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/Zeekeey-jpeg/LeRoy-HQWrote 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/zeekeey-jpeg/leroy-hq/simulator)<a href="https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/simulator"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/simulator/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/zeekeey-jpeg/leroy-hq/simulator"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/simulator.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 | $0.00070 | $0.02041 |
| Opus 5.5 | $0.00028 | $0.00816 |
| Sonnet 5.5 | $0.00014 | $0.00408 |
| Haiku 4.5 | $0.00007 | $0.00204 |
Grade A, and why
simulator 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simulator Agent - Protocol Compliance Testing
Purpose
Execute protocol compliance tests by submitting questions and validating responses against 5 compliance metrics.
When to Use
- Full simulation runs (250-question validation)
- Batch testing of enforcement fixes
- Regression testing after protocol changes
- Validation of Phase 1/2/3 enforcement implementations
Capabilities
- Submit questions to Claude (simulated user requests)
- Capture full response including timings, state changes, task logs
- Validate gate output, memory recall, agent spawn, response time, answer correctness
- Export results in validation framework JSON format
Tools Available
- Read - Load questions from test-questions.json, read state.json for validation
- Bash - Execute timing measurements, state snapshots
- Grep/Glob - Search for patterns in responses
- TodoWrite - Track batch progress (optional)
Input Format
Receives batch assignment with 5-25 questions:
{
"batch_id": 1,
"questions": [
{
"question_id": "Q001",
"question": "What is Protocol Enforcement v5.6?",
"category": "decisions",
"source_file": "Decisions/Protocol-Enforcement-v5.6.md",
"expected_answer": "Information about Protocol Enforcement v5.6",
"complexity": "trivial"
}
// ... more questions
],
"output_file": ".claude/session/batch-1-results.json"
}
Execution Protocol
1. Initialize Batch
- Read questions from input
- Create state snapshot (baseline)
- Initialize results array
- Start batch timer
2. Per Question Execution
For each question in batch:
A. Pre-Question Setup
- Snapshot current state.json
- Record start timestamp
- Clear any stale enforcement flags
B. Submit Question
- Format as natural user prompt
- Submit to Claude (simulated request)
- Capture full response text
C. Capture Response Data
- Record end timestamp (calculate duration)
- Read updated state.json (memory_system.last_recall, notes_loaded)
- Extract task log (check for Task tool calls with subagent_type)
- Extract answer content (text after [MEMORY] block if present)
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 · 262 lines · 70 tokens per session scan A 99f13ac258d7
simulator is an agent published in the GitHub repository Zeekeey-jpeg/LeRoy-HQ (10 stars, last pushed 16d ago), licensed MIT. It adds 70 tokens to every session and 2,041 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
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…
test-architect
Use after the worktree is prepared to write all failing acceptance tests from the structure. Tests form the immutable scope fence for implementation. Operates inside the implement phase as a sub-step before the implementer runs.
ux-reviewer
Use when live application verification is needed after implementation. Boots the application, interacts with it as a user would, and evaluates the experience. For API-only projects, sends real HTTP requests. Example triggers — "verify the app works", "test the UI", "check the user experience", "smoke test the…
verifier
Use when comprehensive verification checks need to run before completion. Runs all available checks (format, lint, type check, build, tests) in speed order and produces an evidence-based report. Example triggers — "run all checks", "verify the build", "pre-flight checks", "does everything pass".
lead-eng
Senior engineer that implements features per the architecture and writes open tests.
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…