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 skills add berkayoztunc/orquestra --skill orquestra-simulatorgit clone --depth 1 https://github.com/berkayoztunc/orquestraWrote 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/skills/berkayoztunc/orquestra/orquestra-simulator)<a href="https://agentmods.dev/skills/berkayoztunc/orquestra/orquestra-simulator"><img src="https://agentmods.dev/badge/skills/berkayoztunc/orquestra/orquestra-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/skills/berkayoztunc/orquestra/orquestra-simulator"><img src="https://agentmods.dev/badge/skills/berkayoztunc/orquestra/orquestra-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 | $0.00077 | $0.00411 |
| Opus 5 | $0.00039 | $0.00205 |
| Sonnet 5 | $0.00015 | $0.00082 |
| Haiku 4.5 | $0.00008 | $0.00041 |
Grade A, and why
orquestra-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 12d 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
Orquestra Simulator
Pre-signature dry-run skill. Uses ONLY the Orquestra simulate_instruction MCP tool.
Constraints
- ONLY call
simulate_instruction - DO NOT build a transaction directly — receive
build_instructionoutput from the conductor - DO NOT sign or send anything (no signer-mcp tools)
- DO NOT invent accounts, args, or fee payers — propagate them as-is
- ALWAYS surface the decoded Anchor error when one is present
Procedure
- Receive from the conductor:
projectId,instruction,accounts,args,feePayer,network - Call
simulate_instructionwith those exact inputs - Branch on
success:- success → report compute units + risk level, hand off to
orquestra-signer - failure → lead with
decodedError(or rawerr), show last 5 log lines, STOP the pipeline
- success → report compute units + risk level, hand off to
Output Format
Simulation Result
- Project / Instruction / Network
- ✅ success or ❌ failure
- Compute units (when present)
- Risk level + reasons
On failure
- Decoded Anchor error:
<name>(code<code>) —<msg> - OR raw err:
<json> - Recent logs (last 5 lines)
Handoff
- →
orquestra-signeron success - → STOP on failure, surface error to user
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.
- 12d ago First seen · 43 lines · 77 tokens per session scan A 85cecb8401a8
orquestra-simulator is a skill published in the GitHub repository berkayoztunc/orquestra (23 stars, last pushed 25d ago), licensed MIT. It adds 77 tokens to every session and 411 once invoked, about $0.0004 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 skills, from other repositories
foundry-solidity
Build and test Solidity contracts with Foundry. Use when developing Ethereum contracts, writing Forge tests, deploying with scripts, or debugging with Cast/Anvil. Triggers on forge, cast, anvil, foundry.toml, .t.sol, or .s.sol.
surfpool
Complete Surfpool development environment for Solana - drop-in replacement for solana-test-validator with mainnet forking, cheatcodes, Infrastructure as Code, and Surfpool Studio. The fastest way to develop and test Solana programs.
solana-dev
Solana development: Anchor and Pinocchio programs, Kit clients, wallet flows, testing. Use when building a Solana dapp or program (e.g. write Anchor escrow, create SPL token, wallet-standard login, debug PDA, deploy to devnet).
web3-testing
Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.