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 skills/dbcls/togomcp/research-article-analysisnpx skills add dbcls/togomcp --skill research-article-analysisgit clone --depth 1 https://github.com/dbcls/togomcpWrote 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/dbcls/togomcp/research-article-analysis)<a href="https://agentmods.dev/skills/dbcls/togomcp/research-article-analysis"><img src="https://agentmods.dev/badge/skills/dbcls/togomcp/research-article-analysis.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 | $0.00147 | $0.02642 |
| Opus 5 | $0.00073 | $0.01321 |
| Sonnet 5 | $0.00029 | $0.00528 |
| Haiku 4.5 | $0.00015 | $0.00264 |
Grade A, and why
research-article-analysis 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 6d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Article Analysis (claim validation via TogoMCP SPARQL)
Validate a paper claim-by-claim by running structured SPARQL against five RDF
databases — ChEBI, Rhea, Reactome, UniProt, GO — and citing the query
results (exact formulas, equations, EC numbers, GO definitions), not the paper's
prose or keyword-search text. The driver is the TogoMCP MCP tools
(run_sparql, the search_* tools, get_MIE_file).
The full phased checklist, ID-tracking templates, scoring rubric, and anti-skipping safeguards live in references/research_article_analysis.md — read it for the deliverable structure and discipline. This SKILL.md is the operational path: the SPARQL that actually works (the printed templates have two bugs — see Gotchas), the verified tool calls, and the traps.
Prerequisites
- The TogoMCP MCP server connected to your client (e.g. Claude Desktop,
Claude Code). Its
run_sparql,search_*, andget_MIE_filetools are what drive this skill. - Network access from that server to
rdfportal.org.
Warm-up check (confirm connectivity before trusting the templates)
Before relying on the templates, send the ChEBI structure query below through the
run_sparql tool and confirm it returns a row — that proves the endpoint is
reachable and the (chemrof-namespace) pattern still resolves. If it returns
nothing, that database's query type is broken (endpoint down or schema drift) —
re-read its MIE via get_MIE_file and fix the pattern below before relying on it.
Run the analysis (phases, with verified queries)
Follow the phase discipline in the reference doc: 2A select databases (5
rules), 2B get_MIE_file(database=...) for each, 2C keyword-search to
get IDs, 2D run 2+ SPARQL per database using those IDs, 3A reconstruct the
DB-backed logical flow (results → conclusion) + 3B triage the gaps, 4 score
flow soundness, then deliver the four-part FINAL SUMMARY (main claim /
conclusion / DB-backed flow / gap analysis). Drive 2D with the TogoMCP
run_sparql tool. The query types below were all
run live (bile-acid example) and returned data — copy these, not the reference
doc's printed templates.
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.
- 6d ago First seen · 174 lines · 147 tokens per session scan A 1b926442dbe5
research-article-analysis is a skill published in the GitHub repository dbcls/togomcp (13 stars, last pushed 3d ago), licensed MIT. It adds 147 tokens to every session and 2,642 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
open-ontologies
AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
start-experiment
Start the autoresearch optimization loop for a specific model + lane. Resolves the hierarchical program.md (root → model → lane), asks the user for hardware (local TPU VM or GKE cluster of a specified TPU type + topology), discovers available clusters from .env/, checks occupancy with USERPREFIX-aware attribution…
stop-experiment
Stop the autoresearch optimization loop cleanly. Disarms the launch-armed process watcher, cancels pending wakeups, reaps orphan workloads on the project's cluster pool, files any missing experiment pages, runs lint, and appends a clean-shutdown marker to wiki/log.md. Invoke at the end of an autoresearch session.
edit-model-code
Coding-discipline guidelines for surgically modifying model code inside a per-experiment fork in the autoresearch loop. Adapts Andrej Karpathy's LLM-coding guidelines (think before coding, simplicity first, surgical changes, goal-driven execution) to this project's invariants — no semantics drift, one mechanism per…
author-kernel
Authoring discipline for kernel-family candidates (the author role of kernelexperiments/program.md step K4). Load BEFORE writing any kernel candidate — whether you are a solo agent running the whole K0–K9 loop (production: Gemini / Claude / Codex from a bare prompt) or a dispatched author process in the trial…
formulate-kernel-hypothesis
Generate ONE structured kernel-optimization hypothesis — step K2 of wiki/kernelexperiments/program.md. Self-contained for the kernel lane (any harness, bare-prompt solo or dispatched): reads the K1 bound diagnosis + the kernel index's signal→lever map + the family's refuted layers, and returns a proposal with the…