LiteLLM Agent Control Plane provides one place to call several coding-agent systems, including OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, and DeepAgents. It is for users who need to work with these agents through a shared control point.
Borrowing it
Nothing to install: this file belongs to LiteLLM-Labs/litellm-agent-control-plane. 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/LiteLLM-Labs/litellm-agent-control-plane/main/AGENTS.mdgit clone --depth 1 https://github.com/LiteLLM-Labs/litellm-agent-control-planeWrote 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/litellm-labs/litellm-agent-control-plane/agents-md)<a href="https://agentmods.dev/instructions/litellm-labs/litellm-agent-control-plane/agents-md"><img src="https://agentmods.dev/badge/instructions/litellm-labs/litellm-agent-control-plane/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 5.1 | $0.00339 | $0.00339 |
| Opus 5 | $0.00169 | $0.00169 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
litellm-agent-control-plane 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 8d 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.
What it actually says
AGENTS.md
Before making implementation changes, read and follow the repo-wide
CODING_STANDARDS.md.
First-time setup
Run once after cloning to activate the committed git hooks:
git config core.hooksPath .githooks
The pre-commit hook keeps model_prices_backup.json in sync with the
upstream litellm JSON on every commit. It warns and skips silently if
the network is unavailable — it never blocks a commit.
MCP integration invariants
mcp_server_ids (in AgentDraft) is the sole source of truth for which
MCP integrations are attached to an agent.
createInputFromDraftmust derivemcp_serversandmcp_toolsettool entries exclusively frommcp_server_ids. Never readmcp_toolsetentries back out ofdraft.toolsto build the output — those may be stale.- Strip all
mcp_toolsetentries fromdraft.toolsbefore buildingallTools, then append fresh toolsets fromresolvedMcpServers. - Only emit a toolset for an ID that resolved to a known
INTEGRATIONSentry. An ID with no matching integration produces no toolset and no server URL.
On the backend (runtime_provision.rs), integration_mcp_toolsets must
cross-check each toolset's mcp_server_name against the resolved mcp_servers
list. Any toolset whose server name is absent from mcp_servers is dropped.
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.
- 8d ago First seen · 34 lines · 339 tokens per session scan A 3d8f96924a36
litellm-agent-control-plane AGENTS.md is an instructions file published in the GitHub repository LiteLLM-Labs/litellm-agent-control-plane (1,278 stars, last pushed 2mo ago), licensed MIT. It adds 339 tokens to every session, about $0.0017 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.
Other instructions, from other repositories
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.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.