Borrowing it
Nothing to install: this file belongs to SawyerHood/middleman. 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/SawyerHood/middleman/main/AGENTS.mdgit clone --depth 1 https://github.com/SawyerHood/middlemanWrote 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/sawyerhood/middleman/agents-md)<a href="https://agentmods.dev/instructions/sawyerhood/middleman/agents-md"><img src="https://agentmods.dev/badge/instructions/sawyerhood/middleman/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/sawyerhood/middleman/agents-md"><img src="https://agentmods.dev/badge/instructions/sawyerhood/middleman/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 | $0.01158 | $0.01158 |
| Opus 5.5 | $0.00463 | $0.00463 |
| Sonnet 5.5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
middleman 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Middleman - Agent Notes
What This Project Is
middleman is a local-first multi-agent orchestration platform. It runs:
- A Node.js backend for manager/worker orchestration and persistence.
- A TanStack Start + Vite SPA for dashboard, chat, settings, and artifacts.
- Realtime updates over WebSocket.
Scope Expectations
This is a greenfield project — do not worry about backwards compatibility. Breaking changes to APIs, storage formats, protocols, and UI are fine. Move fast and keep the codebase clean.
For dashboard/chat/settings work, preserve existing behavior and interaction patterns unless the task explicitly requests a redesign.
Architecture (Current)
Frontend
- SPA with TanStack Start + Vite in
apps/ui. - Real-time client state and transport in
apps/ui/src/lib/ws-client.ts. - Core UI surfaces in
apps/ui/src/components/chat/*andapps/ui/src/components/settings/*.
Backend
- HTTP + WebSocket server in
apps/backend/src/ws/server.ts. - Agent orchestration and runtime logic in
apps/backend/src/swarm/*. - Scheduler in
apps/backend/src/scheduler/*.
Contracts
Canonical wire contracts are defined in:
packages/protocol/
Run and Test
Development
pnpm dev
Starts backend + UI in one command (two local ports):
- Backend HTTP + WS:
http://127.0.0.1:47187/ws://127.0.0.1:47187 - UI:
http://127.0.0.1:47188
Production
pnpm prod
Default production ports:
- Backend HTTP + WS:
http://127.0.0.1:47287/ws://127.0.0.1:47287 - UI preview:
http://127.0.0.1:47289
Useful checks
pnpm build
pnpm test
pnpm exec tsc --noEmit
Shadcn UI
Use shadcn/ui for shared UI primitives and new component additions. Always prefer shadcn components over hand-rolled HTML elements.
Add components from the apps/ui directory using the shadcn CLI:
cd apps/ui
pnpm dlx shadcn@latest add <component-name>
For example:
cd apps/ui
pnpm dlx shadcn@latest add button label switch select tabs separator scroll-area checkbox tooltip textarea
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 · 125 lines · 1,158 tokens per session scan A c49236f9a826
middleman AGENTS.md is an instructions file published in the GitHub repository SawyerHood/middleman (184 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,158 tokens to every session, about $0.0046 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.