research-flow

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 commands/griddynamics/rosetta/research-flow

Clone the repo

git clone --depth 1 https://github.com/griddynamics/rosetta

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/griddynamics/rosetta/research-flow.svg)](https://agentmods.dev/commands/griddynamics/rosetta/research-flow)

Your own site

<a href="https://agentmods.dev/commands/griddynamics/rosetta/research-flow"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/research-flow.svg" alt="Measured on agentmods" height="20"></a>

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 649 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin unknown 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.

Model	Per session	Once invoked
Fable 5	$0.00017	$0.00649
Opus 5	$0.00009	$0.00324
Sonnet 5	$0.00003	$0.00130
Haiku 4.5	$0.00002	$0.00065

Measured today against content hash 20837ca5ec2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-flow 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 today.

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.

plugins/core-copilot-light/commands/research-flow.md · 66 lines

What it actually says

<research_flow>

<description_and_purpose> Orchestrates deep research via meta-prompting: craft an optimized research prompt, then execute it in a dedicated subagent. </description_and_purpose>

<workflow_phases>

All Rosetta prep steps MUST be FULLY completed
USE SKILL load-project-context, orchestration, hitl
MUST ALWAYS use todo tasks ledger, ASAP. Phases are sequential. Independent tasks can run in parallel.
Orchestrator trusts the system and skills; coordinates sequence, artifacts, state, and approvals only.
Workflow state MUST be saved to agents/TEMP/<FEATURE>/research-flow-state.md file.
If /goal is set repeat phases 3-4 until goal is met.

<context_load phase="1" subagent="researcher" role="Context gatherer for research scope" subagent_required_model="Claude Sonnet 5, GPT-5.6 Terra, Gemini 3.7 Flash">

Read all lines from CONTEXT.md, ARCHITECTURE.md, and IMPLEMENTATION.md.
Input: user research request. Output: loaded project context.
Update research-flow-state.md.

</context_load>

<prompt_craft phase="2" subagent="researcher" role="Research prompt architect" subagent_required_model="Claude Opus 5, GPT-5.6 Terra, GPT-5.6 Sol, Gemini 3.7 Flash">

Create an optimized research prompt for the user request.
Save as research-prompt.md in FEATURE PLAN folder. Output ONLY the optimized prompt.
Input: user request + project context. Output: research-prompt.md.
Required skills: reasoning
Update research-flow-state.md.
HITL approval of research prompt before execution.

</prompt_craft>

<execute_research phase="3" subagent="researcher" role="Deep research executor" subagent_required_model="Claude Sonnet 5, GPT-5.6 Terra, Gemini 3.7 Flash">

Execute the approved research prompt as a separate subagent.
Input: approved research-prompt.md. Output: docs/<feature>-research.md.
Required skills: research
Update research-flow-state.md.

</execute_research>

Finalize docs/<feature>-research.md.
Input: completed research document. Output: finalized research document.
Update research-flow-state.md and mark complete.

</workflow_phases>

</research_flow>

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.

today First seen · 66 lines · 17 tokens per session scan A 20837ca5ec2e

Subscribe to this mod's changes

research-flow is a command published in the GitHub repository griddynamics/rosetta (342 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 649 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 2026-09-03.

Productivity Research claude-code codex copilot cursor developer-tools mcp-server workflow

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

OPSX: Apply

OPSX: Propose

OPSX: Archive

OPSX: Explore

/opsx-propose

/opsx-sync