rudder AGENTS.md

Repository instructions for Rudder, open-source software for assigning, running, reviewing, and improving work performed by AI agents. They describe its product rules, repository identity, and how to read the project documentation.

In plain words
What is it for?
Use them when changing Rudder’s product logic, documentation, naming, onboarding, or repository structure, especially when legacy Paperclip identifiers need to remain compatible.
Why use it?
They help contributors preserve the product’s intended behavior and avoid confusing the working Rudder project with its template for other projects.

Instructions file for CodexOpenCode

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/undertone0809/rudder/agents-md
Clone the repo
git clone --depth 1 https://github.com/Undertone0809/rudder

Made for: Codex, OpenCode.

Per session 4,019 This file is loaded in full into every session.
When invoked 4,019 The same file — it is already loaded in full.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5 $0.04019 $0.04019
Opus 5 $0.02010 $0.02010
Sonnet 5 $0.00804 $0.00804
Haiku 4.5 $0.00402 $0.00402

Measured 3d ago against content hash b220b6673f7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

rudder AGENTS.md scanned grade C with 2 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.rudder/instances/dev

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:3100/api/health
AGENTS.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for human and AI contributors working in this repository.

1. Purpose

Rudder is open-source software for assigning, running, reviewing, and improving agent work. It connects goals, tasks, knowledge, runs, reviews, budgets, and workflows so agents can work within clear boundaries, collaborate, and move work forward. The current product behavior contract is the guarded Product Logic Registry in doc/product/. The product north-star metric is the weekly count of real agent-work loops successfully completed through Rudder end-to-end.

1.1 Repository Identity

  • This repository began as a Rudder fork/derivative of an early version of Paperclip. When renaming or rebranding internals, prefer compatibility-preserving changes for legacy paperclip* identifiers, config keys, and protocol values unless a deliberate breaking migration is planned.
  • Treat the product description above as the current canonical short introduction when updating README, product docs, and onboarding copy.

2. Read This First

Read docs in layers instead of scanning the whole doc/ tree.

Documentation folders have different audiences:

  • docs/ is the public website documentation. It is user-facing, use-case-led, and written for installation, onboarding, and product understanding.
  • doc/ is internal product, engineering, plans, and archive documentation for contributors working on Rudder itself.

When the task is to improve website docs, edit docs/. When the task is to change contributor/product-development guidance, edit doc/.

Start here for almost every task:

  1. doc/product/PRODUCT.md
  2. doc/product/README.md

Then choose the route that matches the work:

  • Desktop app, packaging, installer, local prod startup:
    • doc/README.md
    • doc/engineering/DESKTOP.md
    • doc/engineering/DEVELOPING.md
    • desktop/scripts/smoke.mjs
    • scripts/prod-desktop.mjs
  • Server/runtime/database work:
    • doc/README.md
    • doc/engineering/DEVELOPING.md
    • doc/engineering/DATABASE.md
    • doc/engineering/DEPLOYMENT-MODES.md
    • relevant doc/product/domains/** contracts when behavior changes
  • CLI/task-surface work:
    • doc/README.md
    • doc/engineering/CLI.md
    • relevant doc/product/domains/issues/**, doc/product/domains/work-routing/**, and doc/product/domains/agents/** contracts
  • Visible UI or interaction design work:
    • doc/README.md
    • doc/product/PRODUCT.md
    • doc/engineering/DESIGN.md
    • relevant doc/product/domains/** contracts for user-visible behavior
  • Release/publishing work:
    • doc/README.md
    • doc/engineering/RELEASING.md
    • doc/engineering/PUBLISHING.md
    • doc/engineering/RELEASE-AUTOMATION-SETUP.md
  • Plugin work:
    • doc/README.md
    • doc/engineering/PLUGIN_AUTHORING_GUIDE.md
    • doc/engineering/PLUGIN_RUNTIME_CONTRACT.md
    • doc/product/domains/plugins/**

Read the full file on GitHub · 357 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.

  1. 3d ago First seen · 357 lines · 4,019 tokens per session scan C b220b6673f7e

Subscribe to this mod's changes

rudder AGENTS.md is an instructions file published in the GitHub repository Undertone0809/rudder (287 stars, last pushed 3d ago), licensed Apache-2.0. It adds 4,019 tokens to every session, about $0.0201 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens