A command set for reviewing software changes through five checks: logic, project conventions, build or runtime status, regressions, and performance. It also tracks bugs and build results.

Use it to verify changes, inspect edge cases and race conditions, check naming and patterns, confirm the project runs, look for regressions, and record findings.

It creates a repeatable review gate that can catch incorrect behavior, broken integrations, build failures, and avoidable slowdowns.

qa — Command by xthenyo

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.

agentmods

npx agentmods add commands/xthenyo/game-mcp/qa

Clone the repo

git clone --depth 1 https://github.com/xthenyo/game-mcp

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 576 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00015	$0.00576
Opus 5	$0.00008	$0.00288
Sonnet 5	$0.00003	$0.00115
Haiku 4.5	$0.00002	$0.00058

Measured yesterday against content hash 703dc1180732, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

templates/common/claude/commands/qa.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA

5-check verification gate. Systematically verify every change.

Activation

get_context("QA") -> start from next_task field
claim_task(id, "QA")
Follow agent_prompt exactly
Run the 5-Check Gate
log_decision("QA", "finding", tag="BUG|PERF")
complete_task(id, "QA", self_review="5-check results: X pass, Y fail")

5-Check Verification Gate

Run all 5 checks in order for every review. Report results.

1. Coherence — Is the logic correct?

Is the code logically consistent?
Are edge cases handled? (null, empty, zero, negative)
Any race condition risks?

2. Convention — Does it follow project standards?

All English? Any non-English identifiers/comments?
Correct naming conventions?
Proper patterns used (DI, events, async)?

3. Build — Does it compile/run?

All imports/references correct?
No deprecated APIs?

4. Regression — Does it break existing code?

Does the change affect other systems?
Are existing integrations broken?

5. Performance — Any performance issues?

Expensive operations in hot paths?
Memory allocations in loops?
String concatenation in loops?

6. Error Monitoring (if Sentry configured)

Check Sentry dashboard for new errors after deployment
Verify error breadcrumbs are meaningful
Confirm no PII leaking in error reports
Check error rate trends

Verification Tools

Tool	When to use
`gemini "..."`	Research known issues, best practices for a pattern
Context7 MCP	Check official docs for API correctness (Unity, VContainer, etc.)
Sequential Thinking MCP	Systematic root cause analysis for complex bugs
Sentry MCP (if enabled)	`sentry_search_issues()`, `sentry_get_issue_details()` — production error dashboard

Bug Report Format

id: BUG-XXX
severity: P0|P1|P2|P3
file: "path/to/file:line"
steps: [1, 2, 3]
expected: "..."
actual: "..."
gate_failed: "coherence|convention|build|regression|performance"

Don't

Read the full file on GitHub · 79 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.

yesterday First seen · 79 lines · 15 tokens per session scan A 703dc1180732

Subscribe to this mod's changes

qa is a command published in the GitHub repository xthenyo/game-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 576 once invoked, about $0.0001 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.

Debugging Testing

qa