What is gigwa-explore-instance?

A read-only skill for surveying a Gigwa server, a system for storing and analyzing genetic variation data. It checks the connection, lists available databases, projects, and analysis runs, and flags possible import problems.

Use it to discover available data, obtain the exact identifiers needed by other Gigwa analyses, switch servers for the session, and spot runs that may have been imported incorrectly.

It gives you a clear inventory and basic health check before you begin genetic-data analysis on an unfamiliar or inherited server.

gigwa-explore-instance — Skill by gkanogiannis/Gigwa-MCP

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-explore-instance

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-explore-instance/github.svg)](https://agentmods.dev/skills/gkanogiannis/gigwa-mcp/gigwa-explore-instance)

Your own site

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

Per session 181 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,015 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	$0.00181	$0.01015
Opus 5.5	$0.00072	$0.00406
Sonnet 5.5	$0.00036	$0.00203
Haiku 4.5	$0.00018	$0.00102

Measured 2mo ago against content hash 88df22ee38f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gigwa-explore-instance 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-explore-instance/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gigwa explore instance

Overview

A one-shot survey of a whole Gigwa instance plus a health check: confirm you can reach it, enumerate everything on it with the exact ids later analyses need, and flag any run that was imported badly. Drives the gigwa-mcp MCP server's discovery and audit tools. No arguments required.

When to use

First contact with an unknown or inherited Gigwa server; "what's here and is any of it broken?"
To obtain the variantSetDbIds that every other skill (gigwa-qc-triage, gigwa-diversity-report, gigwa-region-scan) needs.

Prerequisites

The gigwa-mcp server is connected. Read-only; works anonymously against the configured GIGWA_URL (defaults to the public ICARDA instance when unset).

Step-by-step workflow

(Optional) Point at a different server — gigwa_connect(url, profile?, anonymous?) switches the active Gigwa instance at runtime (no restart). Credentials come from the environment (default GIGWA_USER/GIGWA_PASS, or GIGWA_USER_<PROFILE>/ GIGWA_PASS_<PROFILE> when a profile is named) — never from the chat. The switch is verified before it takes effect and lasts for the session.
Connectivity — gigwa_server_info(): confirms the URL is reachable and reports the server version and the authenticated user (or anonymous).
Enumerate —
- list_content(): human-readable databases → projects → runs.
- list_variant_sets(): every run with its exact variantSetDbId and variant/ call-set counts. This is where you copy ids for downstream skills.
Health check — audit_import_quality() with no variant_set_db_id scans the whole instance and ranks every run OK / SUSPECT / BROKEN (writes import_quality_scan.csv).
Summarise what data is available (databases, projects, runs, sizes) and call out anything that needs attention (broken/suspect runs, empty projects).

Interpreting results

list_content is the human view; list_variant_sets is the id-bearing view — use both.
In the audit, BROKEN runs should not be analysed until re-imported; SUSPECT runs warrant a closer QC pass (gigwa-qc-triage).
The catalog://tools and gigwa://server/info MCP resources are complementary, network-free ways to inspect capabilities and configured connection info.

Read the full file on GitHub · 71 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/instance-anatomy.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 · 71 lines · 181 tokens per session scan A 88df22ee38f2

Subscribe to this mod's changes

gigwa-explore-instance is a skill published in the GitHub repository gkanogiannis/Gigwa-MCP (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 181 tokens to every session and 1,015 once invoked, about $0.0007 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-explore-instance next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gigwa-explore-instancegkanogiannis/Gigwa-MCP	Skill	0	1mo ago	Apache-2.0	A	181	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