A quality-assurance sign-off command that checks a change against its acceptance criteria, runs tests, probes unusual cases, and gives a ship or no-ship decision. Acceptance criteria are the conditions a change must meet.

Use it after implementation to verify normal and invalid inputs, concurrent use, regressions, and the main user path.

It catches behavior problems that a code-diff review may miss by actually running the software and checking related features before release.

qa — Command for Claude Code by fatihkan

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.

Clone the repo

git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 81 skills, 86 commands, 30 agents, 7 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/fatihkan/badi/qa.svg)](https://agentmods.dev/commands/fatihkan/badi/qa)

Your own site

<a href="https://agentmods.dev/commands/fatihkan/badi/qa"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/qa.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 460 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	$0.00000	$0.00460
Opus 5	$0.00000	$0.00230
Sonnet 5	$0.00000	$0.00092
Haiku 4.5	$0.00000	$0.00046

Measured today against content hash 611a43d2424d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 today.

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/commands/qa.md · 44 lines

What it actually says

QA sign-off command. Verifies a change against acceptance criteria, runs the test suite, probes edge cases, and issues a ship / no-ship verdict via the qa-lead agent.

Required Tools

Read (change, specs, acceptance criteria)
Grep / Glob (locate affected tests and behavior)
Bash (run the test suite, exercise the CLI/app)
Agent (delegate to qa-lead)

When to Use

After implementation, before /ship. Run this to get an evidence-backed verdict on whether the change is safe to release. Complements /review (which reads the diff) by actually executing and judging behavior.

Procedure

Step 1: Establish Acceptance Criteria

Derive checkable criteria from the spec, /eng-review plan, or the user's intent.
If criteria are unclear, state the assumptions being verified.

Step 2: Delegate to QA Lead

Launch the qa-lead agent. Ask it to:

Map the change to each acceptance criterion (PASS/FAIL).
Run the project's full test suite and capture real pass/fail counts.
Probe edge cases (empty, max, invalid, concurrent) and negative paths.
Check for regressions in adjacent features.
Smoke-test the primary user path.

Step 3: Collect Evidence

Ensure every PASS/FAIL cites the command run and its real output. A skipped check is reported as skipped; a flaky/failing test blocks SHIP.

Step 4: Issue the Verdict

SHIP — all criteria pass, suite green, no regressions.
SHIP WITH RISK — passes with a named, accepted risk.
NO-SHIP — blocking issues; list exactly what must be fixed.

Step 5: Record

Add the verdict and any blocking issues to the task board.
On NO-SHIP, route defects back to the implementing agent.

Output Format

Verdict (SHIP / SHIP WITH RISK / NO-SHIP)
Acceptance Criteria (each PASS/FAIL + evidence)
Test Run (pass/fail counts + quoted failures)
Edge & Regression Findings
Blocking Issues (if any)

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.

today First seen · 44 lines · 0 tokens per session scan A 611a43d2424d

Subscribe to this mod's changes

qa is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 460 tokens. 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 2026-09-06.

Code review Testing agents ai-workflow cli developer-tools hooks

qa