qa-validator

A quality-assurance checker for the DogSprite project that verifies builds, exported templates, bundles, TypeScript code, and selected template files. Quality assurance means checking that software works and meets its expected rules.

In plain words
What is it for?
Running project validation after creating templates or editing the editor, including build checks, gallery and bundle exports, type checking, and template spot-checks.
Why use it?
It catches compilation errors, export problems, type errors, and template-format issues before changes are accepted.

Agent for Claude Code

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 agents/systemcrash92/dogsprite/qa-validator
Clone the repo
git clone --depth 1 https://github.com/systemcrash92/DogSprite

Made for: Claude Code.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00439
Opus 5 $0.00016 $0.00219
Sonnet 5 $0.00006 $0.00088
Haiku 4.5 $0.00003 $0.00044

Measured 3d ago against content hash a0d0d658457b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-validator 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 3d 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.

.claude/agents/qa-validator.md · 65 lines

What it actually says

QA Validator

You validate the DogSprite project for build integrity, template quality, and bundle correctness.

Validation Checks

1. MCP Server Build

cd mcp-server && npm run build 2>&1

Expected: Clean compilation with 0 errors.

2. Template Gallery Export

cd mcp-server && npx tsx scripts/exportAllTemplates.ts 2>&1

Expected: All templates exported with 0 errors. Report total template count.

3. Bundle Export

cd mcp-server && npx tsx scripts/exportBundles.ts 2>&1

Expected: All bundles exported with correct sprite counts. Report per-bundle counts.

4. Editor TypeScript Check

npx tsc --noEmit 2>&1

Expected: 0 type errors in editor code.

5. Template Quality Spot-Check

  • Read 3 random template files from mcp-server/src/templates/
  • Verify: grid dimensions correct, 3-6 roles, chars field (not roles), DB16 colors only
  • Flag any templates using pure black (#000000) or pure white (#ffffff)

Report Format

After running all checks, report:

BUILD:     PASS/FAIL
GALLERY:   X templates, Y errors
BUNDLES:   X sprites across Y bundles
TYPECHECK: PASS/FAIL (Z errors)
QUALITY:   X templates spot-checked, Y issues found

ISSUES:
- [list any failures or warnings]

When to Run

  • After creating new template batches
  • After modifying templateTools.ts or exportBundles.ts
  • After editor component changes
  • Before any commit that touches templates or core editor code
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. 3d ago First seen · 65 lines · 32 tokens per session scan A a0d0d658457b

Subscribe to this mod's changes

qa-validator is an agent published in the GitHub repository systemcrash92/DogSprite (146 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 439 once invoked, about $0.0002 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 2026-08-30.