qa-generator

qa-generator is a skill for Claude Code, Codex from dbcls/togomcp. It costs 186 tokens per session (5,235 once invoked), scanned A, original, MIT.

A workflow for creating or updating benchmark questions for TogoMCP, a system that answers questions by querying biology databases.

In plain words
What is it for?
It is for adding, refreshing, validating, replacing, redirecting, or retiring benchmark questions in the evaluation set.
Why use it?
It helps ensure evaluation questions genuinely require live database access and that their data and calculations are internally consistent.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/dbcls/togomcp/qa-generator
Any agent
npx skills add dbcls/togomcp --skill qa-generator
Clone the repo
git clone --depth 1 https://github.com/dbcls/togomcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for qa-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/dbcls/togomcp/qa-generator.svg)](https://agentmods.dev/skills/dbcls/togomcp/qa-generator)
Your own site
<a href="https://agentmods.dev/skills/dbcls/togomcp/qa-generator"><img src="https://agentmods.dev/badge/skills/dbcls/togomcp/qa-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,235 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00186 $0.05235
Opus 5 $0.00093 $0.02618
Sonnet 5 $0.00037 $0.01047
Haiku 4.5 $0.00019 $0.00524

Measured 5d ago against content hash ebff5511db4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-generator 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 5d 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.

.claude/skills/qa-generator/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TogoMCP Benchmark QA Generator

This skill produces new, fully-validated benchmark questions one at a time, enforcing the type-first creation protocol and the 28-category QA review that the existing 100 questions passed. A question is only useful if it requires live RDF access to answer and is arithmetically self-consistent; this skill exists to guarantee both, not just to emit plausible-looking YAML.

It runs in a Claude Code environment with the TogoMCP MCP server (SPARQL + REST wrappers + TogoID), OLS4 (ontology lookup), and PubMed/NCBI tools connected, plus filesystem access. Use those tools freely — that is the normal mode here. Either TogoMCP server works — they expose the identical tool surface, differing only in the tool prefix (mcp__togomcp-dev__* vs mcp__togomcp__*). Prefer the local togomcp-dev when present because its registry is fresher (it picks up new endpoints.csv rows immediately); the remote togomcp is a fine fallback for the established databases, with the one caveat that its registry can lag, so a recently added database may not be available there yet. OLS4 and PubMed are separate servers, unaffected by which TogoMCP you use.

The Five Hard Rules

1. Nothing is invented. Every SPARQL query in sparql_queries must execute successfully against the real endpoint before it is written. Every result_count, every triple in rdf_triples, and every fact in ideal_answer must come from an actual query result you ran this session. A fabricated count or triple is worse than a missing one — it silently poisons the benchmark.

2. Question scope = query scope (no sampling). If exploration discovers N ontology terms (GO/MONDO/ChEBI/EC/MeSH), the SPARQL VALUES clause must use all N, including all getDescendants(). A "which/how many/list all" question must query the entire set, never a subset. This is the single most common way a question silently becomes wrong — see references/coverage-gaps.md.

Read the full file on GitHub · 184 lines

Files

What ships with it

6 files 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.

Changes

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.

  1. 5d ago First seen · 184 lines · 186 tokens per session scan A ebff5511db4a

Subscribe to this mod's changes

qa-generator is a skill published in the GitHub repository dbcls/togomcp (13 stars, last pushed 2d ago), licensed MIT. It adds 186 tokens to every session and 5,235 once invoked, about $0.0009 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.

Related

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…

fabio-rovai/open-ontologies · 110 tokens

post-cortex-agents

Multi-agent orchestration system for Post-Cortex MCP memory infrastructure. Use when working with persistent memory, knowledge graphs, semantic search, session management, or context building.

julymetodiev/post-cortex · 39 tokens

mcp-sparql

Exposes SPARQL query capabilities to LLMs via the Model Context Protocol. Supports SELECT, ASK, CONSTRUCT, and DESCRIBE queries against any SPARQL endpoint.

daedalus/mcp-sparql · 0 tokens

knowledge-graph-sparql

Knowledge graph construction, SPARQL querying, and entity linking for library and research data management using RDF and Wikidata.

xjtulyc/awesome-rosetta-skills · 31 tokens

investigate-issue

Investigate a GitHub issue by fetching details, analyzing the codebase, researching documentation, and presenting an actionable implementation plan with test guidance. Use when asked to investigate, analyze, triage, or plan work for a GitHub issue. Invoked with /investigate-issue or /investigate-issue (prompts for ID).

maximhq/bifrost · 78 tokens

harness-test-writer

Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…

maximhq/bifrost · 133 tokens