What is ccflare AGENTS.md?

Repository guidance for ccflare, a Bun and TypeScript monorepo, meaning one repository containing multiple related packages, for an AI service proxy. It describes the workspace layout, engineering standards, and core proxy features.

Working on provider HTTP or WebSocket proxying, account failover, session selection, SQLite persistence, and changes across the monorepo.

It gives an agent the project’s source of truth for package ownership, design choices, and checks before handing work back.

ccflare AGENTS.md — Instructions file by snipeship

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/snipeship/ccflare/agents-md

Clone the repo

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

Made for: Codex, OpenCode.

Per session 2,406 This file is loaded in full into every session.

When invoked 2,406 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.02406	$0.02406
Opus 5	$0.01203	$0.01203
Sonnet 5	$0.00481	$0.00481
Haiku 4.5	$0.00241	$0.00241

Measured 2d ago against content hash 2dd4968645de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

AGENTS.md · 419 lines

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, and codex
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.md
docs/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

Read the full file on GitHub · 419 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.

2d ago First seen · 419 lines · 2,406 tokens per session scan A 2dd4968645de

Subscribe to this mod's changes

ccflare AGENTS.md is an instructions file published in the GitHub repository snipeship/ccflare (1,039 stars, last pushed 4mo ago), licensed MIT. It adds 2,406 tokens to every session, about $0.0120 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.

anthropic-api anthropic-claude claude claude-api claude-code codex

ccflare AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Engineering Standard

What This Repo Is

Reading Order

What this file has done since we first saw it

Other instructions, from other repositories

open-managed-agents AGENTS.md

Claude-PHP-SDK copilot-instructions.md

claude-code-templates CLAUDE.md

claude-code-hub CLAUDE.md

1flowbase AGENTS.md

claudecodeui AGENTS.md