ccflare is a proxy server that forwards Anthropic and OpenAI API requests to multiple provider accounts without translating their request formats. It routes requests by URL prefix, balances traffic, retries rate-limited accounts, and records request and usage information. The catalogue instructions relate to configuring and operating the proxy for coding-agent APIs.
Borrowing it
Nothing to install: this file belongs to snipeship/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.
curl -O https://raw.githubusercontent.com/snipeship/ccflare/main/AGENTS.mdgit clone --depth 1 https://github.com/snipeship/ccflareWrote 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/snipeship/ccflare/agents-md)<a href="https://agentmods.dev/instructions/snipeship/ccflare/agents-md"><img src="https://agentmods.dev/badge/instructions/snipeship/ccflare/agents-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.
<a href="https://agentmods.dev/instructions/snipeship/ccflare/agents-md"><img src="https://agentmods.dev/badge/instructions/snipeship/ccflare/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02406 | $0.02406 |
| Opus 5.5 | $0.00962 | $0.00962 |
| Sonnet 5.5 | $0.00481 | $0.00481 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
ccflare AGENTS.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 1mo 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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for code agents working in this repository.
This file is the repo-local source of truth for:
- workspace structure
- package ownership
- commands to run before handing work back
- DRY / refactor expectations
- where to look in
docs/before making architectural changes
Engineering Standard
Always optimize for code that is:
- clear to read
- easy to maintain
- appropriately DRY
- locally coherent
- boring in the good sense
Prefer small, obvious abstractions over clever ones. Remove repetition when it reduces maintenance cost, but do not introduce generic helper layers that make the code harder to follow than the duplication they replace.
The target is not “maximum abstraction.” The target is code that a strong engineer can understand and modify quickly without guessing at hidden behavior.
What This Repo Is
ccflare is a Bun/TypeScript monorepo for a multi-provider AI proxy.
Core product behavior:
- provider-native HTTP passthrough for
anthropic,openai,claude-code, andcodex - WebSocket proxying for supported upstreams
- account failover and session-based selection
- SQLite-backed request/account/auth-session persistence
- management API
- browser dashboard
- terminal UI
High-level docs:
Reading Order
If you are changing behavior, read in this order:
README.mddocs/architecture.md- the domain-specific doc for your area
Use these targeted references:
- API/control plane:
docs/api-http.md - runtime/request flow:
docs/data-flow.md - provider behavior:
docs/providers.md - config rules:
docs/configuration.md - database/persistence:
docs/database.md - load-balancing/session strategy:
docs/load-balancing.md - TUI behavior:
docs/tui.md - deployment/paths/build outputs:
docs/deployment.md - contribution expectations:
docs/contributing.md
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.
- 1mo ago First seen · 419 lines · 2,406 tokens per session scan A 2dd4968645de
ccflare AGENTS.md is an instructions file published in the GitHub repository snipeship/ccflare (1,052 stars, last pushed 6mo ago), licensed MIT. It adds 2,406 tokens to every session, about $0.0096 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.