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 Unique-Divine/jiyuu --skill sai-perpsgit clone --depth 1 https://github.com/Unique-Divine/jiyuuWrote 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/unique-divine/jiyuu/sai-perps)<a href="https://agentmods.dev/skills/unique-divine/jiyuu/sai-perps"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/sai-perps/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/unique-divine/jiyuu/sai-perps"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/sai-perps.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 | $0.00109 | $0.01168 |
| Opus 5 | $0.00055 | $0.00584 |
| Sonnet 5 | $0.00022 | $0.00234 |
| Haiku 4.5 | $0.00011 | $0.00117 |
Grade A, and why
sai-perps 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 9d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sai Perps
Use this skill for Sai read/query/reconcile work across protocol state, indexed data, public APIs, database semantics, referral analytics, and app behavior.
Boundaries
Use agent skill sai-ops when a request uploads code, migrates contracts,
executes admin messages, creates or updates referral codes, issues trading
credits, changes production configuration, triggers trades, mutates a sheet, or
writes a state-change changelog. This skill can supply read-only preflight and
postflight checks.
For a Sai Keeper Postgres schema, SQL semantics, or freshness question, read
references/sai-db.md. For direct private database
access, Tailscale/primary-replica routing, or any write operation, also use the
private agent skill sai-db; do not infer connection details from repository
configuration or environment variables.
For Heart Monitor GraphQL transaction messages, custom Wasm events, and ordinary
chain-indexed wallet evidence, use agent skill nibiru-gql. Heart Monitor event
proof establishes the upstream chain input; it does not by itself prove the Sai
Keeper derived-state row or the Sai app-visible balance.
Reference router
| Surface | Use when | Reference |
|---|---|---|
| Live contracts | Protocol state, contract configuration, markets, collaterals, OI limits, fees, vault mappings, deposits, affiliate claimable rewards, and credit balances. | sai-contracts.md |
| SLP Vault contracts | Vault health, collateralization, share price, deposit caps, daily risk state, epochs, withdrawal timing, raw vault state, pending gov fees. | sai-vaults.md |
| Sai Keeper GraphQL | Indexed trades and LP history, app-visible oracle prices, fees, referral history, subscriptions, and user-facing entities. | sai-graphql.md |
| DexPal REST | Public product aggregates, stats, markets, yield, health checks, and date-window metrics. | sai-rest.md |
| Sai Keeper Postgres | Table and column meanings, units, migrations, routines, API implementation, and aggregate freshness. | sai-db.md |
| Cross-source reconciliation | Explaining why chain, GraphQL, REST, DB, sheets, or boku notes disagree. | sai-reconciliation.md |
| Referral checks | Existing referral code ownership, redemption history, sheet metadata, EVM/Bech32 normalization, testnet balance/credit checks. | sai-referrals.md |
What ships with it
8 files 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.
- 9d ago First seen · 89 lines · 109 tokens per session scan A 8fe7199995d9
sai-perps is a skill published in the GitHub repository Unique-Divine/jiyuu (6 stars, last pushed 2d ago), licensed MIT. It adds 109 tokens to every session and 1,168 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
code-navigation
Rapid, focused navigation to locate definitions/usages and map the impact of proposed changes.
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
bridge
Cross-chain token transfers using Wormhole and CCTP.