agentmods.dev

agentbridge-protocol AGENTS.md

A set of instructions for AI coding agents working on the AgentBridge repository. It explains the project, its current state, file layout, and important commands.

In plain words
What is it for?
Use it when asking an AI agent to work on the AgentBridge codebase. It helps the agent understand what the project contains and how it is currently maintained.
Why use it?
It gives an agent the repository context it needs before changing code. This reduces the chance of ignoring existing packages, planned work, tests, or project conventions.

Instructions file for CodexOpenCode

1 1mo ago A scan 2,524 tokens original Apache-2.0
View the source file marmar9615-cloud/agentbridge-protocol
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/marmar9615-cloud/agentbridge-protocol/agents-md
Clone the repo
git clone --depth 1 https://github.com/marmar9615-cloud/agentbridge-protocol

Made for: Codex, OpenCode.

Per session 2,524 This file is loaded in full into every session.
When invoked 2,524 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 $0.02524 $0.02524
Opus 5 $0.01262 $0.01262
Sonnet 5 $0.00505 $0.00505
Haiku 4.5 $0.00252 $0.00252

Measured 2d ago against content hash 35a2be0dc70e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentbridge-protocol 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 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.

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 · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Working notes for any AI coding agent operating on this repository (OpenAI Codex, Claude Code, Cursor, custom). Model-neutral. Keep this file short. For deeper, Claude-specific notes see CLAUDE.md.

Project summary

AgentBridge is an AI-native action layer for web apps. Web apps publish a manifest at /.well-known/agentbridge.json. MCP clients discover the manifest, validate inputs, enforce confirmation on risky actions, call action endpoints, and audit the results.

The repo ships:

  • Five publishable npm packages plus an MCP server, scoped under @marmarlabs.
  • A demo Next.js app and a Studio dashboard.
  • A Vitest test suite (86 tests as of v0.2.1).

Current state

Read the full file on GitHub · 199 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 · 199 lines · 2,524 tokens per session scan A 35a2be0dc70e

Subscribe to this mod's changes

agentbridge-protocol AGENTS.md is an instructions file published in the GitHub repository marmar9615-cloud/agentbridge-protocol (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,524 tokens to every session, about $0.0126 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.

AI SafetyJSON Schemaagent-toolingai-agentsclideveloper-tools
Related

Other instructions, from other repositories

orbit CLAUDE.md

Instructions for schmitech/orbit, covering claude.md, project overview, commands, setup and running the server.

schmitech/orbit · 1,234 tokens

crust AGENTS.md

Instructions for chenxin-yan/crust, covering tests, documentation, changesets, agent skills and issue tracker.

chenxin-yan/crust · 388 tokens

CORE CLAUDE.md

Instructions for DariuszNewecki/CORE, covering claude.md — core, what core is, and what you are, source layout, how to work in this repo and governed and prohibited surfaces.

DariuszNewecki/CORE · 8,080 tokens

dsh-auto-review AGENTS.md

Instructions for PerryLink/dsh-auto-review, covering agents.md, layout, hard rules applied here, build and docs.

PerryLink/dsh-auto-review · 2,031 tokens

orloj CLAUDE.md

Instructions for OrlojHQ/orloj, covering orloj claude instructions, critical repository rules and implementation notes.

OrlojHQ/orloj · 258 tokens

qwed-verification copilot-instructions.md

Instructions for QWED-AI/qwed-verification: Read and follow QWEDRULES.md for every suggestion.

QWED-AI/qwed-verification · 155 tokens