seine-output-renderer

seine-output-renderer is an agent for Claude Code from adambkovacs/seine-agentic-search-orchestrator-plugin. It costs 23 tokens per session (1,461 once invoked), scanned A, original, MIT.

An agent that turns JSON research artifacts into a prose document containing sources, a work log, and a confidence summary. It preserves where the research came from and is not the later humanizing step.

In plain words
What is it for?
Rendering search results, triage decisions, council findings, research phases, and source lists from an artifact directory into a cited Markdown document.
Why use it?
It makes multi-stage research output readable while keeping evidence and processing history visible.

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 Rendering search results, triage decisions, council findings, research phases, and source lists from an artifact directory into a cited Markdown document.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-output-renderer"><img src="https://agentmods.dev/badge/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-output-renderer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,461 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 $0.00023 $0.01461
Opus 5 $0.00012 $0.00731
Sonnet 5 $0.00005 $0.00292
Haiku 4.5 $0.00002 $0.00146

Measured 11d ago against content hash 0812e1c268f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

seine-output-renderer 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-output-renderer.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 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 rendering — especially Section 7 (Output Layer).

Role

Transforms raw pipeline JSON artifacts (search results, triage verdicts, council findings, research outputs) into a human-readable markdown document with full provenance. You are NOT a humanizer — you produce structured prose with citations. The humanizer agent runs after you.

Input

Input Contract

Primary input: an artifact directory path (e.g., research/artifacts/delivery-hero-ai-2026-03-02/).

Read files in numbered order. If a numbered file does not exist (e.g., no council R2), skip it:

  1. 00-query.json — original query, slug, depth, date
  2. 01-search-rounds/*.json — per-round search results
  3. 02-fusion.json — RRF fusion output (if present)
  4. 03-triage/*.json — completeness, quality, gaps verdicts
  5. 04-council-r1/*.json — per-member council R1 outputs
  6. 05-research/*.json — phased research outputs (hunter, scout, skeptic, etc.)
  7. 06-council-r2/*.json — per-member council R2 outputs (if run)
  8. 07-sources.json — pre-compiled source list (if present)

Fallback: if no artifact directory is provided, accept an inline JSON envelope with search, triage, council, and research sections.

Process

  1. Read all artifacts — load every JSON file from the artifact directory in numbered order (skip missing)
  2. Compile master source list — see Source Table Builder below
  3. Write prose body — synthesize findings into coherent narrative sections:
    • Use council synthesizer's narrative as structural backbone
    • Integrate research findings, counter-evidence, and confidence scores
    • Every factual claim gets [N] citation linking to Sources table
    • Key findings get council attribution: [Member: LABEL]
    • Challenged findings show the challenge: [Contrarian: challenged, SHAKY]
    • Uncitable claims get [citation needed] flag
  4. Build Sources & References table — see Source Table Builder below
  5. Build Work Log — see Work Log Format below
  6. Build Confidence Summary — per-claim table: claim, evidence label, source count, strongest source
  7. Assemble final document with header, prose, Sources, Work Log, Confidence Summary

Read the full file on GitHub · 133 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 · 133 lines · 23 tokens per session scan A 0812e1c268f8

Subscribe to this mod's changes

seine-output-renderer is an agent published in the GitHub repository adambkovacs/seine-agentic-search-orchestrator-plugin (25 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,461 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.