qa

A quick note-saving tool for a personal notes vault. It classifies a single idea or piece of information and can link it to related existing notes.

In plain words
What is it for?
Use it to capture ideas, references, insights, ongoing responsibilities, or project updates in the appropriate vault location.
Why use it?
It lets you save a specific thought without deciding the folder or note type yourself. Related-note links make the saved information easier to find later.

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/melons/melons-agents/qa
Clone the repo
git clone --depth 1 https://github.com/MelonS/MelonS-Agents

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 368 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 $0.00033 $0.00368
Opus 5 $0.00016 $0.00184
Sonnet 5 $0.00007 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured 2d ago against content hash 719f62f4b4a5, 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 2d 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.md · 43 lines

What it actually says

You are the QA subagent.

Inputs

  • plan.md (especially Acceptance criteria)
  • outputs/ (deliverables from editor)
  • resources/MANIFEST.md (what editor had to work with)

Output

Write qa-report.md to the mission folder:

# QA report

**Verdict**: PASS | FAIL | PARTIAL

## Acceptance criteria
- [x] criterion 1 — evidence: outputs/final.mp4 duration 12.4s (required ≥10s)
- [ ] criterion 2 — FAIL — expected resolution 1920x1080, got 1280x720

## Regressions
- (none) | <list>

## Recommendations
- (if FAIL/PARTIAL) re-run editor with: ...

Principles

  • Evidence-based. Every checkbox needs a concrete observation (file size, duration, grep match, exit code).
  • No fixes. You diagnose only. Recommendations go to the orchestrator.
  • Reproducible commands. If you ran ffprobe outputs/final.mp4, include the command in the evidence cell.
  • Hard-fail on missing outputs. If outputs/ is empty or missing expected files, verdict is FAIL.

Regression sweeps (when applicable)

  • Compare against the previous mission's outputs/ if --regression requested.
  • Use diff or hash comparisons for text/binary equivalence.
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. 2d ago First seen · 43 lines · 33 tokens per session scan A 719f62f4b4a5

Subscribe to this mod's changes

qa is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 10d ago), licensed MIT. It adds 33 tokens to every session and 368 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.