p1-research-orchestrator

p1-research-orchestrator is an agent for Claude Code from babyworm/rtl-agent-team. It costs 50 tokens per session (7,534 once invoked), scanned A, original, MIT.

An orchestrator for the first research phase of a project. It refines the specification, explores possible solutions, coordinates experts, runs three review rounds, and creates structured research files.

In plain words
What is it for?
Use it to clarify requirements, investigate solution paths, coordinate domain experts, review findings, and generate research artifacts.
Why use it?
It organizes a broad research task so important options and specialist views are less likely to be missed. It also turns the research into defined outputs for later work.

Agent for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: model in frontmatter; names the AskUserQuestion tool; mentions Codex.

Part of the rtl-agent-team plugin — 47 skills, 99 agents, 6 hooks shipped together

Good fit Use it to clarify requirements, investigate solution paths, coordinate domain experts, review findings, and generate research artifacts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/babyworm/rtl-agent-team/p1-research-orchestrator
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/babyworm/rtl-agent-team

Made for: Claude Code.

Or install rtl-agent-team, the plugin that ships this one along with the rest of its 47 skills, 99 agents, 6 hooks.

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 p1-research-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p1-research-orchestrator/github.svg)](https://agentmods.dev/agents/babyworm/rtl-agent-team/p1-research-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/p1-research-orchestrator"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p1-research-orchestrator/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 p1-research-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/p1-research-orchestrator"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p1-research-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,534 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 $0.00050 $0.07534
Opus 5 $0.00025 $0.03767
Sonnet 5 $0.00010 $0.01507
Haiku 4.5 $0.00005 $0.00753

Measured 10d ago against content hash 58d770cb8348, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

p1-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 10d 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/p1-research-orchestrator.md · 494 lines

How it starts

The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAT audit protocol (condensed; dev source: plugin_docs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime):

  • Tag key moments [RAT: CATEGORY | SOURCE] description — categories: THOUGHT, DECISION (source label MANDATORY), INSIGHT, DELEGATE (name the target agent), WARNING (specific, actionable).
  • DECISION source labels: USER_CONFIRMED | SPEC_DERIVED (cite section) | AGENT_ASSUMED (brief justification required). Tag natural decision points only — do not over-annotate routine operations.
  • Prompt self-report: on spawn, save your received task description to .rat/audit/{session_id}/prompts/{NNN}_{agent-name}.md ({session_id} from .rat/audit/session-id.txt); skip silently if the audit dir is absent.
  • Path convention: {plugin_root} in any path = plugin installation root, read from .rat/state/spawn-context.json field plugin_root; if unavailable, try the project-local path, else proceed without the file. Resolve project-relative paths against PROJECT_ROOT=<abs> (prompt) > spawn-context project_root > $RAT_PROJECT_ROOT env > CWD.

You are the Phase 1 Research Orchestrator. You drive the complete spec research pipeline from raw specification to structured requirements and algorithm candidate survey.

Your job is to CLARIFY specs (AskUserQuestion), ACQUIRE domain knowledge (domain-consult), EXPLORE solution paths (parallel agents), COORDINATE expert review (3-round chief), and PRODUCE artifacts. You do NOT make algorithm selections — you present candidates with trade-offs for the user to decide.

The p1-spec-research-policy skill (loaded via skills: field) defines all quality criteria, review protocols, naming conventions, and checklists. Reference it for pass/fail decisions.

Workflow

Step 0a — Goal Clarifier Trigger

Before invoking spec-analyst, decide whether to run goal-clarifier first.

Heuristic (must match the Python reference in tests/unit/test_p1_goal_clarifier_assets.py::needs_clarifier):

Let a = $ARGUMENTS.strip().

Read the full file on GitHub · 494 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. 10d ago First seen · 494 lines · 50 tokens per session scan A 58d770cb8348

Subscribe to this mod's changes

p1-research-orchestrator is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 17d ago), licensed MIT. It adds 50 tokens to every session and 7,534 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

ruby-developer

Implementación de código Ruby on Rails siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en Rails (controllers, models, migrations, services), se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere una Spec SDD aprobada antes de empezar.

gonzalezpazmonica/savia · 73 tokens

completeness-judge

Truth Tribunal judge — report covers what its title/abstract promises.

gonzalezpazmonica/savia · 18 tokens

security-attacker

Agente Red Team que simula ataques contra el código y la configuración del proyecto. Busca vulnerabilidades, misconfiguraciones, dependencias inseguras, inyecciones, exposición de datos y vectores de ataque comunes (OWASP Top 10, CWE Top 25).

gonzalezpazmonica/savia · 60 tokens

expert

Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner →…

chrono-meta/forge-harness · 114 tokens

hub-persona-auditor

Use when an external-facing draft (briefing, card, guide) is ready for pre-publication audit. Returns 3+ persona reader simulation, 4-axis (resonance/confusion/resistance/supplement) review, and 3-tier revision proposals (mandatory/strong/recommended). Do not use for internal memos, CATALOG entries, memory files, code…

chrono-meta/forge-harness · 89 tokens

architect

A system-architecture agent that maps how a software project should be structured. It creates a simple first design and a more detailed version, including the main bottleneck—the part most likely to limit the system.

andrewcigan/vibe-dev-plugin · 59 tokens