origin-dollar: Skill for Claude Code

.claude/skills/fork-test/SKILL.md

fork-test is a skill for Claude Code from OriginProtocol/origin-dollar. It costs 16 tokens per session (4,738 once invoked), scanned A, original, MIT.

A generator for Foundry fork tests that run smart-contract code against copied state from a real blockchain network. These tests check integrations that simplified fake components cannot represent accurately.

In plain words
What is it for?
Use it to test contract interactions with live on-chain state, including deposits, withdrawals, rebalancing, router swaps, oracle reads, and bridge flows.
Why use it?
It helps verify behavior involving real pools, swaps, price feeds, rewards, and cross-chain flows rather than relying only on mocks. It keeps fork tests concrete because network calls make repeated fuzz testing slow.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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/fork-test/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 fork-test

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/originprotocol/origin-dollar/fork-test"><img src="https://agentmods.dev/badge/skills/originprotocol/origin-dollar/fork-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,738 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 $0.00016 $0.04738
Opus 5.5 $0.00006 $0.01895
Sonnet 5.5 $0.00003 $0.00948
Haiku 4.5 $0.00002 $0.00474

Measured 12d ago against content hash 50890c5b8c26, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fork-test 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 12d 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.

.claude/skills/fork-test/SKILL.md · 403 lines

How it starts

The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fork Test Skill

Generate Foundry fork tests for a specific contract, validating behavior against real on-chain state. Fork tests complement unit tests for paths that mocks cannot faithfully reproduce — AMO pool interactions, real router swaps, oracle reads, gauge rewards, and cross-chain flows. Follow the guidelines below to ensure consistency and maintainability across our fork test suite.

1. Directory Layout

contracts/tests/fork/<category>/<ContractName>/
├── shared/
│   └── Shared.t.sol          # Abstract base with setUp, fork creation, deploy, helpers
└── concrete/
    ├── Deposit.t.sol          # One file per integration scenario
    ├── Withdraw.t.sol
    └── Rebalance.t.sol

NEVER fuzz/ directory — fork tests are concrete only (RPC calls make fuzz runs prohibitively slow).

Fewer files than unit tests: Only create files for functions with meaningful integration behavior (pool interactions, swaps, bridge flows). Simple setters, view functions, and access control are covered by unit tests.

<category> matches the subdirectories already in contracts/tests/fork/ (strategies, vault, token, etc.).

One file per integration scenario

Each file tests one public/external function's interaction with real on-chain state. The file name uses PascalCase matching the function name (e.g. deposit() → Deposit.t.sol).

Do NOT create fork test files for:

  • Functions already fully covered by unit tests with no external protocol dependency
  • Simple setters, view functions, access control, constructor validation, pure math

2. Inheritance Chain

forge-std/Test
  └─ Base  (contracts/tests/Base.t.sol)  — actors, constants, fork IDs, contract refs
       └─ BaseFork  (contracts/tests/fork/BaseFork.t.sol)  — fork creation helpers
            └─ Fork_<Contract>_Shared_Test  (shared/Shared.t.sol)  — abstract; setUp, deploy, helpers
                 └─ Fork_Concrete_<Contract>_<Feature>_Test  (concrete/*.t.sol)
  • Base creates actors (alice, bobby, …, governor, strategist, etc.) and declares constants, IERC20 external token refs, and fork IDs (forkIdMainnet, forkIdBase, forkIdArbitrum). Base only contains actors, constants, IERC20 external tokens, fork IDs, and setUp(). All typed contract/proxy/mock state variables are declared in each Shared.t.sol file.
  • BaseFork provides _createAndSelectFork<Chain>() helpers that read RPC URLs from environment variables and create Foundry forks.
  • Fork_<Contract>_Shared_Test is abstract and owns all deployment + configuration logic on top of the fork.
  • Concrete test contracts inherit Fork_<Contract>_Shared_Test directly — no extra layers.

Read the full file on GitHub · 403 lines

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. 12d ago Changed · -8 lines 50890c5b8c26
  2. 1mo ago First seen · 411 lines · 16 tokens per session scan A f4fa64b4dc03

Subscribe to this mod's changes

fork-test is a skill published in the GitHub repository OriginProtocol/origin-dollar (153 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 4,738 once invoked, about $0.0001 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.