research-orchestrator

research-orchestrator is an agent for coding agents from zircote-plugins/sigint. It costs 66 tokens per session (15,001 once invoked), scanned A, original, MIT.

An orchestration agent for structured intelligence research sessions. It manages research phases, specialist agents, reviews, finding consolidation, progress tracking, and cleanup.

In plain words
What is it for?
Use it to run research sessions, assign analysis across dimensions, verify methods, merge findings, detect changes, and manage the research team lifecycle.
Why use it?
It coordinates a multi-stage research process so work from different analysts is checked, combined, and tracked consistently.

Agent

Part of the sigint plugin — 16 skills, 9 commands, 6 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/zircote-plugins/sigint/research-orchestrator
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/sigint

Or install sigint, the plugin that ships this one along with the rest of its 16 skills, 9 commands, 6 agents, 1 hook.

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 research-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/zircote-plugins/sigint/research-orchestrator.svg)](https://agentmods.dev/agents/zircote-plugins/sigint/research-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/zircote-plugins/sigint/research-orchestrator"><img src="https://agentmods.dev/badge/agents/zircote-plugins/sigint/research-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 15,001 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.15001
Opus 5 $0.00033 $0.07501
Sonnet 5 $0.00013 $0.03000
Haiku 4.5 $0.00007 $0.01500

Measured 4d ago against content hash 87ac38e844ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-orchestrator 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 4d 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/research-orchestrator.md · 1,414 lines

How it starts

The opening of the file, as written. The whole thing — 1,414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Orchestrator Agent

You are the orchestrator for sigint research sessions. You manage the full lifecycle of a research session — from team creation through finding merge to cleanup — following the Anthropic long-running agent harness pattern.

Structured Data Protocol: All JSON file operations (creation, mutation, extraction) MUST follow protocols/STRUCTURED-DATA.md. Use jq via Bash for all JSON file I/O. Every write or mutation MUST be followed by schema validation using the corresponding schemas/*.jq file — if validation fails, diagnose, correct with jq, and re-validate (max 2 retries) before proceeding. See the Retry-and-Correct protocol in protocols/STRUCTURED-DATA.md. Read is acceptable for comprehension-only reads.

You are spawned by skills (start, update, augment) with a mode-specific prompt. Your responsibilities:

  1. Team lifecycle: Create team, spawn dimension-analysts, coordinate via SendMessage, shut down
  2. Progress tracking: Write research-progress.md on every phase transition
  3. Codex review gates: Spawn codex review agents at pipeline boundaries, quarantine failures
  4. Finding merge: Consolidate dimension findings, detect conflicts, update state
  5. Delta detection: Compare new findings against prior state (update mode)
  6. Provenance enforcement: Ensure every finding carries a provenance record

Orchestration Modes

You receive one of these modes in your spawn prompt:

Mode Spawned By Behavior
full /sigint:start Full session: elicitation → spawn all dimensions → merge → cleanup
update /sigint:update Load prior state → spawn specified dimensions → delta detection → merge
augment /sigint:augment Spawn single dimension-analyst → merge into existing state

Phase 0: Initialize Team and Directory

Step 0.1: Create Team

TeamCreate(team_name: "sigint-{topic_slug}-research")

If TeamCreate fails, retry once. If it fails again, report the error and stop.

Read the full file on GitHub · 1,414 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. 4d ago First seen · 1,414 lines · 66 tokens per session scan A 87ac38e844ab

Subscribe to this mod's changes

research-orchestrator is an agent published in the GitHub repository zircote-plugins/sigint (20 stars, last pushed 17d ago), licensed MIT. It adds 66 tokens to every session and 15,001 once invoked, about $0.0003 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 agents, from other repositories

competitor-scout

Amnesiac single-competitor intelligence gatherer. Researches exactly one competitor with BrightData and returns one cited JSON dossier. Use one scout per competitor, fanned out in parallel during /radar. Reports back only; never talks to other scouts.

sabahudin-web/competitive-intelligence-radar · 57 tokens

devils-advocate

Strategic analyst teammate for /radar-council. Owns the skeptic lens. Its job is to disprove the other analysts' recommendations, expose unsupported claims, and stop the team from anchoring on the first plausible story. Spawned as an agent-team teammate, not a plain subagent.

sabahudin-web/competitive-intelligence-radar · 67 tokens

pricing-analyst

Strategic analyst teammate for /radar-council. Owns the pricing and packaging lens. Reads the latest briefing and dossiers, argues where the business is exposed or advantaged on price, and challenges the other analysts. Spawned as an agent-team teammate, not a plain subagent.

sabahudin-web/competitive-intelligence-radar · 64 tokens

product-gap-analyst

Strategic analyst teammate for /radar-council. Owns the product and positioning gap lens. Reads the latest briefing and dossiers, finds where rivals are pulling ahead or leaving openings, and challenges the other analysts. Spawned as an agent-team teammate, not a plain subagent.

sabahudin-web/competitive-intelligence-radar · 64 tokens

threat-sentiment-analyst

Strategic analyst teammate for /radar-council. Owns the threat and market-sentiment lens. Reads the latest briefing and dossiers, ranks which rival is the rising danger and reads the mood of the market, and challenges the other analysts. Spawned as an agent-team teammate, not a plain subagent.

sabahudin-web/competitive-intelligence-radar · 74 tokens

catalog

You are writing search queries that will find everyone competing with ONE product.

mo-root/open-kb · 0 tokens