sumo-qa-closing-qa-gaps

sumo-qa-closing-qa-gaps is a skill for Claude Code from sumithr/sumo-qa. It costs 100 tokens per session (2,787 once invoked), scanned A, original, Apache-2.0.

A workflow for closing one known QA gap at a time with a failing test, the smallest necessary change, and a passing result. A QA gap is a concrete behaviour that currently has no covering test.

In plain words
What is it for?
Use it to drive one uncovered behaviour from evidence of failure through implementation, a passing regression test, and a status update.
Why use it?
It turns review findings, mutation survivors, or failed scenarios into verified regression coverage instead of leaving them as unresolved notes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sumo-qa plugin — 20 skills, 2 agents, 3 hooks, 1 MCP server shipped together

Good fit Use it to drive one uncovered behaviour from evidence of failure through implementation, a passing regression test, and a status update.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sumithr/sumo-qa/sumo-qa-closing-qa-gaps
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 sumithr/sumo-qa --skill sumo-qa-closing-qa-gaps
Clone the repo
git clone --depth 1 https://github.com/sumithr/sumo-qa

Made for: Claude Code.

Or install sumo-qa, the plugin that ships this one along with the rest of its 20 skills, 2 agents, 3 hooks, 1 MCP server.

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 sumo-qa-closing-qa-gaps

README.md
[![agentmods](https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-closing-qa-gaps/github.svg)](https://agentmods.dev/skills/sumithr/sumo-qa/sumo-qa-closing-qa-gaps)
Your own site
<a href="https://agentmods.dev/skills/sumithr/sumo-qa/sumo-qa-closing-qa-gaps"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-closing-qa-gaps/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.

agentmods 80×15 button for sumo-qa-closing-qa-gaps

Your own site · 80×15
<a href="https://agentmods.dev/skills/sumithr/sumo-qa/sumo-qa-closing-qa-gaps"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-closing-qa-gaps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,787 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00100 $0.02787
Opus 5 $0.00050 $0.01393
Sonnet 5 $0.00020 $0.00557
Haiku 4.5 $0.00010 $0.00279

Measured 9d ago against content hash 7e72af5147b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sumo-qa-closing-qa-gaps 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 9d 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/sumo-qa-closing-qa-gaps/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Closing QA gaps

QA evidence — a review's uncovered risk, an unmet acceptance criterion, a mutation survivor, a graded-scenario failure — has named a concrete behaviour with no covering test. This skill drives it to closure one loop at a time (red → minimum change → green → status update), orchestrating the existing disciplines — never replacing them.

Announce at the start of EVERY turn while this skill is active — entry, red, green, status-update, refusal, and decline turns all open with: "Closing one QA gap at a time." A turn that skips the announce has left the loop discipline.

Output discipline (mandatory)

Inherits the global discipline from using-sumo-qa: output discipline (no internal taxonomy labels), output economy (findings not framing; one question per turn; no closing pleasantries), knowledge authority hierarchy, specialty-tool fit.

The Iron Law

ONE GAP PER LOOP, EVIDENCE AT BOTH ENDS. The red (failing) output is captured before any production change; the green output plus targeted regression is captured before the gap's status moves. A second gap starts only when the user explicitly asks. This skill NEVER declares a change safe to merge — that verdict belongs to sumo-qa-reviewing-before-merge, against fresh evidence.

Read the full file on GitHub · 94 lines

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. 9d ago First seen · 94 lines · 100 tokens per session scan A 7e72af5147b0

Subscribe to this mod's changes

sumo-qa-closing-qa-gaps is a skill published in the GitHub repository sumithr/sumo-qa (6 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 2,787 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

live-audit

Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…

Grinv/steam-games-mcp · 83 tokens

pr-quality-cycle

Combined PR quality workflow: address inline review comments AND fix Codecov patch coverage gaps in one end-to-end cycle. Use when a PR has both review feedback and coverage regression, or when you want a single checklist that covers triage, code fixes, test additions, verification, and push-gate validation before…

Anselmoo/mcp-ai-agent-guidelines · 67 tokens

qa

QA test a live website with Axon discovery/content evidence plus browser automation when interaction is required. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.

dinglebear-ai/axon · 52 tokens

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

harness-engineering-lifecycle

Design, implement, and integrate generalized validation harnesses across a producer-consumer boundary after a local harness contract exists. Use when refactoring custom validation CLIs/MCPs for large polyrepos, extending Steward across sibling repos, or deploying a local tool to a consumer project for dogfooding and…

Arenukvern/mcp_flutter · 88 tokens