What is gigwa-qc-triage?

A quality-check workflow for an already imported genetic variant set in Gigwa, a database for genetic variation data. It checks whether the set is reliable enough for later analysis.

Checking call rates, sample heterozygosity, and other quality measures for a Gigwa variant set. Use it when the data is already imported and needs review.

It helps identify missing or unreliable genetic measurements before they affect diversity or association results. It gives a clear go/no-go assessment without changing the stored data.

gigwa-qc-triage — Skill for Claude Code and Codex by gkanogiannis

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.

Any agent

npx skills add gkanogiannis/Gigwa-MCP --skill gigwa-qc-triage

Clone the repo

git clone --depth 1 https://github.com/gkanogiannis/Gigwa-MCP

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gkanogiannis/gigwa-mcp/gigwa-qc-triage/github.svg)](https://agentmods.dev/skills/gkanogiannis/gigwa-mcp/gigwa-qc-triage)

Your own site

<a href="https://agentmods.dev/skills/gkanogiannis/gigwa-mcp/gigwa-qc-triage"><img src="https://agentmods.dev/badge/skills/gkanogiannis/gigwa-mcp/gigwa-qc-triage/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gkanogiannis/gigwa-mcp/gigwa-qc-triage"><img src="https://agentmods.dev/badge/skills/gkanogiannis/gigwa-mcp/gigwa-qc-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,098 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00201	$0.01098
Opus 5.5	$0.00080	$0.00439
Sonnet 5.5	$0.00040	$0.00220
Haiku 4.5	$0.00020	$0.00110

Measured 2mo ago against content hash 6ad467343818, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gigwa-qc-triage 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.

skills/gigwa-qc-triage/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gigwa QC triage

Overview

Vet an already-imported variant set and return a go/no-go verdict for downstream analysis. Runs the same read-only QC tools as the import skill, minus the import, then turns the numbers into a recommendation. Drives the gigwa-mcp MCP server's qc_* and audit_import_quality tools.

When to use vs gigwa-import-and-qc

This skill — the data is already in Gigwa; you just need to know if it's trustworthy.
gigwa-import-and-qc — you still need to load the data first (it imports, then runs exactly these QC steps).

Prerequisites

The gigwa-mcp server is connected; read-only, so anonymous access on a public instance is fine.
A variant_set_db_id (MODULE§project§run) from list_variant_sets() (or the gigwa-explore-instance skill).

Step-by-step workflow

Run each step on the same variant_set_db_id, noting the flag to watch:

qc_call_rate(variant_set_db_id) — overall call rate and the worst samples/markers (writes call_rate_samples.csv, call_rate_markers.csv). Watch: entities far below the min_*_call_rate defaults (0.5).
qc_heterozygosity(variant_set_db_id) — per-sample observed heterozygosity; heed the high-Ho warning (contamination, off-types, or a het-miscoding import).
qc_duplicate_accessions(variant_set_db_id) — clones / mislabelled duplicates via pairwise IBS (writes duplicate_pairs.csv, duplicate_groups.csv).
qc_maf_filter(variant_set_db_id) — how many markers a MAF/missingness filter would drop (default maf_threshold=0.05, max_missing=0.5).
audit_import_quality(variant_set_db_id) — confirm there is no genotype-encoding artifact (writes import_quality_scan.csv).

Verdict rubric

Turn the numbers into one of three calls (see references/qc-thresholds.md for the table):

GO — call rates healthy, no Ho outlier cluster, few/no unexpected duplicates, MAF filter drops a reasonable fraction, audit OK.
GO WITH CAVEATS — usable after dropping the worst samples/markers or de-duplicating; state exactly what to remove.
NO-GO — audit BROKEN/SUSPECT, pervasive low call rate, or an implausible heterozygosity/monomorphic profile → fix the import (see gigwa-import-and-qc) before any diversity analysis.

Read the full file on GitHub · 77 lines

Files

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.

references/qc-thresholds.md 3.2 KB

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.

2mo ago First seen · 77 lines · 201 tokens per session scan A 6ad467343818

Subscribe to this mod's changes

gigwa-qc-triage is a skill published in the GitHub repository gkanogiannis/Gigwa-MCP (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 201 tokens to every session and 1,098 once invoked, about $0.0008 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.

Scientific

gigwa-qc-triage next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gigwa-qc-triagegkanogiannis/Gigwa-MCP	Skill	0	1mo ago	Apache-2.0	A	201	Claude Code, 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