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 5.5 | $0.00030 | $0.00566 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,416 once invoked, about $0.0003 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.
yrb-hes-evidence-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| yrb-hes-evidence-mcpTIGERwu0118/yrb_hes_mcp | Skill | 0 | 2mo ago | MIT | A | 74 | Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 44 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 83 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 205 | Claude Code |