open-bridge AGENTS.md

open-bridge AGENTS.md is an instructions file for Codex, OpenCode from bks-lab/open-bridge. It costs 8,154 tokens per session, scanned A, original, MIT.

Repository instructions for open-bridge, a central project that coordinates coding agents, repositories, and tools. AGENTS.md is the shared operating manual that different AI coding tools read.

In plain words
What is it for?
Use it when an agent starts work in open-bridge or needs to find the correct project, task rules, commands, or supporting documentation.
Why use it?
It gives agents one consistent set of startup steps, rules, safety limits, and navigation guidance. This reduces conflicting behavior between tools such as Claude Code and Codex.

Instructions file for CodexOpenCode

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/bks-lab/open-bridge/agents-md
Clone the repo
git clone --depth 1 https://github.com/bks-lab/open-bridge

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 open-bridge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bks-lab/open-bridge/agents-md.svg)](https://agentmods.dev/instructions/bks-lab/open-bridge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/bks-lab/open-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/bks-lab/open-bridge/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,154 This file is loaded in full into every session.
When invoked 8,154 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 $0.08154 $0.08154
Opus 5 $0.04077 $0.04077
Sonnet 5 $0.01631 $0.01631
Haiku 4.5 $0.00815 $0.00815

Measured 3d ago against content hash c92157397496, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

open-bridge 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.

AGENTS.md · 629 lines

How it starts

The opening of the file, as written. The whole thing — 629 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Bridge — Agent Instructions

This file is the canonical, tool-agnostic operating manual for this repo — session start flow, rules, task management, agents, standing orders, commands. It is for any AI coding agent (Claude Code, GitHub Copilot, Gemini CLI, Codex, Cursor, Windsurf, or any future tool). It is tool-agnostic with ONE exception — sub-agents are Claude Code only; every other feature works identically across tools. The filename follows the AGENTS.md convention (Linux Foundation); the content applies to all agents regardless of which name your tool looks for. CLAUDE.md and GEMINI.md are thin wrappers that point here.

This repo is your central command hub. From here you navigate to every repo, project, and tool in your ecosystem. Your agents handle analysis, deployment, security, communication, and monitoring — in parallel.

For humans: the README is the narrative + architecture overview with mermaid diagrams. Read it first if you're new to the project.

For you (the agent): this file is a lean router. It holds the behavioural invariants and guardrails, says what each system is and when it matters, and points at the rules/ and docs/ files that carry the mechanics.

Strategic status: bks-lab/open-bridge (OSS, MIT) is the public CORE layer. Downstream forks (org overlays, personal instances) add overlays via the /promote flow with scope: routing.

Required Reading

  1. This file (AGENTS.md) is the full operating manual. The name is a convention; the content applies to all agents.
  2. Read the session slice of bridge-config.yaml with python3 scripts/bridge-config.py --session (identity, purpose, user_profile, theme, language, work). The other fifteen blocks belong to the skill that owns them; read a block with --keys <block> when that skill runs.
  3. Index ecosystem.yaml if present — the project registry (repos, packages, infrastructure, workspaces). Created during onboarding, user-specific and gitignored (like bridge-config.yaml), so absent on a fresh clone. It is not an @-import: Phase 1 runs python3 scripts/context-index.py ecosystem.yaml for the settings plus one line per entry, and --get <name> fetches an entry when the work names one — the split skills have always had, applied to a declared map (docs/context-index.md). ecosystem.example.yaml is present on a fresh clone as the registry template — onboarding uses it as the starting point (copy + auto-populate → the gitignored ecosystem.yaml); do not hand-copy it.

Read the full file on GitHub · 629 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. 3d ago First seen · 629 lines · 8,154 tokens per session scan A c92157397496

Subscribe to this mod's changes

open-bridge AGENTS.md is an instructions file published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed 3d ago), licensed MIT. It adds 8,154 tokens to every session, about $0.0408 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.