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 agentmods add instructions/edholofy/dojo.md/claude-mdgit clone --depth 1 https://github.com/edholofy/dojo.mdWrote 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/instructions/edholofy/dojo.md/claude-md)<a href="https://agentmods.dev/instructions/edholofy/dojo.md/claude-md"><img src="https://agentmods.dev/badge/instructions/edholofy/dojo.md/claude-md.svg" alt="Measured on agentmods" 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 | $0.03168 | $0.03168 |
| Opus 5 | $0.01584 | $0.01584 |
| Sonnet 5 | $0.00634 | $0.00634 |
| Haiku 4.5 | $0.00317 | $0.00317 |
Grade A, and why
dojo.md 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 5d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
dojo.md — Training arena for AI agents. Scenario-based evaluation with mock services, LLM-judged assertions, and automatic skill generation. Supports any model via OpenRouter with auto-training loops.
Development Commands
npm run dev # Run CLI via tsx (e.g., npm run dev -- train stripe-refunds)
npm run build # Compile TypeScript
npm run test # Run vitest
npm run start # Run compiled CLI
Environment
Requires .env file (gitignored):
ANTHROPIC_API_KEY=sk-ant-... # Required for Anthropic models (claude-*)
OPENROUTER_API_KEY=sk-or-... # Required for OpenRouter models (openai/*, meta-llama/*, etc.)
The Anthropic SDK auto-reads ANTHROPIC_API_KEY from env. Load .env before running:
source .env && npx tsx src/cli/index.ts train stripe-refunds
Architecture
Scenario YAML → Loader → Engine → Mock Layer → Evaluator → Skill Generator
↕ ↕
SQLite Recorder ModelClient (Anthropic / OpenRouter)
Key Files
| File | Purpose |
|---|---|
src/types/index.ts |
All core type definitions |
src/types/schemas.ts |
Zod schemas for YAML validation |
src/engine/loader.ts |
Parse + validate YAML scenarios |
src/engine/runner.ts |
Execute single scenario against mocks |
src/engine/arena-runner.ts |
Arena benchmarking — multi-model fair comparison |
src/engine/training.ts |
Orchestrate full training run (levels, eval, skill gen) |
src/engine/training-loop.ts |
Auto-training loop with convergence detection |
src/engine/agent-bridge.ts |
Drive agent via ModelClient + skill context injection |
src/engine/model-client.ts |
ModelClient interface + createModelClient() factory |
src/engine/anthropic-client.ts |
Anthropic SDK implementation of ModelClient |
src/engine/openrouter-client.ts |
OpenRouter (OpenAI SDK) implementation of ModelClient |
src/engine/model-utils.ts |
Model string parsing, slug generation, API key validation |
src/mocks/session.ts |
MockSession — isolated state per scenario run |
src/mocks/stripe.ts |
Stripe mock handlers (4 tools) |
src/mocks/registry.ts |
Tool registry + normalized tool definitions |
src/evaluator/judge.ts |
Deterministic + LLM-judged assertions |
src/generator/skill-generator.ts |
Produce per-model SKILL.md from failure patterns |
src/recorder/db.ts |
SQLite persistence with model tracking |
src/mcp/server.ts |
MCP server (6 tools) |
src/cli/index.ts |
CLI entry point |
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.
- 5d ago First seen · 272 lines · 3,168 tokens per session scan A fc9a08f7b428
dojo.md CLAUDE.md is an instructions file published in the GitHub repository edholofy/dojo.md (9 stars, last pushed 4mo ago), licensed MIT. It adds 3,168 tokens to every session, about $0.0158 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 instructions, from other repositories
evalscope AGENTS.md
AGENTS.md instructions for modelscope/evalscope, covering agents.md, setup, build, lint, test, docs generation and quick eval.
langwatch CLAUDE.md
Claude Code instructions for langwatch/langwatch, covering langwatch, before you implement anything, development environment, running with no container runtime and local dev by hostname — thuishaven / portless (recommended).
Eval CLAUDE.md
Instructions for ai-twinkle/Eval, covering twinkle eval — 專案規範手冊（claude.md）, 目錄, 1. 專案定位與設計理念, 1.1 誕生背景 and 1.2 核心設計哲學.
scorio AGENTS.md
AGENTS.md instructions for mohsenhariri/scorio, covering agents.md, common commands, python (scorio/), julia (julia/scorio.jl/) and javascript / typescript (js/scorio/).
tracelens CLAUDE.md
Instructions for ssf0409/tracelens, covering tracelens - development guide, project overview, ownership boundary, tracelens owns and downstream projects own.
Hegelion CLAUDE.md
Instructions for Hmbown/Hegelion, covering claude.md, what is hegelion, build & development commands, install dependencies (uv recommended) and run all tests.