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-research-hunter)<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.
<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>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 | $0.00015 | $0.00669 |
| Opus 5 | $0.00008 | $0.00334 |
| Sonnet 5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
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.
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 queryresults— fused search results (RRF-ranked array)depth—drillorsiegedomains_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
- Extract core claims from every result — one claim per discrete assertion
- Cluster into evidence groups — thematic families of related claims
- Assess evidence_label per claim using SOLID/SOFT/SHAKY/UNKNOWN vocabulary
- Build evidence_map — array of clusters with claims, labels, and source counts
- Identify gaps — what would a complete answer require that is missing?
- Record full source provenance — URL, title, type, trust_tier, retrieved_at
Depth Behavior
drill: 3–5 clusters, top findings per cluster, representative sourcessiege: 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
}
]
}
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.
- 11d ago First seen · 58 lines · 15 tokens per session scan A f78f7fee66fe
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.
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.