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 skills add TIGERwu0118/yrb_hes_mcp --skill yrb-hes-evidence-mcpgit clone --depth 1 https://github.com/TIGERwu0118/yrb_hes_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/skills/tigerwu0118/yrb_hes_mcp/yrb-hes-evidence-mcp)<a href="https://agentmods.dev/skills/tigerwu0118/yrb_hes_mcp/yrb-hes-evidence-mcp"><img src="https://agentmods.dev/badge/skills/tigerwu0118/yrb_hes_mcp/yrb-hes-evidence-mcp/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/skills/tigerwu0118/yrb_hes_mcp/yrb-hes-evidence-mcp"><img src="https://agentmods.dev/badge/skills/tigerwu0118/yrb_hes_mcp/yrb-hes-evidence-mcp.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 | $0.00074 | $0.01416 |
| Opus 5 | $0.00037 | $0.00708 |
| Sonnet 5 | $0.00015 | $0.00283 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
yrb-hes-evidence-mcp 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 11d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YRB-HES Evidence MCP
Overview
Use the MCP as a read-only evidence gateway for rag_sag.yrb3_v3. It connects metadata, abstract screening, heading/subchunk records, SAG Event/Entity associations, verified edges, embeddings-backed recall, and structured spatiotemporal evidence while preserving exact source locators.
The geospatial business layer is part of the same rag_sag.yrb3_v3 schema: entity_geocode, entity_geocode_log, entity_hydro_relation, spatial_units, the hydro_*_source tables, and their read-only summary views. The former yrb3.public copy is a frozen archive and is not an active MCP source. Table names remain unchanged after the copy. The response may retain a geocode_sidecar key for client compatibility, but it does not represent a second database connection.
Required workflow
- Call
healthcheckfirst. Confirm database identity, schema, table availability, and current counts. - For a research question, call
search_evidencewith a concise query. Applylanguage, publication-year, evidence-year, and exactdocument_idsfilters when the question provides them. - Use
compare_evidencefor cross-paper comparison. Treat each comparison row as a lead until its returned sources and locators are checked. - Use
get_subchunk_contextto inspect local heading/subchunk context,get_document_overviewfor one-document status, andtrace_sourcebefore quoting or making a document-level claim. - Use
search_entityandexpand_entityto follow canonical concepts across Events and documents. Useget_spatiotemporal_evidencefor explicit spatial/temporal evidence and theis_research_areagate. - Use
search_geocodefor coordinates and verdicts of geocoded spatial entities, andget_document_geocodefor all geocoded entities of one document. The search supportsin_yrb(legacy envelope),in_yrb9(nine-province administrative mask), andin_yrb_hydro(hydrological-basin point membership) as separate filters; never conflate their meanings. Treat geocodes as candidate anchoring: checkverdict,score, andlevelbefore mapping claims (adopt/catalog_center/sectionare coordinate-bearing;out_of_basin/foreign_referenceare explicit exclusions;region_no_point/non_spatial/needs_papercarry no point by design).doc_refson each row lists the papers an entity came from. Usepapercheck_briefto pull a condensed verification brief (evidence quotes, abstract sentence, optional full-text hits viainclude_text) when an entity's identity or location is in doubt. - Report
coverage,warnings, andconflicts. Preservedocument_id,subchunk_id,event_id, evidence IDs, heading paths, and source hashes in working notes.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 67 lines · 74 tokens per session scan A 629dd26bf15d
yrb-hes-evidence-mcp is a skill published in the GitHub repository TIGERwu0118/yrb_hes_mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 74 tokens to every session and 1,416 once invoked, about $0.0004 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 skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…