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.
npx agentmods add instructions/onelevenvy/flock/agents-mdgit clone --depth 1 https://github.com/Onelevenvy/flockWhat 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 | $0.02131 | $0.02131 |
| Opus 5 | $0.01066 | $0.01066 |
| Sonnet 5 | $0.00426 | $0.00426 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
flock 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- flock CLAUDE.md — 97% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to CodeX when working with code in this repository.
Project Overview
Flock is a multi-provider AI agent desktop application with tool orchestration, sandbox execution, visual workflow, and browser/computer-use capabilities. It's a Rust workspace with a Tauri-based desktop UI (React + TypeScript + Mantine).
Build & Development Commands
Rust Backend
# Build the CLI
cargo build --release
# Run in single-shot mode
cargo run -- "your question"
# Run interactive REPL
cargo run
# Run with specific provider/profile
cargo run -- --profile deepseek "your question"
# Run tests (workspace-wide)
cargo test
# Run a single crate's tests
cargo test -p flock-core
cargo test -p flock-agent
cargo test -p flock-tools
cargo test -p flock-skills
# Run a specific test
cargo test -p flock-core test_name
# Lint
cargo clippy --workspace
Tauri Desktop UI
cd flock-ui
# Install dependencies
npm install
# Development server
npm run dev
# or
npm run tauri dev
# Build for production
npm run build
# or
npm run tauri build
# Lint frontend
npm run lint
Architecture
Workspace Crates
| Crate | Purpose |
|---|---|
flock-core |
Core types, config, database, IPC interface, crypto, model factory |
flock-agent |
Agent engine, session management, tool execution, memory, graph orchestration, workflow engine |
flock-tools |
Tool registry, built-in tools (Read/Write/Edit/Bash/Grep/Glob), MCP integration, sandbox tools (CodeExecution, SandboxExec, Browser, ComputerUse) |
flock-skills |
Skill discovery, loading, frontmatter parsing, hooks, permissions, bundled skills |
flock-ui/src-tauri |
Tauri desktop app backend (commands, agent state, workspace management) |
workspace-hack |
cargo-hakari build optimization |
Key Dependencies
- LangGraph: Rust reimplementation (langgraph-rust) for agent graph orchestration
- LLM Providers: OpenAI-compatible (default), Anthropic, AWS Bedrock, Google Vertex
- Database: SQLite via sqlx for sessions, conversations, providers, tools, MCP servers, workflows
- Async Runtime: Tokio
- Sandbox: Daytona cloud container runtime for isolated code execution
- Browser Automation: Playwright (Python, runs inside sandbox via CDP)
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.
- 3d ago First seen · 194 lines · 2,131 tokens per session scan A 037200881ccd
flock AGENTS.md is an instructions file published in the GitHub repository Onelevenvy/flock (1,103 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,131 tokens to every session, about $0.0107 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
TradingAgents-Telegram CLAUDE.md
Instructions for IvanWng97/TradingAgents-Telegram, covering tradingagents-telegram — architecture reference, layout, architecture (for code reviewers), request lifecycle (manual /watch tap) and state ownership.
daiv AGENTS.md
Instructions for srtab/daiv, covering agents.md, commands (verified), single test / pattern, translations and repo map (only what's non-obvious).
dive-into-langgraph AGENTS.md
AGENTS.md instructions for luochang212/dive-into-langgraph, covering agents.md, how we work, what this project is, project layout and environment & toolchain.
auxilia CLAUDE.md
Claude Code instructions for keurcien/auxilia, covering claude.md, project overview, backend conventions, layered architecture and naming.
daiv CLAUDE.md
Instructions for srtab/daiv, a project described as: Your AI-powered SWE teammate, built into your git workflow.
open-swe CLAUDE.md
Claude Code instructions for langchain-ai/open-swe, covering claude.md, project, commands, architecture and entrypoints.