orchestrate

orchestrate is a command for Claude Code from ngtiendong/Academic-Research-Agent-Skill. It costs 0 tokens per session (273 once invoked), scanned A, original, MIT.

A research workflow coordinator that examines the project's current stage, evidence, missing documents, and decision gates.

In plain words
What is it for?
Use it to recommend the next appropriate command, define the permitted scope, identify prohibited work, and list only the documents needed now.
Why use it?
It prevents work from advancing beyond what the available evidence authorises and highlights decisions that require the researcher.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to recommend the next appropriate command, define the permitted scope, identify prohibited work, and list only the documents needed now.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ngtiendong/academic-research-agent-skill/orchestrate
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/ngtiendong/Academic-Research-Agent-Skill

Made for: Claude Code.

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 orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/commands/ngtiendong/academic-research-agent-skill/orchestrate/github.svg)](https://agentmods.dev/commands/ngtiendong/academic-research-agent-skill/orchestrate)
Your own site
<a href="https://agentmods.dev/commands/ngtiendong/academic-research-agent-skill/orchestrate"><img src="https://agentmods.dev/badge/commands/ngtiendong/academic-research-agent-skill/orchestrate/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 orchestrate

Your own site · 80×15
<a href="https://agentmods.dev/commands/ngtiendong/academic-research-agent-skill/orchestrate"><img src="https://agentmods.dev/badge/commands/ngtiendong/academic-research-agent-skill/orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 273 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 $0.00000 $0.00273
Opus 5 $0.00000 $0.00137
Sonnet 5 $0.00000 $0.00055
Haiku 4.5 $0.00000 $0.00027

Measured 9d ago against content hash 94b41456629d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

orchestrate 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 9d 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.

.claude/commands/orchestrate.md · 33 lines

What it actually says

/orchestrate

Act as the Orchestrator.

Language

If config/language.yaml exists, follow output_language and translation_mode. Otherwise write in English.

Task

Inspect the available project state and decide the next best research action.

Procedure

  1. Identify the current stage: idea, scope, literature, formalization, novelty, reality audit, evidence recovery, feasibility pilot, planning, implementation, full run, review, or writing.
  2. Resolve the project-local naming profile and inspect the evidence required for the requested decision.
  3. State NOT_ASSESSED for gates that lack prerequisites; artifact existence alone does not pass a gate.
  4. Detect fatal assumptions, missing evidence, and decisions that require the human.
  5. Route only work authorized by BLOCK, FEASIBILITY_PILOT_ONLY, EXECUTION_READY, or FULL_RUN_READY.
  6. Do not perform the downstream task unless the user explicitly asks and the gate permits it.
  7. Recommend only the artifacts needed now. Do not propose a complete lifecycle bundle for a raw idea.

Output

  • Current Stage
  • Evidence Read
  • Missing Artifacts
  • Authorized Scope
  • Prohibited Work
  • Recommended Command
  • Human Decision Needed
  • Next Small Step
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. 9d ago First seen · 33 lines · 0 tokens per session scan A 94b41456629d

Subscribe to this mod's changes

orchestrate is a command published in the GitHub repository ngtiendong/Academic-Research-Agent-Skill (44 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 273 tokens. 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.