benchflow CLAUDE.md

Project instructions for Benchflow, a research project for building reinforcement-learning environments, training models after initial training, and evaluating them.

In plain words
What is it for?
Working on the Benchflow codebase and following its repository guidance.
Why use it?
They give an agent project-specific guidance, including where to find more instructions. Without the full instructions, the exact rules are unclear.

Instructions file

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.

agentmods
npx agentmods add instructions/benchflow-ai/benchflow/claude-md
Clone the repo
git clone --depth 1 https://github.com/benchflow-ai/benchflow
Per session 11 This file is loaded in full into every session.
When invoked 11 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.00011 $0.00011
Opus 5 $0.00005 $0.00005
Sonnet 5 $0.00002 $0.00002
Haiku 4.5 $0.00001 $0.00001

Measured 3d ago against content hash 6e12224f3c05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

benchflow 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 3d 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.

Origin

This is a copy

88% identical to kaneo CLAUDE.md — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 2 lines

What it actually says

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. 3d ago First seen · 2 lines · 11 tokens per session scan A 6e12224f3c05

Subscribe to this mod's changes

benchflow CLAUDE.md is an instructions file published in the GitHub repository benchflow-ai/benchflow (335 stars, last pushed 3d ago), licensed Apache-2.0. It adds 11 tokens to every session, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to kaneo CLAUDE.md, differing in 6 lines, and is treated as a copy.