seine-research

seine-research is a skill for Claude Code from adambkovacs/seine-agentic-search-orchestrator-plugin. It costs 20 tokens per session (2,782 once invoked), scanned A, original, MIT.

A multi-stage research workflow that gathers evidence, checks claims, resolves disagreements, and combines findings. It uses different research depths and labels confidence in the evidence.

In plain words
What is it for?
Use it for discovery, source checking, claim challenges, conflict resolution, red-team review, and calibrated confidence scoring.
Why use it?
It helps make complex research more systematic and shows when conclusions are well supported or uncertain.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

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

Good fit Use it for discovery, source checking, claim challenges, conflict resolution, red-team review, and calibrated confidence scoring.

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

Any agent
npx skills add adambkovacs/seine-agentic-search-orchestrator-plugin --skill seine-research
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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-research"><img src="https://agentmods.dev/badge/skills/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,782 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00020 $0.02782
Opus 5 $0.00010 $0.01391
Sonnet 5 $0.00004 $0.00556
Haiku 4.5 $0.00002 $0.00278

Measured 12d ago against content hash 05e4756ada9a, 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 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.

skills/seine-research/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Seine Research (Backend 2)

Phased research pipeline using Claude Code's native Agent tool. Requires drill or siege depth. Read agents/seine-kb/REFERENCE.md for schemas, ADR rules, and depth behavior.

Evidence Vocabulary

Label Meaning Numeric
SOLID Multiple independent sources, no contradictions 1.0
SOFT Single credible source or indirect evidence 0.6
SHAKY Single biased source or conflicting evidence 0.3
UNKNOWN Insufficient evidence 0.0

Model Selection

Depth Model
drill sonnet
siege opus

Pipeline

Phase A (Discovery)    hunter + scout        → Evidence map + adjacent signals
    ↓ Gate A           validator             → PASS / PASS_WITH_NOTES / FAIL
Phase B (Analysis)     skeptic + referee     → Claim challenges + conflict resolution
    ↓ Gate B           validator             → PASS / PASS_WITH_NOTES / FAIL
Phase C (Synthesis)    adversarial-reviewer  → Red-team analysis
                       confidence-quantifier → Calibrated confidence scores

Gate failure stops the pipeline immediately (ADR-S009). Partial results returned with stopped_at field.


Step 1 — Phase A: Discovery (parallel)

Spawn hunter and scout simultaneously in a single message:

Agent({ subagent_type: "seine-research-hunter", model: "<drill=sonnet|siege=opus>",
        prompt: "Query: <query>\nPrior results: <search_results_json>\nTask: Build evidence map and confidence table." })
Agent({ subagent_type: "seine-research-scout",  model: "<drill=sonnet|siege=opus>",
        prompt: "Query: <query>\nPrior results: <search_results_json>\nTask: Find adjacent signals, weak signals, and timing triggers." })

Both must output the Research Agent Schema (KB Section 3): 6 required blocks — scope, findings, counter_evidence, confidence_table, gaps, sources (ADR-S007).

Step 2 — Gate A

Spawn validator with Phase A combined outputs:

Agent({ subagent_type: "seine-research-validator", model: "sonnet",
        prompt: "Query: <query>\nPhase A outputs: <hunter_json + scout_json>\nTask: Schema check + confidence assessment. Return PASS, PASS_WITH_NOTES, or FAIL." })

Read the full file on GitHub · 252 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 · 252 lines · 20 tokens per session scan A 05e4756ada9a

Subscribe to this mod's changes

seine-research is a skill published in the GitHub repository adambkovacs/seine-agentic-search-orchestrator-plugin (25 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 2,782 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens