What is better-ccflare CLAUDE.md?

Project instructions for better-ccflare, a proxy that distributes Claude requests across multiple account providers to avoid rate limits.

Use them when working on testing, file changes, Git branches, and commits in the better-ccflare repository.

They keep development and testing within the repository's safety rules, protect excluded generated files, and prevent incorrect branch or file operations.

How tombii/better-ccflare configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tombii/better-ccflare. 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/tombii/better-ccflare/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tombii/better-ccflare

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tombii/better-ccflare/claude-md.svg)](https://agentmods.dev/instructions/tombii/better-ccflare/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tombii/better-ccflare/claude-md"><img src="https://agentmods.dev/badge/instructions/tombii/better-ccflare/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,640 This file is loaded in full into every session.

When invoked 3,640 The same file — it is already loaded in full.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin fork From a forked repository.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03640	$0.03640
Opus 5	$0.01820	$0.01820
Sonnet 5	$0.00728	$0.00728
Haiku 4.5	$0.00364	$0.00364

Measured today against content hash f372e2366e98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

better-ccflare CLAUDE.md scanned grade B with 2 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 today.

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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST http://localhost:8081/v1/messages -H "Content-Type: application/json" -H "Authorization: Bearer test" -d '{"model":"z-ai/glm-4.5-air:free","messages":[{"role":"user","content":"test"}],"max_tokens":10}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**NEVER curl the Anthropic endpoint** — not directly, and not via the proxy using the `claude` account. Real Anthropic accounts can get banned for automated/scripted usage. The `claude` account must only be used through

CLAUDE.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Load balancer proxy for Claude distributing requests across multiple account providers to avoid rate limiting.

⚠️ CRITICAL: Testing Restrictions

NEVER curl the Anthropic endpoint — not directly, and not via the proxy using the claude account. Real Anthropic accounts can get banned for automated/scripted usage. The claude account must only be used through real Claude Code. For testing, always use non-Anthropic accounts (ollama, litellm, omniroute, etc.) and force-route with x-better-ccflare-account-id.

⚠️ CRITICAL: File Exclusions

README files - Only modify ./README.md (root) and docs/README.md (docs index). Do NOT modify apps/cli/README.md.

NEVER TOUCH these auto-generated files — must be excluded from all reads, edits, searches, and commits:

packages/proxy/src/inline-worker.ts
packages/database/src/inline-vacuum-worker.ts
packages/database/src/inline-integrity-check-worker.ts

If accidentally modified: git checkout -- <path>

Git Refspecs

This repo has both a main branch and a main tag. Always use refs/heads/main (not main) for local branch operations (push, checkout). For merge-base and log comparisons against the remote, use origin/main (the remote ref) to avoid the ambiguous refspec warning from the local tag.

Branch Management

Always branch from main with a fresh pull. Never make changes directly on main. PRs: gh pr checkout <PR_NUMBER> or git checkout <branch-name>.

If git push origin main fails with src refspec main matches more than one (branch/tag name collision), push explicitly: git push origin refs/heads/main:refs/heads/main.

PR Review Against Current Main (MANDATORY)

Before reviewing or merging any PR, always find the merge base and identify what main has added since the PR branched:

git fetch origin pull/<PR_NUMBER>/head:<branch-name>
git fetch origin main
MERGE_BASE=$(git merge-base <branch-name> origin/main)
git log $MERGE_BASE..origin/main --oneline          # commits on main the PR doesn't have
git diff $MERGE_BASE..origin/main --name-only        # files main changed since PR branched

Read the full file on GitHub · 221 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.

today Changed · +11 tokens per session f372e2366e98
8d ago First seen · 221 lines · 3,629 tokens per session scan B 21537ca84295

Subscribe to this mod's changes

better-ccflare CLAUDE.md is an instructions file published in the GitHub repository tombii/better-ccflare (265 stars, last pushed today), licensed MIT. It adds 3,640 tokens to every session, about $0.0182 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It comes from a forked repository.

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

better-ccflare: Instructions file for Claude Code