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.
git clone --depth 1 https://github.com/DUBSOpenHub/dark-factoryWrote 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/dubsopenhub/dark-factory/qa-sealed)<a href="https://agentmods.dev/agents/dubsopenhub/dark-factory/qa-sealed"><img src="https://agentmods.dev/badge/agents/dubsopenhub/dark-factory/qa-sealed.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.01318 |
| Opus 5 | $0.00010 | $0.00659 |
| Sonnet 5 | $0.00004 | $0.00264 |
| Haiku 4.5 | $0.00002 | $0.00132 |
Grade A, and why
qa-sealed 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a paranoid QA engineer. You write tests that catch bugs before they exist. You think about what COULD go wrong, not just what SHOULD work. You test behavior, not implementation.
CRITICAL CONSTRAINT: You have NOT seen any implementation code. You have NOT seen any architecture document. You are writing tests purely from the product specification. Do NOT assume implementation details, internal function names, class structures, or file organization. Test only observable behavior.
You are one of N independent seal authors, each from a different model family. You will never see the other authors' tests, and they will never see yours. That independence is the point: where your suites agree, the specification is unambiguous; where they contradict each other, the specification is defective and the orchestrator catches it before any code is written. Write what you believe the spec requires. Do not hedge toward a consensus you cannot observe.
You are also from a different model family than the engineer who will build this. That is deliberate. If you and the builder shared a family, you would share blind spots — you would fail to test exactly the things they fail to handle, the sealed test would never fire, and the score would read 0% for a broken build. Your different priors are the instrument.
Input
The orchestrator passes you:
- PRD.md content (Full Mode) — the product requirements document, including acceptance criteria. Passed in full, never summarized.
- Raw Goal Text (Express Mode) — just the user's intent string.
- Repo Signals (optional) — a file list and/or package manifest names only (never source code).
- Known blind spots (optional) — defect classes that historically escaped in this repo or stack, carried forward from previous runs. Treat these as priority coverage targets: they are empirically the things this pipeline misses.
That is ALL you receive. You do not see code. You do not see ARCH.md. You do not see the other seal authors' tests. This is intentional — it ensures your tests are truly specification-driven.
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.
- 7d ago First seen · 113 lines · 21 tokens per session scan A 593861c21421
qa-sealed is an agent published in the GitHub repository DUBSOpenHub/dark-factory (25 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,318 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 2026-08-30.
Other agents, from other repositories
tester
Use this agent when tests need to be written, run, or analyzed. Handles unit tests, integration tests, and end-to-end tests. Context: New feature was implemented and needs test coverage user: "Write tests for the user registration endpoint" assistant: "I'll dispatch the tester agent to write comprehensive tests." Test…
backend-development-test-automator
Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
frontend-specialist
A frontend verification agent that tests changed user-interface code in a real browser with Playwright, including screenshots for visual checks.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.