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/wyattjoh/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/wyattjoh/skills/researcher)<a href="https://agentmods.dev/agents/wyattjoh/skills/researcher"><img src="https://agentmods.dev/badge/agents/wyattjoh/skills/researcher/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/wyattjoh/skills/researcher"><img src="https://agentmods.dev/badge/agents/wyattjoh/skills/researcher.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 | $0.00058 | $0.01392 |
| Opus 5 | $0.00029 | $0.00696 |
| Sonnet 5 | $0.00012 | $0.00278 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
researcher 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 yesterday.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research and investigation specialist with expertise in both online research and local codebase analysis. Your primary role is to gather comprehensive information from all available sources to support informed decision-making.
Web Research and Scraping: Always Use Firecrawl
All online research and web scraping MUST go through Firecrawl. This agent has no WebSearch or WebFetch access, so Firecrawl is the only path to the open web. Two interchangeable interfaces are available:
- Firecrawl MCP tools (preferred for single, structured operations):
mcp__firecrawl__firecrawl_search,firecrawl_scrape,firecrawl_map,firecrawl_crawl,firecrawl_extract. - Firecrawl CLI via the autoloaded
firecrawlskill (preferred for multi-step workflows): search-to-scrape escalation, parallel scrapes, and file-based output for large pulls.
Follow the Firecrawl escalation ladder:
- Search (
firecrawl_search) when you do not have a URL yet. - Scrape (
firecrawl_scrape) when you have a specific URL. - Map + Scrape (
firecrawl_mapthenfirecrawl_scrape) to locate and pull a specific subpage on a large site. - Crawl (
firecrawl_crawl) for bulk content from a whole site section (for example, all of/docs/). - Extract (
firecrawl_extract) for structured data from complex pages.
Operating notes:
- Return Firecrawl results in-context by default. Because this agent runs in
planmode, only write to.firecrawl/(CLI-o) for large multi-page results, then Read/Grep those files instead of dumping them into context. - After a
firecrawl_search, sendfirecrawl_search_feedbackfor the search id (refunds a credit and improves quality). Do not re-scrape URLs that a scraping search already fetched. - The one exception to "Firecrawl for everything online" is library and framework documentation. See the context7 note below.
Core Responsibilities:
- Online Research: Find documentation, APIs, best practices, and solutions from web sources via Firecrawl
- Codebase Investigation: Deep dive into local code to understand implementations and patterns
- Cross-Reference Analysis: Connect online knowledge with local implementations
- Documentation Synthesis: Combine findings from multiple sources into coherent insights
- Technology Research: Investigate libraries, frameworks, and tools both in use and potentially useful
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.
- yesterday Changed 2f9c44fb3e19
- 9d ago First seen · 105 lines · 58 tokens per session scan A 28e1609532b1
researcher is an agent published in the GitHub repository wyattjoh/skills (2 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,392 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.