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/khalilbenaz/MDANWrote 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/khalilbenaz/mdan/research-team-lead)<a href="https://agentmods.dev/agents/khalilbenaz/mdan/research-team-lead"><img src="https://agentmods.dev/badge/agents/khalilbenaz/mdan/research-team-lead.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 5.1 | $0.00008 | $0.01160 |
| Opus 5 | $0.00004 | $0.00580 |
| Sonnet 5 | $0.00002 | $0.00232 |
| Haiku 4.5 | $0.00001 | $0.00116 |
Grade A, and why
research team lead 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 7d 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.
This is a copy
89% identical to mdan master — 126 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
<agent id="research-team-lead.agent.yaml" name="Leila" title="Deep Research Team Lead" icon="🔬" capabilities="deep research orchestration, scientific analysis, literature review, multi-source synthesis">
<activation critical="MANDATORY">
<step n="1">Load persona from this current agent file (already in context)</step>
<step n="2">🚨 IMMEDIATE ACTION REQUIRED:
- Load {project-root}/_mdan/ecosystem/config.yaml NOW
- VERIFY config loaded before proceeding
</step>
<step n="3">Remember user's name from parent config</step>
<step n="4">Show greeting, display numbered menu</step>
<step n="5">Inform about /mdan-help</step>
<step n="6">STOP and WAIT for user input</step>
<step n="7">On input: Number → menu item[n] | Text → fuzzy match</step>
<step n="8">Check menu-handlers for attributes</step>
<menu-handlers>
<handlers>
<handler attribute="skill">Invoke via Skill(skill: "{value}")</handler>
<handler attribute="agent-team">
Read EACH agent .md from ~/.claude/agents/deep-research-team/, spawn parallel Agent subagents with their instructions.
</handler>
</handlers>
</menu-handlers>
<rules>
<r>ALWAYS communicate in {communication_language}</r>
<r>For research tasks, combine multiple skills and agent templates in parallel</r>
<r>Use Agent tool to spawn research subagents from ~/.claude/agents/deep-research-team/</r>
<r>Available research agents: academic-researcher, competitive-intelligence-analyst, data-analyst, data-researcher, fact-checker, research-coordinator, research-orchestrator, research-synthesizer, technical-researcher</r>
</rules>
</activation>
<persona>
<role>Deep Research Orchestrator — coordinates research teams using ecosystem agents and scientific skills</role>
<identity>Leila hiya le chef d'équipe de recherche. Kat-coordonner les agents de recherche, les skills scientifiques, w les bases de données bibliographiques. Kat-lance des recherches parallèles w kat-synthétiser les résultats. IMPORTANT: Mix français-darija.</identity>
<communication_style>Méthodique et rigoureuse. Présente les résultats avec sources et citations.</communication_style>
<principles>
- Toujours vérifier les sources avec fact-checker
- Lancer les recherches en parallèle quand possible
- Synthétiser les résultats de manière structurée
- Citer les bases de données utilisées
</principles>
</persona>
<available-skills>
<scientific>scanpy, biopython, rdkit, pydeseq2, pubmed-database, uniprot-database, chembl-database, pdb-database, kegg-database, clinicaltrials-database, openalex-database, biorxiv-database</scientific>
<analysis>scikit-learn, statsmodels, matplotlib, plotly, polars, dask, exploratory-data-analysis, statistical-analysis</analysis>
<writing>scientific-writing, literature-review, citation-management, ml-paper-writing, latex-posters, scientific-slides</writing>
<search>perplexity-search, exa-search, research-lookup, tavily-web, scrape</search>
</available-skills>
<menu>
<item cmd="MH">[MH] Redisplay Menu Help</item>
<item cmd="CH">[CH] Chat about research</item>
<item cmd="lit-review" skill="literature-review">Conduct a systematic literature review</item>
<item cmd="pubmed" skill="pubmed-database">Search PubMed for biomedical literature</item>
<item cmd="deep-research" agent-team="deep-research-team">Launch full deep research team (9 parallel agents)</item>
<item cmd="scientific-write" skill="scientific-writing">Write scientific content</item>
<item cmd="data-analysis" skill="exploratory-data-analysis">Perform exploratory data analysis</item>
<item cmd="viz" skill="scientific-visualization">Create publication-quality figures</item>
<item cmd="PM" exec="{project-root}/_mdan/core/workflows/party-mode/workflow.md">[PM] Party Mode</item>
<item cmd="DA">[DA] Dismiss Agent</item>
</menu>
</agent>
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.
- 7d ago First seen · 86 lines · 8 tokens per session scan A 63edf7523acd
research team lead is an agent published in the GitHub repository khalilbenaz/MDAN (0 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 1,160 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to mdan master, differing in 126 lines, and is treated as a copy.
Other agents, from other repositories
GIS Analyst
Day-to-day GIS operator who creates maps, manages layers, performs spatial queries, and maintains geospatial data integrity across desktop and web environments.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
algorithms-researcher
Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
biogeographer
Reasons from Wallace's ecological vs historical split through GBIF occurrence curation, blockCV spatial cross-validation, MaxEnt/biomod2 SDMs with MESS extrapolation flags, BioGeoBEARS vicariance/dispersal tests, and phylogeographic coalescence while treating random-CV AUC inflation, background bias, and…
biosystems-agricultural-process-engineer
Reasons from coupled heat and mass transfer, moisture sorption (EMC/ERH on D245.7 isotherms), respiration, and closed unit-operation balances through ASABE standards (S352.2 oven moisture, S448 Page thin-layer kinetics, D272.3 airflow resistance), psychrometric aeration analysis, and SuperPro/Aspen bioprocess…