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.
npx skills add gyanranjan/polyagent-skills --skill expert-researchgit clone --depth 1 https://github.com/gyanranjan/polyagent-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/skills/gyanranjan/polyagent-skills/expert-research)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/expert-research"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/expert-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.
<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/expert-research"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/expert-research.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 | $0.00057 | $0.00818 |
| Opus 5 | $0.00028 | $0.00409 |
| Sonnet 5 | $0.00011 | $0.00164 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
expert-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 10d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Research
Purpose
Act as a domain expert, not a passive summarizer. Build a defensible recommendation by collecting high-quality evidence, testing assumptions, and presenting clear tradeoffs with confidence levels.
When to Use
- User asks for expert opinion, deep analysis, or strategic recommendation
- Topic is high-impact, ambiguous, or likely to have hidden risks
- Decision quality depends on external facts, benchmarks, or competing options
- User asks for "deep research", "best approach", "what should we do", or similar
When NOT to Use
- User only wants a quick draft/summary (use a domain-specific lightweight skill)
- Task is purely mechanical with no meaningful decision/tradeoff
Inputs
Required:
- Decision goal — what decision/action this analysis should support
Optional (but strongly recommended):
- Scope boundaries — what to include/exclude
- Constraints — timeline, budget, regulatory, technical
- Success criteria — what "good" looks like
- Existing hypotheses/options
Process
Step 1: Frame the Decision
Define:
- Decision question
- Decision deadline/urgency
- Constraints and evaluation criteria
If these are incomplete, ask 3-5 focused questions before continuing.
Step 2: Build an Evidence Plan
List:
- Key unknowns to resolve
- Sources needed (docs, standards, benchmarks, user data, expert input)
- Validation method for each unknown
Step 3: Deep Research or Input Collection
- If research tools/sources are available: collect and synthesize evidence
- If unavailable or restricted: ask user for targeted inputs (documents, links, data, assumptions)
- Explicitly mark each claim as:
- Evidence-backed
- Inference
- Open question
Step 4: Challenge Assumptions
For each major assumption:
- Why it may fail
- What would invalidate it
- Mitigation or contingency plan
Step 5: Compare Options with Tradeoffs
Build a concise options table:
- Option
- Benefits
- Risks
- Cost/effort
- Time-to-value
- Recommendation fit
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.
- 10d ago First seen · 126 lines · 57 tokens per session scan A 4c946e097e14
expert-research is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 818 once invoked, about $0.0003 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
deep-research
Multi-lens research engine — one question, 9 angles, synthesized analysis. Uses /research-skill-graph/ as the knowledge base. Load this skill when given a research question and use it to produce deep, structured analysis. Invoke by saying "do deep research on [question]".
Deep Research
Produce a deep, structured research report on a topic: decompose into key dimensions, analyze each with evidence and reasoning, synthesize cross-cutting insights, and surface open questions. Use for deep research, analysis, and literature/landscape reviews.
competitive-analysis
Analyze competitors systematically. Compare products, features, pricing, positioning, and market strategies. Generate comprehensive competitive intelligence reports.
strategic-initiative-modeling
Model strategic initiatives and expansion scenarios — market entry, partnerships, M&A, new product lines, platform plays — building financial projections and strategic rationale for major company moves.
win-loss-analysis
Pattern analysis across closed deals to reverse-engineer your ideal customer and fix leaks.
html-ppt-zhangzara-mat
A margin-recovery diagnosis for a regional grocery chain — the governing thought, the driver tree, the priorities, and the roadmap. Built as a decision-grade consulting deck for client sponsor, steering committee.