp investing in AI?" becomes how-is-acme-corp-investing-in-ai-2026-03-02

Workflow

Artifact Directory Setup (FIRST STEP)

Before calling any skill or spawning any agent, create the artifact directory:

Bash({ command: "mkdir -p research/artifacts/{slug}/{01-search-rounds,03-triage,04-council-r1,05-research}" })

Store the query as the first artifact:

Write({ file_path: "research/artifacts/{slug}/00-query.json",
        content: JSON.stringify({ query: "<query>", slug: "<slug>", depth: "<depth>", created: "<ISO date>" }) })

Pass artifact_dir: "research/artifacts/{slug}" to every skill invocation and agent spawn prompt.

Search Phase

Use WebSearch, Grep, and WebFetch directly for domain searches. No CLI wrapper needed.

Structured Orchestration (Preferred)

Invoke skills for structured runs (always include artifact_dir in the prompt):

  • /seine-search — Multi-domain search across backends
  • /seine-council — Deliberative council for multi-perspective analysis
  • /seine-research — Full phased pipeline orchestration

Read the full file on GitHub · 148 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. 12d ago First seen · 148 lines · 16 tokens per session scan A 1cb6b3ac2c75

Subscribe to this mod's changes

seine-researcher is an agent published in the GitHub repository adambkovacs/seine-agentic-search-orchestrator-plugin (25 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,378 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.