origin-dollar: Skill for Claude Code

.claude/skills/optimize-ousd-allocation/SKILL.md

optimize-ousd-allocation is a skill for Claude Code from OriginProtocol/origin-dollar. It costs 170 tokens per session (4,245 once invoked), scanned A, original, MIT.

A finance workflow that analyzes how OUSD funds are divided among several on-chain lending, liquidity, and vault strategies. It recommends how to rebalance those funds to increase estimated annual USDC earnings while preserving required redemption liquidity.

In plain words
What is it for?
Use it to evaluate current OUSD allocation, compare strategy yields and constraints, identify proposed transfers, and prepare a rebalancing plan for a human-controlled multisig transaction.
Why use it?
Capital spread across different strategies can earn different rates and may have different liquidity limits. This workflow compares the available choices and produces a proposed set of moves without executing them.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: positional $N argument.

This is OriginProtocol/origin-dollar's own configuration. It tells Claude Code how to work on origin-dollar itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything origin-dollar configures →

Reuse

Borrowing it

Nothing to install: this file belongs to OriginProtocol/origin-dollar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/OriginProtocol/origin-dollar/master/.claude/skills/optimize-ousd-allocation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/OriginProtocol/origin-dollar

Made for: Claude Code.

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 optimize-ousd-allocation

README.md
[![agentmods](https://agentmods.dev/badge/skills/originprotocol/origin-dollar/optimize-ousd-allocation/github.svg)](https://agentmods.dev/skills/originprotocol/origin-dollar/optimize-ousd-allocation)
Your own site
<a href="https://agentmods.dev/skills/originprotocol/origin-dollar/optimize-ousd-allocation"><img src="https://agentmods.dev/badge/skills/originprotocol/origin-dollar/optimize-ousd-allocation/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 optimize-ousd-allocation

Your own site · 80×15
<a href="https://agentmods.dev/skills/originprotocol/origin-dollar/optimize-ousd-allocation"><img src="https://agentmods.dev/badge/skills/originprotocol/origin-dollar/optimize-ousd-allocation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,245 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00170 $0.04245
Opus 5.5 $0.00068 $0.01698
Sonnet 5.5 $0.00034 $0.00849
Haiku 4.5 $0.00017 $0.00424

Measured 1mo ago against content hash d800cc6f5e6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

optimize-ousd-allocation 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/backcheck.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/optimize-ousd-allocation/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OUSD Allocation Optimizer

Autonomously find the OUSD collateral allocation that maximizes total annual USDC earnings across every bucket, then output an executable rebalancing plan. No user input required.

You produce a plan; you never execute moves. Relocating funds is a Strategist-multisig action. Deliverable = the net moves + expected $/yr gain, for a human to sign.

Base lineage: this skill merges a production-grounded rebalancer (the ousdConstraints gates, greedy step algorithm, freeze guards, spread-floor knowledge) with (a) an independent on-chain verification layer — we do not fully trust the MCP — (b) AMO coverage, (c) the sustainable-vs-transient rate correction, and (d) a persistent learning loop.

TODO — known gaps

  • AMO realized APY not wired. No data source for the Curve OUSD/USDC AMO's fee+gauge yield. Hold AMO at its 10% floor; flag opportunity cost only. AMO-vs-Morpho yield tradeoffs are out of scope until closed.

The buckets

  • Ethereum Morpho (chain 1) — MetaMorpho vault over Blue markets (OETH/USDC + others), OETH/USDC hard-capped at 90% util.
  • Base Morpho (chain 8453) — cross-chain (CCTP), bridge-slow.
  • HyperEVM Morpho (chain 999) — cross-chain (CCTP), bridge-slow.
  • Curve OUSD/USDC AMO — redemption/peg liquidity; ≥10% of TVL floor. (Omitted by the base rebalancer — do not omit it; it's ~15% of collateral.)
  • OUSD Vault buffer — idle USDC (0% APY) and the withdrawal queue.

Core principle — optimize dollars, and sustainable dollars

Objective: maximize TotalYield = Σ(balanceᵢ × APYᵢ) (annual USDC). Relocation keeps total AUM fixed, so this equals maximizing blended OUSD APY. Marginal APY only orders candidate moves; the accept/reject gate is always the global TotalYield delta — never a single strategy's rate.

Value each market at its sustainable rate (rate at 90% target utilization), not a transient spot spike. Withdrawing spikes a market's rate above target; that reverts within hours as borrowers repay. See references/methodology.md §3, §9. Do not credit a withdrawn source's remaining balance at its spiked rate — that's the classic bug that tells you to drain a market.

Read the full file on GitHub · 157 lines

Files

What ships with it

7 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. 1mo ago First seen · 157 lines · 170 tokens per session scan A d800cc6f5e6f

Subscribe to this mod's changes

optimize-ousd-allocation is a skill published in the GitHub repository OriginProtocol/origin-dollar (153 stars, last pushed today), licensed MIT. It adds 170 tokens to every session and 4,245 once invoked, about $0.0007 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 2026-09-04.