aif-handoff AGENTS.md

aif-handoff AGENTS.md is an instructions file for Codex, OpenCode from lee-to/aif-handoff. It costs 3,614 tokens per session, scanned A, original, MIT.

A project map for an autonomous task-management system with a Kanban board and AI subagents. A monorepo is one repository containing multiple related packages and applications.

In plain words
What is it for?
Working on task workflows, agent adapters, the API, database, React interface, state machine, and tests.
Why use it?
It shows the system's workflow stages, technology choices, package layout, and available AI runtimes so changes fit the existing design.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

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/lee-to/aif-handoff/agents-md
Clone the repo
git clone --depth 1 https://github.com/lee-to/aif-handoff

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for aif-handoff AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lee-to/aif-handoff/agents-md.svg)](https://agentmods.dev/instructions/lee-to/aif-handoff/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lee-to/aif-handoff/agents-md"><img src="https://agentmods.dev/badge/instructions/lee-to/aif-handoff/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,614 This file is loaded in full into every session.
When invoked 3,614 The same file — it is already loaded in full.
Security scan A 0 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 5.1 $0.03614 $0.03614
Opus 5 $0.01807 $0.01807
Sonnet 5 $0.00723 $0.00723
Haiku 4.5 $0.00361 $0.00361

Measured 6d ago against content hash 17c951cc566b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

aif-handoff 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 6d 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.

AGENTS.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project map for AI agents. Keep this file up-to-date as the project evolves.

Project Overview

Autonomous task management system with Kanban board and AI subagents. Tasks flow through stages automatically (Backlog → Planning → Plan Ready → Implementing → Review → Done), each handled by runtime-resolved workflows (Claude adapter first). Skills-mode tasks (useSubagents=false) can optionally insert Improve after Planning and Verify before Review.

Tech Stack

  • Language: TypeScript (ES2022, ESNext modules)
  • Monorepo: Turborepo (npm workspaces)
  • API: Hono + WebSocket
  • Runtime Abstraction: @aif/runtime workspace (runtime/provider contracts + registry)
  • Database: SQLite (better-sqlite3 + drizzle-orm)
  • Frontend: React 19 + Vite + TailwindCSS 4
  • Runtime: Pluggable adapter system (@aif/runtime) — built-in Claude (Agent SDK) + Codex (SDK/CLI/API) + OpenRouter (API) adapters
  • Agent: Runtime-neutral coordinator + node-cron
  • Testing: Vitest

