What is OzBridge AGENTS.md?

Project instructions for OzBridge, a VS Code extension that connects Copilot Chat with the Oz AI agent command-line tool. They describe the project structure, commands, and development details.

Use them when compiling, testing, watching, bundling, or packaging OzBridge. They also help when working with its npm workspaces and the copilot-chat-toolkit package.

They give an agent the project-specific information needed to build, test, and package the extension correctly. They also point out steps that are easy to miss, such as building a workspace package first.

How sena-labs/OzBridge configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sena-labs/OzBridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sena-labs/OzBridge/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sena-labs/OzBridge

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sena-labs/ozbridge/agents-md/github.svg)](https://agentmods.dev/instructions/sena-labs/ozbridge/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sena-labs/ozbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/sena-labs/ozbridge/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sena-labs/ozbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/sena-labs/ozbridge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 619 This file is loaded in full into every session.

When invoked 619 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00619	$0.00619
Opus 5.5	$0.00248	$0.00248
Sonnet 5.5	$0.00124	$0.00124
Haiku 4.5	$0.00062	$0.00062

Measured 18d ago against content hash d1b4babf4141, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

OzBridge 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 18d 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 · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cursor Cloud specific instructions

Project overview

OzBridge is a VS Code extension (TypeScript, npm workspaces) that bridges VS Code Copilot Chat with Warp Terminal's Oz AI agent CLI. It is a pure extension — no databases, Docker, or external services are needed for development. The workspace package copilot-chat-toolkit (under packages/copilot-chat-toolkit) is a build-time dependency.

Key commands

All standard dev commands are in package.json scripts and documented in README.md and CONTRIBUTING.md. Quick reference:

Task	Command
Type-check (lint)	`npm run compile`
Unit tests	`npm test -- --run` (Vitest, ~13 s)
Build bundle	`npm run build` (esbuild, produces `dist/extension.js`)
Dev watch mode	`npm run watch`
Package VSIX	`npm run package`
Test with coverage	`npm run test:coverage`

Non-obvious caveats

Workspace package build order: The copilot-chat-toolkit package must be built (npm run build --workspace=copilot-chat-toolkit) before npm run build for the main extension if its dist/ directory is missing. After the first build, npm install links it automatically.
Vitest runs serially (fileParallelism: false in vitest.config.ts) because MCP server tests open real TCP sockets; parallel file execution causes port collisions on some platforms. This is intentional and should not be changed.
The vscode module is mocked via vitest.config.ts alias — tests never need a real VS Code instance. The mock lives at test/mocks/vscode.ts.
Bundle budget: The bundle budget is 170 KB for dist/extension.js, enforced in esbuild.js (BUNDLE_MAX_KB) and by the Bundle budget (dist/extension.js) CI check. Override locally with OZBRIDGE_BUNDLE_MAX_KB. npm run build prints the current size against the budget.
verify-install script (scripts/verify-install.cjs): Loads the bundled extension with a vscode stub and calls activate(). Some assertion failures about activationEvents are expected when run against the current manifest — the script checks for onStartupFinished and per-command activation events that the extension intentionally omits in favor of lazy activation.
E2E tests (npm run test:e2e) require a real VS Code Electron instance and xvfb-run -a on headless Linux. These are not part of the standard CI loop for unit testing.
Test descriptions are written in English (it('returns …'), it('rejects …')), like the rest of the repository.

Read the full file on GitHub · 31 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.

18d ago Changed · +12 tokens per session d1b4babf4141
2mo ago First seen · 31 lines · 607 tokens per session scan A 04c4bff8861f

Subscribe to this mod's changes

OzBridge AGENTS.md is an instructions file published in the GitHub repository sena-labs/OzBridge (3 stars, last pushed 3d ago), licensed MIT. It adds 619 tokens to every session, about $0.0025 per session on Opus 5.5. 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.

Claude Code ai-agents codex copilot copilot-chat cursor

plugin-files-mode

Rosetta Plugin Mode Bootstrap.

griddynamics/rosetta · 236 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

OzBridge: Instructions file for Codex