Borrowing it
Nothing to install: this file belongs to u9401066/rootcause-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/u9401066/rootcause-mcp/master/.github/agents/research.agent.mdgit clone --depth 1 https://github.com/u9401066/rootcause-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/u9401066/rootcause-mcp/research)<a href="https://agentmods.dev/agents/u9401066/rootcause-mcp/research"><img src="https://agentmods.dev/badge/agents/u9401066/rootcause-mcp/research/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/u9401066/rootcause-mcp/research"><img src="https://agentmods.dev/badge/agents/u9401066/rootcause-mcp/research.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 | $0.00025 | $0.00925 |
| Opus 5.5 | $0.00010 | $0.00370 |
| Sonnet 5.5 | $0.00005 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
research 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Assistant
Use this agent for biomedical literature search, paper exploration, and Zotero import workflows.
Tool Ownership
- PubMed Search MCP 0.6.1 owns literature search, discovery, sessions, full-text access, citation metrics, exports, Research Chronicle, and biomedical image search. Its SDK v2 surface contains 45 tools in 16 categories.
- Zotero Keeper 2.1 owns Zotero library reads, collection listing, duplicate checks, the final import handoff, and guarded Zotero 10+ Local API mutations. Its default surface contains 32 tools.
- Do not duplicate PubMed searching inside Zotero Keeper. Keep the boundary clear.
Default Workflow
- Search with PubMed Search MCP:
unified_search(query="...", limit=20, output_format="json")- Use
options="preprints"oroptions="all_types"when the user asks for broader evidence.
- Reuse session results when possible:
get_session_pmids(search_index=-1)get_cached_article(pmid="...")get_session_summary()
- Check Zotero before importing:
list_collections()when a target collection is needed.check_articles_owned(pmids=[...])before import.
- Import through the single keeper bridge:
import_articles(articles=[...], collection_name="...")- For RIS text, use
import_articles(ris_text="...", collection_name="..."). - If
interactive_saveis used, submit an exact collection key.ROOTis valid only after its second confirmation.
- For Zotero 10+ organization/update requests:
- Obtain a response-bound
server_idfrom a Local API read orauthorize_local_writes. Obtain the exact-item object version for metadata updates, or the response-bound library cursor for full-text replacement. - Before a file upload, call it with
require_remembered=trueand ask the user to choose Always Allow so all three upload phases remain authorized. - Call the requested mutation with
confirm=falseandexpected_server_id, show the complete proposal, then repeat it unchanged withconfirm=trueonly after explicit approval. - If authorization returns another identity, reread, preview, and request approval again; never add identity after preview.
- Never expose a Local API key or retry a 412 version conflict.
- Obtain a response-bound
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.
- 1mo ago First seen · 63 lines · 25 tokens per session scan A 287102d883b6
research is an agent published in the GitHub repository u9401066/rootcause-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 925 once invoked, about $0.0001 per session on Opus 5.5. 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
research-analyst
Academic research analysis agent. Ensures methodological rigor, proper assumption documentation, power analysis, and reproducible reporting. Use when the analysis must meet peer-review or regulatory standards.
forecaster
Time series forecasting agent. Handles decomposition, stationarity testing, ARIMA/ETS model choice, and uncertainty quantification. Use when predicting future values from historical data.
geospatial-analyst
Geospatial analysis agent. Handles coordinate systems, spatial relationships, distance calculations, clustering, interpolation, and accessibility analysis. Use when data has a geographic or spatial dimension.
statistical-analyst
Statistical analysis agent. Runs hypothesis tests, ANOVA, effect sizes, sampling design, bootstrap estimation, and non-parametric tests with plain-language interpretation. Use when rigorous statistical testing or estimation is needed.
gsd-debugger
Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd-debug orchestrator.
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].