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 hyperledger-iroha/iroha --skill mochi-local-sandboxgit clone --depth 1 https://github.com/hyperledger-iroha/irohaWrote 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/hyperledger-iroha/iroha/mochi-local-sandbox)<a href="https://agentmods.dev/skills/hyperledger-iroha/iroha/mochi-local-sandbox"><img src="https://agentmods.dev/badge/skills/hyperledger-iroha/iroha/mochi-local-sandbox/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/hyperledger-iroha/iroha/mochi-local-sandbox"><img src="https://agentmods.dev/badge/skills/hyperledger-iroha/iroha/mochi-local-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.00791 |
| Opus 5 | $0.00041 | $0.00396 |
| Sonnet 5 | $0.00016 | $0.00158 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
mochi-local-sandbox 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 8d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mochi Local Sandbox
Use Mochi as the local Iroha devnet launcher and MCP bridge.
Quick Start
- Start the sandbox from the target workspace:
scripts/mochi_local_sandbox.sh up- Use
MOCHI_WORKSPACE_ROOT=/path/to/appwhen the current shell is not already in the app workspace. - Use
MOCHI_PROFILE=four-peer-bftwhen the user wants the four-validator rehearsal instead of the defaultsingle-peer.
- Confirm the sandbox is healthy:
scripts/mochi_local_sandbox.sh status- Healthy means
status: ready,ready: true, andmcp_ready: true. stale-sessionmeanssession.jsonexists but the detached Mochi process is gone; inspectserve.logand rerunuporreset.
- If Codex needs the local MCP endpoint, print the exact add command:
scripts/mochi_local_sandbox.sh mcp-add-command
- Use the workspace bootstrap artifacts:
.env.local.mochi/generated/typescript/connect.ts.mochi/generated/rust/connect.rs.mochi/generated/kotlin/MochiConnect.kt
Working Rules
- Prefer Mochi's curated local
iroha.*MCP tools. Do not prefer rawtorii.*tools when the local MCP surface is healthy. - Treat
.env.local,session.json, and any generatedIROHA_PRIVATE_KEYvalue as runtime-only local-dev material. Do not commit them or copy them into permanent docs. - Use
scripts/mochi_local_sandbox.sh envwhen you need copy/paste shell exports for a local app. - Use
scripts/mochi_local_sandbox.sh resetwhen the local chain must be wiped and regenerated. - Expect generated local configs to enable
[torii.mcp]with the curated writer profile and[torii.transport.norito_rpc]withenabled = true,require_mtls = false, andstage = "ga". - If
upfails, inspect:scripts/mochi_local_sandbox.sh status<workspace>/.mochi/sandbox/<profile>/serve.log<workspace>/.mochi/sandbox/<profile>/session.jsonwhen it exists<workspace>/.mochi/sandbox/<profile>/serve.pidwhenstatusreportsstale-session
- If readiness smoke fails, treat
serve.logas authoritative. The smoke path updates metadata on the existingwonderland.universaldomain and confirms commit through block/event streams plus HTTP transaction-status fallback. - If the user wants a custom non-preset profile, prefer the GUI or direct
mochi sandbox serveflow instead of stretching the helper script beyondsingle-peerandfour-peer-bft.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 49 lines · 82 tokens per session scan A 3d743841b957
mochi-local-sandbox is a skill published in the GitHub repository hyperledger-iroha/iroha (488 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 791 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 2026-09-03.
Other skills, from other repositories
lineth-quickstart
Operating manual for the Lineth Stack quickstart — the Docker-Compose dev/demo stack at docs/getting-started/lineth-stack in the lineth-monorepo that boots a local Linea/Lineth L2 with Sepolia or local L1 finality. Use whenever you are working inside the lineth-stack quickstart and need to boot or run the stack…
docker-compose
Multi-container Docker applications with docker-compose — define services, networks, volumes, and orchestrate local development environments.
blockchain-dlt
Architect and audit Distributed Ledger/Blockchain systems and Smart Contracts.
onchain-data-analysis
On-chain data analysis skill for Etherscan, Dune Analytics, and blockchain explorers.
sui-and-move-tools
Use to get bytecode for a deployed Sui package and produce a disassembled working view. One GraphQL call fetches every module's raw bytecode bytes; sui move disassemble (already on the system, running sui prompt) produces .asm files for analysis. Trigger on "fetch this package's bytecode", "get me the .mv for package…
implementing-container-image-minimal-base-with-distroless
Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime with no shell, package manager, or unnecessary OS utilities.