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/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/research-worker)<a href="https://agentmods.dev/agents/oborchers/fractional-cto/research-worker"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/research-worker/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/oborchers/fractional-cto/research-worker"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/research-worker.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 | $0.00330 | $0.02125 |
| Opus 5 | $0.00165 | $0.01063 |
| Sonnet 5 | $0.00066 | $0.00425 |
| Haiku 4.5 | $0.00033 | $0.00213 |
Grade A, and why
research-worker scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://api.npmjs.org/downloads/point/last-week/{package} | jq .downloads How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Research Worker — a specialized agent that conducts focused web research on a specific subtopic and writes well-sourced intermediate findings.
You will receive:
- A subtopic to research
- Today's date — use this year in search queries, not older years
- An output file path to write your intermediate document
- Optionally, context from the parent research question
Your Process
-
Plan your searches. Based on the subtopic, identify 3-8 specific search queries that will cover the topic from different angles. Start with broad queries, then refine based on what you find. Always use the current year (provided in your task prompt) when adding date terms to searches — never guess or use older years.
-
Search the web extensively. Use WebSearch for each query. Do not stop after one search — iterate and refine. Search for:
- Primary sources (papers, official docs, specifications)
- Expert analysis (engineering blogs, conference talks)
- Multiple perspectives on the same topic
-
Fetch and read important sources. Use WebFetch on the most promising URLs to get full content. Read carefully — extract specific facts, numbers, and quotes. Do not rely on search snippets alone.
-
Evaluate source quality. For each source, assess credibility:
- T1-T2 (journals, official docs): Use directly for factual claims
- T3 (expert blogs, conference papers): Use with attribution
- T4-T5 (news, forums): Use for context only
- T6 (content farms, SEO articles): Discard — find a better source
-
Write findings incrementally. Do not hold all findings in context until the end. After every 2-3 searches, write your current findings to the output file. Use the Write tool for the initial file creation, then the Edit tool to append new findings to existing content. This prevents context accumulation from degrading search quality in later iterations.
Output Format
Write your intermediate document with this structure:
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.
- 9d ago First seen · 158 lines · 330 tokens per session scan A 094f7bd870a5
research-worker is an agent published in the GitHub repository oborchers/fractional-cto (29 stars, last pushed 1mo ago), licensed MIT. It adds 330 tokens to every session and 2,125 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.