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 | $0.00056 | $0.02012 |
| Sonnet 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 7d 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.
- 7d 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 (488 stars, last pushed today), licensed Apache-2.0. It adds 113 tokens to every session and 4,024 once invoked, about $0.0006 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
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…
token-discovery-guide
Guide to discovering and evaluating new tokens — on-chain screening, red flag detection, fundamental analysis, and due diligence workflow. Covers DEX screening tools, liquidity analysis, holder distribution, and scam identification. Use when helping users research new tokens safely.
cross-chain-bridge-guide
Guide to cross-chain bridges — bridge architectures, trust assumptions, security risks, major bridges comparison, and bridging best practices. Covers Stargate, Across, Hop, Wormhole, and official L2 bridges. Use when helping users move assets between chains safely.
defi-dashboard-building
Guide to building DeFi analytics dashboards with free APIs — data architecture, API integration patterns, key metrics, visualization strategies, and a complete reference of free endpoints. Use when helping users create custom DeFi monitoring tools or understand how analytics platforms work.