agentmods.dev

ab AGENTS.md

A repository guide for coding agents working on Agent-Bridge and its related child repositories. It explains which folders are active, how the repositories are organized, and how to start the system.

In plain words
What is it for?
Use it to identify where backend, frontend, and terminal-daemon changes belong, prepare environment files and secrets, and start the production-style local stack.
Why use it?
It reduces mistakes caused by editing the wrong repository or using outdated code as the source of truth. It also gives agents the setup details needed to work in the project.

Instructions file for CodexOpenCode

38 3mo ago A scan 1,140 tokens original MIT
View the source file agent-bridges/ab
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/agent-bridges/ab/agents-md
Clone the repo
git clone --depth 1 https://github.com/agent-bridges/ab

Made for: Codex, OpenCode.

Per session 1,140 This file is loaded in full into every session.
When invoked 1,140 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01140 $0.01140
Opus 5 $0.00570 $0.00570
Sonnet 5 $0.00228 $0.00228
Haiku 4.5 $0.00114 $0.00114

Measured 2d ago against content hash 5923516183a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ab AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

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

curl http://127.0.0.1:8520/health
AGENTS.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

This file is for agentic coding tools working inside Agent-Bridge (ab).

Scope

Work only inside the current ab checkout and its child repos:

  • ab
  • ab-back
  • ab-front
  • ab-pty

Do not treat old repos outside this checkout as the active source of truth.

Repository Model

  • ab is the deploy/orchestration root
  • each child folder is its own git repository
  • root ab is also its own git repository
  • changes should be committed in the repo that owns them

Current Product Split

  • ab-back: backend/API
  • ab-front: main canvas frontend on 5281
  • ab-pty: PTY daemon

Quick Setup

  1. Ensure .env exists:
cp .env.example .env
  1. Ensure AB_JWT_SECRET_PATH points to a real file:
mkdir -p state/back
openssl rand -hex 32 > state/back/jwt-secret
  1. Bootstrap and start the default production-style stack:
scripts/bootstrap.sh
scripts/stack.sh up --mode prod

Default install mode includes one seeded docker demo agent plus its daemon container.

For a clean install without demo data:

scripts/stack.sh up --mode prod --skip-test-data

Developer Setup

Development, test/demo, and local release work require the child repos at:

  • ./ab-back
  • ./ab-front
  • ./ab-pty

Start the bind-mount development stack with:

scripts/stack.sh up --mode dev

Default developer mode also includes the seeded docker-demo-agent.

For a clean dev stack:

scripts/stack.sh up --mode dev --skip-test-data

Quick Verify

scripts/stack.sh ps --mode prod
curl http://127.0.0.1:8520/health
curl http://127.0.0.1:8520/api/auth/status

Frontends:

  • http://127.0.0.1:5281

Default install also seeds:

  • docker-demo-agent

Test Stack

For an isolated clickable test environment with a fresh DB and two seeded docker remote agents:

scripts/test-up.sh

Required host tools:

  • docker
  • docker compose
  • bash
  • curl
  • python3
  • realpath

If the test stack already exists, the script prompts before tearing it down. Answering no must leave the current test environment untouched and exit cleanly.

Read the full file on GitHub · 188 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 · 188 lines · 1,140 tokens per session scan A 5923516183a3

Subscribe to this mod's changes

ab AGENTS.md is an instructions file published in the GitHub repository agent-bridges/ab (38 stars, last pushed 3mo ago), licensed MIT. It adds 1,140 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agent-bridgeai-agentscanvasdevtoolsopen-sourcepty
Related

Other instructions, from other repositories

repo-audit AGENTS.md

Instructions for conorbronsdon/repo-audit, covering agents.md, what this repo is, rules, changing the skill and deliberately not here.

conorbronsdon/repo-audit · 807 tokens

open-pencil copilot-instructions.md

Copilot instructions for open-pencil/open-pencil, covering openpencil copilot instructions, pull request requirements, validation and code conventions.

open-pencil/open-pencil · 291 tokens

bb AGENTS.md

AGENTS.md instructions for get-bb/bb, covering codebase guidelines, simplicity first, code comments, types and contracts and server and daemon.

get-bb/bb · 2,169 tokens

openscreen AGENTS.md

Instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.

getopenscreen/openscreen · 5,627 tokens

openstatus AGENTS.md

AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.

openstatusHQ/openstatus · 1,308 tokens

tldraw CLAUDE.md

Claude Code instructions for tldraw/tldraw, a project described as: Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.

tldraw/tldraw · 5 tokens