research-workflow-orchestrator

research-workflow-orchestrator is a skill for Claude Code from WenyuChiou/research-hub. It costs 48 tokens per session (1,861 once invoked), scanned A, original, MIT.

A resumable coordinator for multi-stage research projects that automates low-risk steps, records where information came from, and pauses for human decisions.

In plain words
What is it for?
It is for coordinating research across scoping, discovery, synthesis, experiments, writing, and release when an audit trail is needed.
Why use it?
It prevents important scientific choices from being made silently and lets a project continue from saved workflow state.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the research-workspace plugin — 13 skills, 1 MCP server shipped together

Good fit It is for coordinating research across scoping, discovery, synthesis, experiments, writing, and release when an audit trail is needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wenyuchiou/research-hub/research-workflow-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.

Any agent
npx skills add WenyuChiou/research-hub --skill research-workflow-orchestrator
Clone the repo
git clone --depth 1 https://github.com/WenyuChiou/research-hub

Made for: Claude Code.

Or install research-workspace, the plugin that ships this one along with the rest of its 13 skills, 1 MCP server.

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-workflow-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/wenyuchiou/research-hub/research-workflow-orchestrator/github.svg)](https://agentmods.dev/skills/wenyuchiou/research-hub/research-workflow-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/wenyuchiou/research-hub/research-workflow-orchestrator"><img src="https://agentmods.dev/badge/skills/wenyuchiou/research-hub/research-workflow-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 research-workflow-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/wenyuchiou/research-hub/research-workflow-orchestrator"><img src="https://agentmods.dev/badge/skills/wenyuchiou/research-hub/research-workflow-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,861 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 $0.00048 $0.01861
Opus 5 $0.00024 $0.00931
Sonnet 5 $0.00010 $0.00372
Haiku 4.5 $0.00005 $0.00186

Measured 7d ago against content hash 576e2aa4a7af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-workflow-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 7d 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/research-workflow-orchestrator/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

research-workflow-orchestrator

Coordinate an entire research project without turning consequential scientific decisions into silent automation. The orchestrator resumes from .research/workflow_state.yml, performs safe work automatically, and asks for one structured decision only when the next action crosses a declared gate.

This is a coordination skill, not a new research engine. It routes to the existing research-hub skills and available CLI/MCP integrations. Read references/workflow-contract.md before the first run. Read references/tool-adapters.md only for the current stage or when selecting a tool adapter. The machine-readable state contract is references/workflow-state.schema.json.

Use when

  • The user asks to run, resume, automate, or supervise a multi-stage research project.
  • Work spans at least three of topic scoping, discovery, synthesis, design, experiments, writing, and release.
  • A persistent human-in-the-loop audit trail is required.

Do not use for one isolated operation. Route a single literature table to literature-triage-matrix, one design conversation to research-design-helper, one paper summary to paper-summarize, or project orientation alone to research-project-orienter.

Required inputs

  1. Project root.
  2. User objective and constraints.
  3. Existing .research/ manifests, if present.
  4. Available tool capabilities. Discover them; never assume an MCP server, connector, credential, or browser session exists.

If the state file does not exist, propose a workflow ID and start at orient. Creating the local state file is reversible, but present the initial plan before executing later stages.

Automation policy

Classify every proposed action before invoking a tool:

Action class Default behavior
Read-only discovery, validation, comparison Run automatically
Local deterministic generation with a preview or rollback Run automatically, preserve provenance
Local reversible metadata update Run automatically when inside approved scope
External write, public communication, account change Stop at external_write
Costly or long experiment/simulation Stop at experiment_authorization
Semantic manuscript/rebuttal change Stop at semantic_revision
Submission, publication, release, merge, destructive cleanup Stop at release_authorization

Read the full file on GitHub · 185 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 185 lines · 48 tokens per session scan A 576e2aa4a7af

Subscribe to this mod's changes

research-workflow-orchestrator is a skill published in the GitHub repository WenyuChiou/research-hub (54 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,861 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

migrate-v0-to-v1

Migrate a Scraps wiki from v0 to v1. Use this whenever the user asks to upgrade Scraps, migrate v0 wiki syntax/config, convert implicit tags to explicit #[[tag]], move from scraps-writer to scraps, or audit a wiki for v1 readiness. This skill is designed for one-pass LLM-led migrations that discover the latest v0 and…

boykush/scraps · 105 tokens

remem

Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.

majiayu000/remem · 42 tokens

ingest

Create a new scrap from a source (prompt, URL, or arbitrary markdown), update cross-links in related scraps, and run a sanity check. Use this when the user wants to add a scrap, summarize an article, save synthesized content to the wiki, or file back a Q&A result.

boykush/scraps · 62 tokens

query

Answer questions about the wiki by searching, reading, and synthesizing relevant scraps with [[Title]] citations. Use this when the user wants to query the wiki, ask what they have written about a topic, compare scraps, find related notes, or pull a synthesized overview from existing scraps.

boykush/scraps · 61 tokens

planning-with-scratchpad

Use when user explicitly requests planning with a scratchpad, or asks for persistent tracking of a complex task that the human can browse visually. Backs planning files with the scratch CLI so a pad's files are registered and viewable.

NikiforovAll/scratchpad · 54 tokens

scratch

Organize knowledge from an agent session into a scratchpad — a folder of files plus a scratchpad.json manifest. Use when a task generates notes, snippets, command output, diagrams, or artifacts worth keeping together for a session/activity.

NikiforovAll/scratchpad · 49 tokens