g-qa

g-qa is a skill for Claude Code from kgiwojno/g-sdd. It costs 73 tokens per session (1,486 once invoked), scanned A, original, MIT.

A post-implementation report that combines review findings and task reports for a completed software feature. It summarizes the issues found across the feature’s separate implementation slices.

In plain words
What is it for?
Use it after implementation to aggregate existing reports into a feature-level quality summary; it does not run tests, scans, or continuous integration.
Why use it?
It gives the team one place to see recurring problems, severity patterns, scope changes, and differences between an agent’s self-report and the final review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions AGENTS.md.

Part of the g-sdd plugin — 11 skills, 4 agents, 11 hooks shipped together

Good fit Use it after implementation to aggregate existing reports into a feature-level quality summary; it does not run tests, scans, or continuous integration.

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

Made for: Claude Code.

Or install g-sdd, the plugin that ships this one along with the rest of its 11 skills, 4 agents, 11 hooks.

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 g-qa

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kgiwojno/g-sdd/g-qa"><img src="https://agentmods.dev/badge/skills/kgiwojno/g-sdd/g-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,486 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 $0.00073 $0.01486
Opus 5 $0.00036 $0.00743
Sonnet 5 $0.00015 $0.00297
Haiku 4.5 $0.00007 $0.00149

Measured 10d ago against content hash 087d3c82f7cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

g-qa 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 10d 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/g-qa/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Behavior

/g-qa is a post-implementation stage, a peer to /g-adr. v1 does document aggregation only — no test execution, no CI, no scanners. The v2+ roadmap — integration tests, accessibility, perf budgets, security scans, feature-flag checks, rollback requirements, licence audit — is tracked for future iterations.

Invoked by /g-implement step 7b after /g-adr completes and before PR creation. Not typically run standalone.

The skill orchestrates: it scopes to the feature, gathers input paths, identifies feature-cycle ADRs via git log, then spawns the g-qa-aggregator named subagent which does the actual aggregation methodology (severity rollups, recurring-finding clustering, scope-drift patterns, per-slice summary, self-vs-final status divergence). The skill echoes the agent's stdout summary on return.

1. Scope to the current feature

Determine the feature name the same way /g-adr's post-implementation mode does — from the caller's feature context or, when run standalone, prompt the user to pick from docs/features/ if there's more than one.

2. Gather inputs

Build the input_paths list to pass to the aggregator:

  • Glob docs/features/[name]/reports/*.md — slice reports.
  • Glob docs/features/[name]/review-reports/*.md — review reports. If a slice has a slice report but no review report (e.g., Blocked slices with review skipped), include the slice report anyway; the aggregator notes the missing review in the per-slice summary.
  • Add docs/features/[name]/PLAN.md for the aggregator's scope-drift cross-reference against Durable Decisions.

Identify ADRs written or updated during this feature's implementation. Scope the git-log to commits unique to the feature branch (between the base branch and the feature branch tip); a plain git log [name] walks the branch's full ancestry and surfaces historical ADRs from before the feature branch existed — noise on long-lived repos.

base=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null \
       | sed 's|^origin/||')
if [ -z "$base" ] && git show-ref --verify --quiet refs/heads/main; then
  base=main
fi
git log "${base}..[name]" --name-only -- docs/adr/

Read the full file on GitHub · 185 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. 10d ago First seen · 185 lines · 73 tokens per session scan A 087d3c82f7cf

Subscribe to this mod's changes

g-qa is a skill published in the GitHub repository kgiwojno/g-sdd (6 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 1,486 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens