unify AGENTS.md

A project instruction file for Unify, the central coordination system for an AI assistant. It explains how a central actor directs specialized managers for contacts, knowledge, tasks, transcripts, guidance, and other state.

In plain words
What is it for?
Use it when setting up Unify locally or changing its manager system, tool loops, interruptible work, knowledge and guidance records, or related Python SDK components.
Why use it?
It gives coding agents the system design and local development information needed to work in a distributed assistant backend. It also clarifies how managers, tools, plans, and related SDKs connect.

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/unifyai/unify/agents-md
Clone the repo
git clone --depth 1 https://github.com/unifyai/unify

Made for: Codex, OpenCode.

Per session 36,949 This file is loaded in full into every session.
When invoked 36,949 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 $0.36949 $0.36949
Opus 5 $0.18475 $0.18475
Sonnet 5 $0.07390 $0.07390
Haiku 4.5 $0.03695 $0.03695

Measured 2d ago against content hash 6c0dc918d50e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

unify 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 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/unifyai/unify/staging/scripts/install.sh | bash

Makes network callslowCapability

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

curl -fsSL https://raw.githubusercontent.com/unifyai/unify/staging/scripts/install.sh | bash
AGENTS.md · 2,766 lines

How it starts

The opening of the file, as written. The whole thing — 2,766 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unify

The assistant's brain, and the cognitive core of the platform.

Read ARCHITECTURE.md first for the system design. This file covers how to work on the code, not what the code does.

What Unify is

Unify implements an AI assistant's brain as a distributed back office. A central Actor orchestrates specialized state managers (ContactManager, KnowledgeManager, TaskScheduler, TranscriptManager, GuidanceManager, FunctionManager, ...) through code-first plans. Most public manager methods run inside an async LLM tool loop and return a steerable handle that supports ask, interject, pause, resume, stop — all the way down the nesting tree. Typed catalogues such as Knowledge and Guidance expose direct CRUD/lifecycle methods as Actor JSON tools (KnowledgeManager_*, GuidanceManager_*) rather than NL tool loops or primitives.*.

Sibling repos consumed via editable installs (see [tool.uv.sources] in pyproject.toml):

  • unisdk — Python SDK wrapping the Orchestra REST API
  • unillm — LLM client with caching, provider normalization, observability

The open agent runtime (unify, unisdk, unillm) talks to the hosted Orchestra backend (ORCHESTRA_URL, default https://api.unify.ai/v0). orchestra and console are private/hosted and are not part of the open-source repo set.

Unify consumes data from Orchestra via unisdk, makes LLM calls via unillm, and triggers external actions through the hosted communication stack in unify-deploy. Console provides observability into its operations.

Read the full file on GitHub · 2,766 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. 2d ago First seen · 2,766 lines · 36,949 tokens per session scan C 6c0dc918d50e

Subscribe to this mod's changes

unify AGENTS.md is an instructions file published in the GitHub repository unifyai/unify (132 stars, last pushed 5d ago), licensed MIT. It adds 36,949 tokens to every session, about $0.1847 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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