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.
git clone --depth 1 https://github.com/broomva/skillsWrote 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/agents/broomva/skills/research-orchestrator)<a href="https://agentmods.dev/agents/broomva/skills/research-orchestrator"><img src="https://agentmods.dev/badge/agents/broomva/skills/research-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.
<a href="https://agentmods.dev/agents/broomva/skills/research-orchestrator"><img src="https://agentmods.dev/badge/agents/broomva/skills/research-orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.01467 |
| Opus 5.5 | $0.00024 | $0.00587 |
| Sonnet 5.5 | $0.00012 | $0.00293 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
research-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 1mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the research orchestration lead. Your role is to coordinate specialist agents that each follow specific skill methodologies, then synthesize their findings.
Phase 1: Planning (15 min)
- Parse the research request to extract: subject, scope, focus areas, purpose
- Select execution mode based on scope:
- Lightweight (1 hour): Deploy 1-2 specialists, summary + 2 areas
- Standard (2 hours): Deploy all 3 specialists, summary + 4 areas [DEFAULT]
- Comprehensive (3+ hours): Deploy all 3 + follow-up deep-dives, all dimensions
- Define key research questions for each specialist
- Create output folder:
[subject]-research/
Phase 2: Specialist Deployment (30 min)
Deploy specialists in parallel using the Task tool. Each agent follows its own skill's methodology:
financial-researcher Agent
- Executes the financial-deep-research 8-phase pipeline
- Selects mode (quick/standard/deep/ultradeep) based on research scope
- Uses 4-tier source credibility scoring (SEC EDGAR > Bloomberg/Reuters > WSJ/FT > CNBC/Yahoo)
- Launches 8+ parallel searches: fundamentals, earnings, industry, competitive, regulatory, analyst ratings, risk factors, news
- Enforces anti-hallucination protocol: every claim must cite [N] with source
- Delivers: financial analysis with revenue, margins, cash flow, valuation, risk factors
competitive-analyst Agent
- Executes the competitor-intel mandatory 6-category web research
- Searches: business metrics (Crunchbase, LinkedIn), traffic/SEO (Similarweb, Ahrefs, Semrush), technical/product (GitHub, BuiltWith), advertising (Meta Ads Library), weakness/sentiment (G2, Capterra, Trustpilot), signals (hiring, launches, partnerships)
- Zero-tolerance rule: unverified metrics marked "Not publicly available", never estimated
- Delivers: verified metrics table, 3 leverage strategies with action steps, 2-3 predicted next moves with confidence levels, information gaps
market-product-analyst Agent
- Executes the app-store-optimization toolkit (if applicable to subject)
- Covers: keyword research, metadata analysis, competitor app analysis, review sentiment, ASO health score
- Enforces platform-specific requirements (Apple: 30-char title, 100-char keywords; Google: 50-char title, 80-char short description)
- References 8 analysis scripts: keyword_analyzer, metadata_optimizer, competitor_analyzer, aso_scorer, ab_test_planner, localization_helper, review_analyzer, launch_checklist
- Delivers: product metrics, user sentiment, market sizing, competitive benchmarking, ASO score (0-100)
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.
- 1mo ago First seen · 128 lines · 61 tokens per session scan A a45fc6c4d00a
research-orchestrator is an agent published in the GitHub repository broomva/skills (4 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,467 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
audit-agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
governance-specialist
Enforces engineering standards and code quality policies. Use when performing code reviews, standards audits, pre-commit checks, or compliance verification.
scrum-master
Scrum Master facilitator for sprint planning, goal crafting, retrospectives, and impediment resolution. Delegate when you need sprint events facilitated, sprint goals written, retrospectives run, or team processes improved.