Project Structure

packages/
├── shared/              # @aif/shared — contracts, schema, state machine, env, constants, logger
│   └── src/
│       ├── schema.ts        # Drizzle ORM schema (SQLite)
│       ├── types.ts         # Shared TypeScript types + RuntimeTransport enum
│       ├── stateMachine.ts  # Task stage transitions
│       ├── constants.ts     # App constants
│       ├── env.ts           # Environment validation
│       ├── logger.ts        # Pino logger setup
│       ├── index.ts         # Node exports
│       └── browser.ts       # Browser-safe exports
├── runtime/             # @aif/runtime — runtime/provider contracts, registry, validation/discovery services, adapters
│   └── src/
│       ├── index.ts         # Public API exports
│       ├── types.ts         # RuntimeAdapter interface, capabilities, execution intent
│       ├── registry.ts      # RuntimeRegistry — adapter registration and lookup
│       ├── bootstrap.ts     # Factory: create registry with built-in adapters
│       ├── resolution.ts    # Profile resolution (task → project → system → env fallback)
│       ├── readiness.ts     # Health check across all registered runtimes
│       ├── capabilities.ts  # Capability assertion before workflow execution
│       ├── promptPolicy.ts  # Agent definition vs slash-command fallback
│       ├── workflowSpec.ts  # Workflow kind, session reuse, required capabilities
│       ├── modelDiscovery.ts # Model listing + connection validation with cache
│       ├── cache.ts         # Generic in-memory TTL cache
│       ├── trust.ts         # Opaque Symbol-based trust token for permission bypass
│       ├── errors.ts        # Runtime error hierarchy
│       ├── module.ts        # Dynamic module loader for external adapters
│       └── adapters/
│           ├── TEMPLATE.ts      # Adapter development guide + skeleton
│           ├── claude/          # Claude adapter (Agent SDK transport)
│           ├── codex/           # Codex adapter (CLI + API transports)
│           └── openrouter/      # OpenRouter adapter (API transport)
├── data/                # @aif/data — centralized data-access layer
│   └── src/
│       ├── participants.ts  # Participant lifecycle and admin invariants
│       ├── authSessions.ts  # Password/session/CSRF persistence
│       ├── taskOwnership.ts # Atomic handoff, assignments, executor history
│       ├── taskTransitions.ts # Actor-aware atomic task transitions
│       ├── audit.ts         # Immutable audit persistence
│       └── index.ts         # Public repository API
├── api/                 # @aif/api — Hono REST + WebSocket server (port 3009)
│   └── src/
│       ├── index.ts         # Server entry point
│       ├── routes/          # tasks/projects/chat/runtime profiles plus auth/participants
│       ├── services/        # runtime.ts, codexIndex.ts, fastFix.ts, roadmapGeneration.ts
│       │                    # github.ts provides the GitHub REST client
│       ├── middleware/      # logger.ts, rateLimit.ts, zodValidator.ts
│       ├── schemas.ts       # Zod request validation
│       └── ws.ts            # WebSocket handler
├── web/                 # @aif/web — React Kanban UI (port 5180)
│   └── src/
│       ├── App.tsx          # Root component
│       ├── components/
│       │   ├── auth/        # LoginPage
│       │   ├── participants/ # Participant menu and administration dialog
│       │   ├── kanban/      # Board, Column, TaskCard, AddTaskForm
│       │   ├── task/        # Detail, ownership/handoff, executor timeline
│       │   ├── layout/      # Header, CommandPalette
│       │   ├── project/     # ProjectSelector, ProjectRuntimeSettings
│       │   ├── settings/    # RuntimeProfileForm
│       │   └── ui/          # Reusable UI primitives (badge, button, dialog, etc.)
│       ├── hooks/           # useTasks, useProjects, useWebSocket, useTheme, useRuntimeProfiles
│       └── lib/             # api.ts, notifications.ts, utils.ts
└── agent/               # @aif/agent — Coordinator + runtime-driven subagent orchestration
    └── src/
        ├── index.ts         # Agent entry point
        ├── coordinator.ts   # Polling coordinator (node-cron)
        ├── autoQueueCommit.ts # Awaited Git commit gate before auto-queue terminal states
        ├── subagentQuery.ts # Universal runtime-backed query execution
        ├── reviewGate.ts    # Auto-review gate using adapter lightModel
        ├── hooks.ts         # Activity logging, project root
        ├── stderrCollector.ts # Generic stderr ring-buffer
        ├── notifier.ts      # Notification system
        ├── githubWorkflow.ts # GitHub sync, branch push, and PR publication
        ├── codex/           # Codex login broker (OAuth-in-Docker bridge)
        └── subagents/       # planner.ts, implementer.ts, reviewer.ts

.claude/agents/          # Agent definitions (loaded by runtimes that support them)
.docker/                 # Dockerfile, entrypoint, Angie configs
data/                    # SQLite database files (gitignored)
.ai-factory/             # AI Factory context and references

Read the full file on GitHub · 209 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. 6d ago First seen · 209 lines · 3,614 tokens per session scan A 17c951cc566b

Subscribe to this mod's changes

aif-handoff AGENTS.md is an instructions file published in the GitHub repository lee-to/aif-handoff (287 stars, last pushed 12d ago), licensed MIT. It adds 3,614 tokens to every session, about $0.0181 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.