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/finesssee/proxypilot/agents-mdgit clone --depth 1 https://github.com/Finesssee/ProxyPilotWrote 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/finesssee/proxypilot/agents-md)<a href="https://agentmods.dev/instructions/finesssee/proxypilot/agents-md"><img src="https://agentmods.dev/badge/instructions/finesssee/proxypilot/agents-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 | $0.01058 | $0.01058 |
| Opus 5 | $0.00529 | $0.00529 |
| Sonnet 5 | $0.00212 | $0.00212 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
ProxyPilot 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 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.
This is a copy
100% identical to CLIProxyAPI AGENTS.md — 1 line 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Go 1.26+ proxy server providing OpenAI/Gemini/Claude/Codex compatible APIs with OAuth and round-robin load balancing.
Repository
Commands
gofmt -w . # Format (required after Go changes)
go build -o cli-proxy-api ./cmd/server # Build
go run ./cmd/server # Run dev server
go test ./... # Run all tests
go test -v -run TestName ./path/to/pkg # Run single test
go build -o test-output ./cmd/server && rm test-output # Verify compile (REQUIRED after changes)
- Common flags:
--config <path>,--tui,--standalone,--local-model,--no-browser,--oauth-callback-port <port>
Config
- Default config:
config.yaml(template:config.example.yaml) .envis auto-loaded from the working directory- Auth material defaults under
auths/ - Storage backends: file-based default; optional Postgres/git/object store (
PGSTORE_*,GITSTORE_*,OBJECTSTORE_*)
Architecture
cmd/server/— Server entrypointinternal/api/— Gin HTTP API (routes, middleware, modules)internal/api/modules/amp/— Amp integration (Amp-style routes + reverse proxy)internal/thinking/— Main thinking/reasoning pipeline.ApplyThinking()(apply.go) parses suffixes (suffix.go, suffix overrides body), normalizes config to canonicalThinkingConfig(types.go), normalizes and validates centrally (validate.go/convert.go), then applies provider-specific output viaProviderApplier. Do not break this "canonical representation → per-provider translation" architecture.internal/runtime/executor/— Per-provider runtime executors (incl. Codex WebSocket)internal/translator/— Provider protocol translators (and sharedcommon)internal/registry/— Model registry + remote updater (StartModelsUpdater);--local-modeldisables remote updatesinternal/store/— Storage implementations and secret resolutioninternal/managementasset/— Config snapshots and management assetsinternal/cache/— Request signature cachinginternal/watcher/— Config hot-reload and watchersinternal/wsrelay/— WebSocket relay sessionsinternal/usage/— Usage and token accountinginternal/tui/— Bubbletea terminal UI (--tui,--standalone)sdk/cliproxy/— Embeddable SDK entry (service/builder/watchers/pipeline)test/— Cross-module integration tests
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 · 59 lines · 1,058 tokens per session scan A a01f8eb7ece7
ProxyPilot AGENTS.md is an instructions file published in the GitHub repository Finesssee/ProxyPilot (261 stars, last pushed 2mo ago), licensed MIT. It adds 1,058 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to CLIProxyAPI AGENTS.md, differing in 1 line, and is treated as a copy.
Other instructions, from other repositories
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
botmux CLAUDE.md
Claude Code instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules：共享还是独立（改前必读） and 编译态（单文件二进制）注意.
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
happier CLAUDE.md
Claude Code instructions for happier-dev/happier, covering claude code and typescript commands.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).