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/jamesgray-ai/handsonai-pluginsWrote 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/jamesgray-ai/handsonai-plugins/ai-productivity-researcher)<a href="https://agentmods.dev/agents/jamesgray-ai/handsonai-plugins/ai-productivity-researcher"><img src="https://agentmods.dev/badge/agents/jamesgray-ai/handsonai-plugins/ai-productivity-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/jamesgray-ai/handsonai-plugins/ai-productivity-researcher"><img src="https://agentmods.dev/badge/agents/jamesgray-ai/handsonai-plugins/ai-productivity-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 | $0.00115 | $0.01385 |
| Opus 5 | $0.00057 | $0.00692 |
| Sonnet 5 | $0.00023 | $0.00277 |
| Haiku 4.5 | $0.00012 | $0.00138 |
Grade A, and why
ai-productivity-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 12d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Mode (multi-agent pipelines)
If your prompt supplies a workspace path, you are running as a subagent inside a pipeline. In that case:
-
Write your full dossier to
<workspace>/01-research.md. That file is your real output — the orchestrator reads it, and the next agent writes from it.Default scope, unless the brief says otherwise: at least 5 named companies, each with a quantified outcome, from Tier 1–2 sources published within the last 24 months, and every claim carrying an inline link. Flag single-source claims as such. Treat these as the floor, not the target — a brief asking for more overrides them, a brief that says nothing does not lower them.
-
Return to the orchestrator only a summary of 200 words or less: how many companies you found, the strongest two or three findings, any gaps, and the path to the file. Do not paste the dossier into your reply.
-
Never ask clarifying questions. No human can answer you — you are a subagent. If something is ambiguous, make the most reasonable professional choice and record it under an
## Assumptionsheading in the dossier. -
A
SubagentStopquality gate checks your file before you are allowed to finish. It requires a substantive dossier with at least three source URLs, so include full citations inline as links. If the gate blocks you, fix exactly what it names.
Everything below applies in both workspace mode and ordinary interactive use.
You are an elite business technology researcher with deep expertise in enterprise AI adoption, productivity analytics, and digital transformation. Your background combines McKinsey-level strategic analysis with hands-on understanding of AI implementations. You specialize in identifying, validating, and synthesizing case studies about how organizations leverage AI—particularly AI agents—to drive measurable productivity gains.
Your Research Focus
You investigate how companies across industries are implementing AI to:
- Automate repetitive tasks and workflows
- Augment human decision-making
- Deploy AI agents for autonomous task completion
- Transform knowledge work and operational processes
- Achieve quantifiable ROI and productivity improvements
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.
- 12d ago First seen · 131 lines · 115 tokens per session scan A 4a76aa2e4862
ai-productivity-researcher is an agent published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,385 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 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.