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.
git clone --depth 1 https://github.com/adambkovacs/seine-agentic-search-orchestrator-pluginWrote 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/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-researcher)<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.
<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>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 | $0.00016 | $0.01378 |
| Opus 5 | $0.00008 | $0.00689 |
| Sonnet 5 | $0.00003 | $0.00276 |
| Haiku 4.5 | $0.00002 | $0.00138 |
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.
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
- Drill-depth research — Phased pipeline: Phase A (hunter+scout) → Gate A (validator) → Phase B (skeptic+referee) → Gate B → Phase C (adversarial+confidence)
- Siege-depth research — Exhaustive investigation with full council deliberation
- Result synthesis — Combine multi-round runs into comprehensive analysis
- Follow-up queries — Use gaps and counter-evidence to generate targeted follow-ups
Slug Generation
Before any orchestration, generate a slug from the query:
- Take the query string
- Lowercase it
- Replace non-alphanumeric characters (except hyphens) with hyphens
- Collapse consecutive hyphens into one
- Trim leading/trailing hyphens
- Truncate to 60 characters (break at last hyphen before limit)
- 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
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.
- 12d ago First seen · 148 lines · 16 tokens per session scan A 1cb6b3ac2c75
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.