Borrowing it
Nothing to install: this file belongs to MelonS/MelonS-Agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MelonS/MelonS-Agents/main/.claude/agents/qa.mdgit clone --depth 1 https://github.com/MelonS/MelonS-AgentsWrote 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.
[](https://agentmods.dev/agents/melons/melons-agents/qa)<a href="https://agentmods.dev/agents/melons/melons-agents/qa"><img src="https://agentmods.dev/badge/agents/melons/melons-agents/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.
<a href="https://agentmods.dev/agents/melons/melons-agents/qa"><img src="https://agentmods.dev/badge/agents/melons/melons-agents/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00033 | $0.00368 |
| Opus 5.5 | $0.00013 | $0.00147 |
| Sonnet 5.5 | $0.00007 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
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 2mo 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.
What it actually says
You are the QA subagent.
Inputs
plan.md(especiallyAcceptance 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--regressionrequested. - Use
diffor hash comparisons for text/binary equivalence.
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.
- 2mo ago First seen · 43 lines · 33 tokens per session scan A 719f62f4b4a5
qa is an agent published in the GitHub repository MelonS/MelonS-Agents (17 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 368 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
CocoScout
Background context ranker. Triggered before Build stages and direct persona invocations to inject relevant CocoPlus context without loading the full context library.
CocoPull
Lossless context distillation agent. Produces dense pull artifacts that preserve decision-bearing facts from large files.
etyb-cartographer
Decision-memory and repo-map curator. Delegate to it after significant merges, at the end of substantial sessions, or when .etyb/memory/ needs maintenance — it refreshes the repo map (architecture, module ownership, test entry points, active plans), appends decision-log entries, compacts stale memory, and merges…
cognitive-fragment-integrator
A tool that combines five or more separate notes or fragments into an existing higher-level document. It reads the document and fragments together, then proposes where each fragment belongs and drafts matching text.
archivist
Memory investigation, synthesis, and authorized curation when surfaced memories are insufficient.
project-memory
Ask to manage project memory documents — list, read, write, or search .md files in the project memory directory.