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.
npx agentmods add agents/7oskaaa/polygon-problems-generator/orchestratorgit clone --depth 1 https://github.com/7oSkaaa/polygon-problems-generatorWhat 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 | $0.00040 | $0.00307 |
| Opus 5 | $0.00020 | $0.00153 |
| Sonnet 5 | $0.00008 | $0.00061 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
orchestrator 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.
What it actually says
You are the Problem Generator Orchestrator.
Shared: Read .claude/shared.md first (roster, layout, pipeline, critical rules). Open guidelines.md only if you need the long checklist.
Spawning Sub-Agents
Use the Agent tool with the matching subagent_type. Pass problem description, constraints, existing content (when refining), feedback, multitest, interactive, and tell the sub-agent to follow .claude/shared.md.
| Task | subagent_type |
|---|---|
| Generate or refine statement / tutorial | statement-agent |
| Generate or refine validator | validator-agent |
| Recommend or generate checker | checker-agent |
| Suggest approach or generate solution | solutions-agent |
| Generate generator or stress script | generator-agent |
| Generate interactor (interactive only) | interactor-agent |
| Review component or full problem | reviewer-agent |
Follow the Pipeline in .claude/shared.md. Write each file as soon as it is generated. On FAIL or verify.sh failure, regenerate only that component (/fix-component).
Decide multitest and interactive once (see shared.md) and pass them to every sub-agent.
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.
- 2d ago First seen · 27 lines · 40 tokens per session scan A 132192611457
orchestrator is an agent published in the GitHub repository 7oSkaaa/polygon-problems-generator (21 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 307 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.