Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hyperledger-iroha/irohanpx agentmods add skills/hyperledger-iroha/iroha/sora-taira-testnetWrote 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/sora-taira-testnet)<a href="https://agentmods.dev/skills/hyperledger-iroha/iroha/sora-taira-testnet"><img src="https://agentmods.dev/badge/skills/hyperledger-iroha/iroha/sora-taira-testnet/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/sora-taira-testnet"><img src="https://agentmods.dev/badge/skills/hyperledger-iroha/iroha/sora-taira-testnet.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 | $0.00113 | $0.04024 |
| Opus 5.5 | $0.00045 | $0.01610 |
| Sonnet 5.5 | $0.00023 | $0.00805 |
| Haiku 4.5 | $0.00011 | $0.00402 |
Grade A, and why
sora-taira-testnet 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SORA Taira Testnet
Use the Taira testnet through native Torii MCP.
Quick Start
- Confirm a Taira MCP server is available in the current Codex environment.
- Treat
https://taira.sora.orgas the primary public Torii/API origin on the current deployment andhttps://taira.sora.org/v1/mcpas its native MCP endpoint. - Before long or stateful writes, sample public health first. Prefer proceeding only when blocks are advancing,
queue_sizeis low,tx_queue_saturated=false, andteu_dataspace_backlogis not climbing. - Prefer curated
iroha.*tools over rawtorii.*tools. - Stay read-only until the user explicitly asks to mutate live state.
- Treat any signing inputs, API tokens, or forwarded auth headers as runtime-only secrets.
MCP Endpoint
Use the public Taira MCP endpoint:
https://taira.sora.org/v1/mcp
The matching public Torii/API root is:
https://taira.sora.org
If the endpoint is not configured locally, instruct the user to add a user-local MCP entry that points at that URL.
If the endpoint returns 404, report that native Torii MCP is not enabled on
the deployment yet and stop before attempting live-network actions.
If the MCP endpoint or the public Torii root returns 502 or 503, report
public ingress / rollout health degradation before attempting writes. Treat
that as deployment health, not user input failure.
If reads work but live writes fail with route_unavailable, report that the
public ingress still cannot reach authoritative peers for the target lane and
point operators at
configs/soranexus/taira/check_mcp_rollout.sh --public-root https://taira.sora.org --write-config <runtime-only client.toml>.
For that runtime-only signer config, prefer
configs/soranexus/taira/taira-canary-client.example.toml; the generic
defaults/client.toml targets the zero chain id and is not valid for Taira.
When --write-config is omitted, the rollout scripts now bootstrap
/run/secrets/taira-canary-client.toml automatically by generating a fresh
ordinary signer, onboarding it on Taira, and attempting an initial faucet claim
before the write canary. For that public onboarding flow, keep aliases
dataspace-scoped like <label>@universal; do not invent domain-scoped aliases
such as @wonderland.universal.
If the rollout is still using hand-edited validator configs, point them at
configs/soranexus/taira/validator_roster.example.toml,
configs/soranexus/taira/validator_secrets.example.toml, and
python3 scripts/render_taira_validator_bundle.py --roster ... --secrets ... --output-dir ...
so every validator shares the same trusted_peers / trusted_peers_pop roster.
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.
- 1mo ago First seen · 364 lines · 113 tokens per session scan A 10ffe83fb502
sora-taira-testnet is a skill published in the GitHub repository hyperledger-iroha/iroha (489 stars, last pushed 2d ago), licensed Apache-2.0. It adds 113 tokens to every session and 4,024 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
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…
web3-audit
Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for…
TronScan Data Lookup
Query TRON blockchain data via the TronScan API — accounts, transactions, tokens, blocks, contracts, transfers, and chain statistics.
zerion-wallet-data
Use when the user asks to check a wallet's portfolio, token balances, DeFi positions, PnL, transaction history, or NFTs. Provides interpreted on-chain data across 40+ EVM chains and Solana via x402 pay-per-request or API key — no raw RPC decoding needed.