Borrowing it
Nothing to install: this file belongs to lee-to/aif-handoff. 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/lee-to/aif-handoff/main/CLAUDE.mdgit clone --depth 1 https://github.com/lee-to/aif-handoffWrote 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/lee-to/aif-handoff/claude-md)<a href="https://agentmods.dev/instructions/lee-to/aif-handoff/claude-md"><img src="https://agentmods.dev/badge/instructions/lee-to/aif-handoff/claude-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 | $0.04046 | $0.04046 |
| Opus 5 | $0.02023 | $0.02023 |
| Sonnet 5 | $0.00809 | $0.00809 |
| Haiku 4.5 | $0.00405 | $0.00405 |
Grade A, and why
aif-handoff CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project instructions for Claude Code. Keep in sync with AGENTS.md.
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 specialized subagents routed through a pluggable runtime layer that supports multiple AI providers.
Tech Stack
- Language: TypeScript (ES2022, ESNext modules)
- Monorepo: Turborepo (npm workspaces)
- API: Hono + WebSocket
- Database: SQLite (better-sqlite3 + drizzle-orm)
- Frontend: React 19 + Vite + TailwindCSS 4
- Runtime: Pluggable adapter system (
@aif/runtime) — built-in Claude (SDK/CLI) + 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
├── data/ # @aif/data — centralized data-access layer
│ └── src/
│ └── index.ts # Repository-style DB operations for API/Agent
├── runtime/ # @aif/runtime — pluggable AI provider abstraction
│ └── 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 (SDK + CLI + API transports)
│ │ ├── index.ts # Factory: createClaudeRuntimeAdapter()
│ │ ├── options.ts # Parse execution intent → Claude SDK query options
│ │ ├── stream.ts # Async stream consumer (events, text, usage)
│ │ ├── run.ts # Orchestrator with timeout/resume retry
│ │ ├── cli.ts # CLI transport: spawn `claude` with --agent/--resume
│ │ ├── sessions.ts # Session list/get/events via Agent SDK
│ │ ├── hooks.ts # SDK hook wiring + generic callback bridges
│ │ ├── errors.ts # Error classification (usage limit, auth, stream)
│ │ └── diagnostics.ts # CLI probe + stderr analysis for diagnoseError()
│ ├── codex/ # Codex adapter (SDK + CLI + API transports)
│ │ ├── index.ts # Factory: createCodexRuntimeAdapter()
│ │ ├── sdk.ts # SDK transport: @openai/codex-sdk thread lifecycle
│ │ ├── cli.ts # CLI transport: spawn process, parse stdout
│ │ ├── sessions.ts # Session management for SDK threads
│ │ ├── api.ts # API transport: HTTP POST to remote endpoint
│ │ └── errors.ts # Error classification (CLI not found, timeout, auth)
│ └── openrouter/ # OpenRouter adapter (API transport)
│ ├── index.ts # Factory: createOpenRouterRuntimeAdapter()
│ ├── api.ts # API transport: chat completions, streaming, model discovery
│ └── errors.ts # Error classification (rate limit, auth, model not found)
├── api/ # @aif/api — Hono REST + WebSocket server (port 3009)
│ └── src/
│ ├── index.ts # Server entry point
│ ├── routes/ # tasks.ts, projects.ts, chat.ts, runtimeProfiles.ts
│ ├── services/ # runtime.ts, fastFix.ts, roadmapGeneration.ts
│ ├── 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/
│ │ ├── kanban/ # Board, Column, TaskCard, AddTaskForm
│ │ ├── task/ # TaskDetail, TaskPlan, TaskLog, AgentTimeline
│ │ ├── 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 — Runtime-neutral coordinator + subagents
│ └── src/
│ ├── index.ts # Agent entry point
│ ├── coordinator.ts # Polling coordinator (node-cron)
│ ├── 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
│ └── subagents/ # planner.ts, implementer.ts, reviewer.ts
└── mcp/ # @aif/mcp — MCP server for Claude Code integration
└── src/
└── tools/ # createTask.ts, updateTask.ts, getTask.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
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 · 223 lines · 4,046 tokens per session scan A e6a00488e13c
aif-handoff CLAUDE.md is an instructions file published in the GitHub repository lee-to/aif-handoff (287 stars, last pushed 14d ago), licensed MIT. It adds 4,046 tokens to every session, about $0.0202 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
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.
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).
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).
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.
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.