sai-perps

sai-perps is a skill for Claude Code, Codex from Unique-Divine/jiyuu. It costs 109 tokens per session (1,168 once invoked), scanned A, original, MIT.

A read-only data skill for checking Sai perpetual-futures markets and reconciling information across blockchain contracts, APIs, databases, and referral records. Perpetual futures are contracts that track an asset’s price without an expiry date.

In plain words
What is it for?
Use it to inspect markets, open interest, fees, trades, vault health, oracle prices, statistics, referral ownership, and historical referral data without changing live state.
Why use it?
It helps compare values from different data sources and distinguish blockchain evidence from indexed database or application data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect markets, open interest, fees, trades, vault health, oracle prices, statistics, referral ownership, and historical referral data without changing live state.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unique-divine/jiyuu/sai-perps
Install

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.

Any agent
npx skills add Unique-Divine/jiyuu --skill sai-perps
Clone the repo
git clone --depth 1 https://github.com/Unique-Divine/jiyuu

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sai-perps

README.md
[![agentmods](https://agentmods.dev/badge/skills/unique-divine/jiyuu/sai-perps/github.svg)](https://agentmods.dev/skills/unique-divine/jiyuu/sai-perps)
Your own site
<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.

agentmods 80×15 button for sai-perps

Your own site · 80×15
<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>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 8fe7199995d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

ai-skills/sai-perps/SKILL.md · 89 lines

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

Read the full file on GitHub · 89 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 89 lines · 109 tokens per session scan A 8fe7199995d9

Subscribe to this mod's changes

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.