orch-research

orch-research is a skill for Claude Code, Codex from mattmre/EVOKORE-MCP-PUBLIC. It costs 21 tokens per session (1,259 once invoked), scanned A, original, MIT.

A research workflow that finds leading GitHub repositories for a topic, evaluates them through several expert perspectives, and packages the findings for presentation.

In plain words
What is it for?
Use it to investigate a technical topic, deeply assess candidate repositories, add integration context, and produce a curated shortlist.
Why use it?
It reduces the time spent comparing unfamiliar repositories and helps connect research results to a target system.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to investigate a technical topic, deeply assess candidate repositories, add integration context, and produce a curated shortlist.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mattmre/evokore-mcp-public/orch-research
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 mattmre/EVOKORE-MCP-PUBLIC --skill orch-research
Clone the repo
git clone --depth 1 https://github.com/mattmre/EVOKORE-MCP-PUBLIC

Made for: Claude Code, Codex.

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 orch-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/orch-research/github.svg)](https://agentmods.dev/skills/mattmre/evokore-mcp-public/orch-research)
Your own site
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/orch-research"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/orch-research/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 orch-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/orch-research"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/orch-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,259 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 $0.00021 $0.01259
Opus 5 $0.00010 $0.00629
Sonnet 5 $0.00004 $0.00252
Haiku 4.5 $0.00002 $0.00126

Measured 8d ago against content hash 95cdfb47b7ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

orch-research 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 8d 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/ORCHESTRATION FRAMEWORK/commands/orch-research/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

orch-research — Topic-Based Repo Research with Expert Panel Review

Purpose

Given a user-supplied narrative describing a topic, domain, or need, this command researches top GitHub repositories, evaluates candidates through expert panels, and produces a curated shortlist with integration recommendations and a presentation-ready summary.

Usage

orch-research "<narrative>" [options]

Options

Option Description Default
--max <n> Maximum repos to deeply evaluate 10
--depth <level> Evaluation depth: quick, standard, deep standard
--context "<text>" Integration context (target system description)
--meta-improve Run meta-improvement cycle after completion false
--no-presentation Skip presentation packaging false

Examples

Basic Topic Research

orch-research "TypeScript MCP server implementations with tool discovery and session management"

Research with Integration Context

orch-research "real-time collaboration frameworks with CRDT support" \
  --context "EVOKORE-MCP v3.1 TypeScript MCP server with WebSocket support" \
  --depth deep

Broad Domain Discovery

orch-research "AI agent orchestration frameworks that support multi-agent coordination, task decomposition, and parallel execution" \
  --max 15

Research with Meta-Improvement

orch-research "developer productivity CLI tools with hook systems" \
  --meta-improve

Reverse Engineering Portfolio Research

orch-research "recently updated reverse engineering repos with strong debugger, decompiler, automation, and malware triage workflows" \
  --context "EVOKORE-MCP reverse-engineering operating model buildout" \
  --depth deep \
  --meta-improve

Workflow Steps

  1. Narrative Analysis — Parse the user's description into structured search criteria, requirements, and quality signals
  2. Repo Discovery (parallel)
    • GitHub API search (code, repos, topics)
    • Community scan (awesome-lists, blog posts, npm/pypi trending, discussions)
  3. Initial Filtering — Deduplicate, rank, and filter to top N candidates based on activity, license, language match, community signal
  4. Deep Evaluation (parallel) — For each candidate: README analysis, file tree structure, architecture pattern, test coverage, dependency health, documentation quality, unique capabilities
  5. Expert Panel Review — Repo Ingestion Panel (Kim, Petrov, Obi, Larsson, Tanaka) evaluates all candidates. Per-repo verdicts: ADOPT / CONSIDER / SKIP
  6. Feasibility Gate — Feasibility Panel (Torres, Wright, Okonkwo, Svensson) assesses integration effort, ROI, adoption approach
  7. Presentation Packaging — Presentation Panel extracts key findings into stakeholder-ready format
  8. Meta-Improvement (optional) — Evaluates expert effectiveness and workflow quality

Read the full file on GitHub · 143 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. 8d ago First seen · 143 lines · 21 tokens per session scan A 95cdfb47b7ed

Subscribe to this mod's changes

orch-research is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 1,259 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.

Related

Other skills, from other repositories

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

LiHongwei-cn/lihongwei-cn · 47 tokens

research-repository

Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.

Owl-Listener/designer-skills · 43 tokens

form-design

Design a form end to end — field order, grouping, validation, and completion. Use when the artifact is a form. For product-wide error strategy use error-handling-ux; for first-run signup use onboarding-design.

Owl-Listener/designer-skills · 51 tokens

peak-end-rule

Apply the Peak-End Rule — a flow is remembered by its most intense moment and its last. Use when designing completion, celebration, or cancellation moments. For sustaining engagement mid-flow, use zeigarnik-effect.

Owl-Listener/designer-skills · 47 tokens

law-of-common-region

Apply the Law of Common Region — a shared container, background, or border groups elements regardless of spacing. Use when grouping must survive a tight layout. For grouping by spacing alone, use law-of-proximity.

Owl-Listener/designer-skills · 48 tokens

critique-visual-hierarchy

Critique a rendered screen's hierarchy — entry point, eye flow, weight distribution, and emphasis. Use when attention lands in the wrong place. For establishing hierarchy in new work, use visual-hierarchy (ui-design).

Owl-Listener/designer-skills · 53 tokens