wagmi-bench: Instructions file for Claude Code

CLAUDE.md

wagmi-bench CLAUDE.md is an instructions file for Claude Code from Dolores-Research/wagmi-bench. It costs 1,772 tokens per session, scanned A, original, Apache-2.0.

Instructions for WAGMI Bench, a local test that replays recorded Bitcoin futures-market periods to evaluate how an agent handles trading risk. It records decisions, trades, accounting, and results in tamper-resistant reports.

In plain words
What is it for?
Use them when running crash scenarios, comparing an agent with baseline strategies, or producing reports from frozen market data.
Why use it?
They keep benchmark results focused on observed survival and risk control rather than unsupported claims about predicting prices or future returns. They also define repeatable steps for demos, scenarios, baselines, and model comparisons.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is Dolores-Research/wagmi-bench's own configuration. It tells Claude Code how to work on wagmi-bench 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 wagmi-bench configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Dolores-Research/wagmi-bench. 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/Dolores-Research/wagmi-bench/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Dolores-Research/wagmi-bench

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 wagmi-bench CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dolores-research/wagmi-bench/claude-md/github.svg)](https://agentmods.dev/instructions/dolores-research/wagmi-bench/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dolores-research/wagmi-bench/claude-md"><img src="https://agentmods.dev/badge/instructions/dolores-research/wagmi-bench/claude-md/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 wagmi-bench CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dolores-research/wagmi-bench/claude-md"><img src="https://agentmods.dev/badge/instructions/dolores-research/wagmi-bench/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,772 This file is loaded in full into every session.
When invoked 1,772 The same file — it is already loaded in full.
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 $0.01772 $0.01772
Opus 5 $0.00886 $0.00886
Sonnet 5 $0.00354 $0.00354
Haiku 4.5 $0.00177 $0.00177

Measured 10d ago against content hash b0f19fdac3db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wagmi-bench CLAUDE.md 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 10d 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.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — WAGMI Bench

WAGMI Bench is a local, deterministic BTC perpetual-futures survival benchmark: it replays recorded market windows, feeds an agent point-in-time observations, and seals decisions, risk checks, fills, ledgers, and metrics into a verifiable evidence bundle. Results are survival-stress evidence — liquidation survival, drawdown control, funding drag, turnover, rule-following. When reporting a result, never state or imply predictive ability, expected future returns, or adoption; say what survived, what was liquidated, and how it read against the baselines on frozen data. Bundles and reports are immutable: every --output must be a path that does not exist yet, and nothing inside a bundle is ever edited. AGENTS.md has the fuller reference; this file is the short version.

When the user asks X, do Y

User asks Do
"does this thing work / show me a report" Keyless demo below (fixture, no keys).
"run the crash packs" / names a scenario packs listfetch-data --pack ID → run baselines + candidate → compare.
"benchmark GPT/Claude/a model on this" --agent llm-local with the user's key; surface the cost estimate before confirming.
"wire in my strategy/bot" wagmibench init → implement decide()--agent http --agent-url.
"wire my EvoSkill skills in" TRADEVOLVE_AGENT_MODE=evoskill + agents.server, then --agent llm --agent-url.
"here's my strategy in markdown" Not a supported input; it must be SKILL.md format first.
"how did my agent do vs baselines" compare over the candidate + baseline bundles on the same pack; read the tier.
"is this result real / can you verify it" replay --bundle --pack; require verdict COMPLETE.
"share this result" wagmibench share --bundle DIR --output DIR (redacted sub-bundle).

Setup

uv sync --group dev

Run everything from the repository root as uv run wagmibench ....

Keyless demo

uv run wagmibench run --pack fixtures/golden-mini/pack --output bundles/demo
uv run wagmibench report --bundle bundles/demo --output reports/demo
open reports/demo/report.html   # Linux: xdg-open

Read the full file on GitHub · 163 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. 10d ago First seen · 163 lines · 1,772 tokens per session scan A b0f19fdac3db

Subscribe to this mod's changes

wagmi-bench CLAUDE.md is an instructions file published in the GitHub repository Dolores-Research/wagmi-bench (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,772 tokens to every session, about $0.0089 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens