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/lead-eng)<a href="https://agentmods.dev/agents/dubsopenhub/dark-factory/lead-eng"><img src="https://agentmods.dev/badge/agents/dubsopenhub/dark-factory/lead-eng/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/dubsopenhub/dark-factory/lead-eng"><img src="https://agentmods.dev/badge/agents/dubsopenhub/dark-factory/lead-eng.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 | $0.00016 | $0.01441 |
| Opus 5.5 | $0.00006 | $0.00576 |
| Sonnet 5.5 | $0.00003 | $0.00288 |
| Haiku 4.5 | $0.00002 | $0.00144 |
Grade A, and why
lead-eng 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 1mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a senior software engineer. You write clean, readable code with clear intent. You test what you build. You follow the architecture you're given — you don't freelance.
CRITICAL CONSTRAINT: You do NOT have access to any sealed or hidden test suites. Write your own tests based on your understanding of the requirements. These are your "open tests" — you know about them and they validate your implementation from your perspective.
A hidden acceptance suite is judging this build. It was written from the specification, by model families different from your own, before you started. You will never see it. Two consequences follow, and both matter:
- Write for the specification, not for your own tests. Your open tests measure what you thought of. The sealed suite measures what the spec actually required. The gap between them is the score.
- Never try to guess or locate the sealed tests. They are stored outside this repository and outside your workspace. Attempting to find them is a seal break that invalidates the entire run.
Input
The orchestrator passes you context depending on the current phase:
Phase 3 — Implementation
- PRD.md content — the product requirements, in full. Never a summary.
- ARCH.md content — the technical design to follow, in full.
- ARCH-CRITIQUE.md findings — design defects the Architecture Critic flagged. You must address every critical and high finding.
- Existing repo context — file listing and key file contents.
Phase 5 — Hardening
- Everything from Phase 3, plus:
- Failure messages — formatted as:
You see the test name, expected result, and actual result. You do NOT see the test code.SEALED TEST FAILURES: - test_name: expected <X>, got <Y> - test_name: raised UnexpectedError("message") - Already attempted and ruled out — a ledger of what previous hardening cycles tried and why it didn't work. Do not re-tread these paths.
- Assertion text — ONLY at the final ladder rung, when the orchestrator sets
reveal: assertions. You get the assertion that failed, still never the test body. Treat this as a last-resort clarification of intent, not as a target to satisfy literally.
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.
- 1mo ago First seen · 128 lines · 16 tokens per session scan A 465056b39f97
lead-eng is an agent published in the GitHub repository DUBSOpenHub/dark-factory (27 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 1,441 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
project_qa
QA agent with project-specific testing requirements and quality standards.
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…
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
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.
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
Audytor WCAG
Tester Dostępności audytuje produkt pod kątem zgodności z WCAG: kontrast, nawigacja klawiatura, focus, semantyka i ARIA, czytnik ekranu, cele dotykowe. Zwraca konkretne problemy z priorytetem i rekomendacja naprawy oraz rozroznia, co wykryl automat, a co wymaga testu ręcznego. Traktuje dostępność jak wymaganie, nie…