Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/oxi-717/ai-native-toolkit/research-ensemble)<a href="https://agentmods.dev/skills/oxi-717/ai-native-toolkit/research-ensemble"><img src="https://agentmods.dev/badge/skills/oxi-717/ai-native-toolkit/research-ensemble.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00119 | $0.01569 |
| Opus 5 | $0.00060 | $0.00785 |
| Sonnet 5 | $0.00024 | $0.00314 |
| Haiku 4.5 | $0.00012 | $0.00157 |
Grade A, and why
research-ensemble 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research — Adversarial Ensemble v2
Conduct autonomous multi-agent research on topic: $ARGUMENTS
Argument Parsing
Format: /research-ensemble [topic] or /research-ensemble [topic] [level] [domain]
Examples:
/research-ensemble kubernetes vs nomad→ standard, auto-domain (tech)/research-ensemble creatine safety deep→ deep, auto-domain (health)/research-ensemble creatine safety deep health→ deep, health/research-ensemble market analysis for SaaS standard business→ standard, business
Defaults: level=standard, domain=auto-detect, report_language=English
Report language: Use REPORT_LANGUAGE if set. Otherwise honor an explicit language request from the user. If neither is present, write reports, headings, progress logs, and user summaries in English. Russian output is only for an explicit Russian request or REPORT_LANGUAGE=ru.
Level Definitions
| Level | Agents | Time | When to use |
|---|---|---|---|
| standard | 6 (3 Scouts + Critic + Synthesizer + Fact-Checker) | 30-60 min | Most research tasks |
| deep | 12-15 (full ensemble, 3 cycles with reflections) | 1-4 hours | Serious research with verification, health, architecture decisions |
Domain Auto-Detection
If domain not specified, detect by keywords in topic:
| Keywords | Domain |
|---|---|
| framework, API, library, database, architecture, kubernetes, docker, code, deploy, CI/CD, microservice, react, python, rust | tech |
| market, competitors, pricing, startup, revenue, business model, ROI, SaaS, funding, GTM | business |
| supplement, dosage, biomarker, sleep, exercise, nutrition, health, vitamin, protocol, longevity, creatine, omega | health |
| firewall, SSH, vulnerability, CVE, hardening, pentest, encryption, TLS, WAF, security, DDoS | security |
| everything else | general |
Execution
Step 0: Preparation
- Parse arguments: extract
{TOPIC},{LEVEL},{DOMAIN} - Create slug from topic: lowercase, replace spaces with underscores, truncate to 50 chars
- Determine
{REPORT_LANGUAGE}fromREPORT_LANGUAGE, then explicit user request, then default English - Create output directory structure:
What ships with it
14 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.
- references/agent-prompts/critic.md 2.8 KB
- references/agent-prompts/deep-diver.md 2.5 KB
- references/agent-prompts/domain-reviewer.md 2.8 KB
- references/agent-prompts/fact-checker.md 2.7 KB
- references/agent-prompts/interaction-mapper.md 3.4 KB
- references/agent-prompts/scout.md 4.4 KB
- references/agent-prompts/statistician.md 2.5 KB
- references/agent-prompts/synthesizer.md 3.0 KB
- references/deep-workflow.md 9.9 KB
- references/domains.md 6.2 KB
- references/exa-search-guide.md 4.3 KB
- references/generate-pdf-report.py 19 KB runs code
- references/profile-template.md 1.6 KB
- references/standard-workflow.md 5.9 KB
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.
- 8d ago First seen · 151 lines · 119 tokens per session scan A 071ce21c3583
research-ensemble is a skill published in the GitHub repository OXI-717/ai-native-toolkit (8 stars, last pushed 15d ago), licensed MIT. It adds 119 tokens to every session and 1,569 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".