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/openbraid/braid/agents-mdgit clone --depth 1 https://github.com/openbraid/braidWhat 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 | $0.01545 | $0.01545 |
| Opus 5 | $0.00772 | $0.00772 |
| Sonnet 5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
braid 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 yesterday.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Context for AI coding agents working in this repository. Humans: this doubles as an orientation doc — but ARCHITECTURE.md is the fuller explanation and CONTRIBUTING.md is the workflow.
All paths here are relative to the repository root.
What Braid is
A macOS desktop app for running several AI coding agents in parallel. Each unit of work is a workspace: its own git branch, a git worktree per repo, an embedded VS Code instance, and its own terminals and agent sessions — all visible from one sidebar.
A second layer, artifacts, stores structured YAML (requirements, design,
spec, test plan) in a .braid/ directory inside the user's own repository, and
configures installed agents to read and write it.
Braid does not ship an agent. It runs whichever ones the user already has.
Repository layout
apps/desktop/ Electron app — main, preload, renderer, bundled VS Code extension
apps/server/ Optional self-hosted NestJS server (team mode). Not required.
docs/guide/ End-user documentation
Inside apps/desktop/src/:
main/ Electron main process (Node)
db/ Drizzle schema + migrations; queries/ holds all SQL
lib/ Pure utilities — no DB, no IPC, no services
services/ Business logic — orchestrates lib + queries + other services
repositories/ Storage seam: interfaces + Local*/Backend* implementations
ipc/handlers/ Thin — call a service, return the result
preload/ contextBridge — exposes typed window.api
renderer/src/ React + Zustand + Tailwind
extension/ VS Code extension, auto-installed into the embedded server
shared/ Types used by more than one process (IPC channels, payloads)
Layer rules, strictly enforced. No layer skips a level:
ipc/handlers → services only
services → queries + lib + other services
queries → Drizzle only
lib → pure functions
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.
- yesterday First seen · 168 lines · 1,545 tokens per session scan A d038e001f96d
braid AGENTS.md is an instructions file published in the GitHub repository openbraid/braid (9 stars, last pushed 19d ago), licensed Apache-2.0. It adds 1,545 tokens to every session, about $0.0077 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 2026-08-31.
Other instructions, from other repositories
chat-on-steroids AGENTS.md
Instructions for totec448-spec/chat-on-steroids, covering chat on steroids — the agent map, 1. the app in sixty seconds, 2. where the bugs actually are, name the identity, then find where it is lost and 3. what is authoritative.
stashbase AGENTS.md
Instructions for liliu-z/stashbase, covering agent maintenance contract for this repo, github access for this repository, temporary worktrees, electron launch environment and documentation route.
chat-on-steroids CLAUDE.md
Instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
tandem-browser CLAUDE.md
Instructions for hydro13/tandem-browser: Read AGENTS.md in full — it is the development guide for coding agents working on this repository: workflow, testing gates, git discipline, context discipline, and the anti-detection architecture rules that must never be violated.
Knote AGENTS.md
Instructions for 1661169091kiwi/Knote, covering agents.md, 构建与验证约定（用户明确要求，所有会话必须遵守） and 测试说明.
clodex-ide AGENTS.md
AGENTS.md instructions for mereyabdenbekuly-ctrl/clodex-ide, covering clodex repository agent rules, open/closed product boundary, commercial product invariant, current protocol v0 phase and current authorization state.