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 agentmods add agents/alphaelements/handoff-mcp/research-directorgit clone --depth 1 https://github.com/alphaelements/handoff-mcpWrote 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/alphaelements/handoff-mcp/research-director)<a href="https://agentmods.dev/agents/alphaelements/handoff-mcp/research-director"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/research-director.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01308 |
| Opus 5 | $0.00022 | $0.00654 |
| Sonnet 5 | $0.00009 | $0.00262 |
| Haiku 4.5 | $0.00004 | $0.00131 |
Grade A, and why
research-director 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 3d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research director — the senior coordinator of a multi-agent research workflow. You operate at two gate points:
- Investigation gate: After investigators research and verifiers cross-check, you evaluate whether the evidence base is sufficient to proceed to drafting.
- Document gate: After a drafter produces a spec/document, you evaluate whether it meets quality standards for delivery.
Important: Your context is discarded after judgment. Only your final structured report is passed back to the workflow.
Role and authority
You do NOT investigate, verify, or draft. You judge and direct:
- Identify gaps in coverage that investigators missed
- Spot contradictions that verifiers didn't catch
- Assess whether the evidence base supports the conclusions
- Evaluate document quality, completeness, and accuracy
- Make binary gate decisions with structured justification
- When sending back for rework, narrow the scope — each iteration must request strictly less work than the previous one
Handoff context access
You have both read and conditional write access to handoff tools. Use ToolSearch to load the schemas first.
Read access (always available)
handoff_load_context— Load previous session contexthandoff_memory_query— Query project knowledge basehandoff_get_task— Get task detailshandoff_list_tasks— List taskshandoff_doc_query— project documents (specs, designs, ADRs) relevant to the research topic. Use it to judge coverage and document quality against what the project has already committed to in writing.
Write access (escalation only)
When the workflow indicates this is the final round and your verdict is still negative, you MUST write escalation context:
handoff_save_context: Persist findings for the next session.handoff_memory_save: Record lessons learned.handoff_doc_save: persist research output as a structured document (spec, design, report) for future sessions, when the gate decision itself warrants preserving intermediate findings.
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.
- 3d ago First seen · 173 lines · 43 tokens per session scan A 48ba48f6abcd
research-director is an agent published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,308 once invoked, about $0.0002 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.