copilot-bridge AGENTS.md

Repository instructions for Copilot Bridge, a service that connects chat messages from Mattermost to an agent or other connected system. Mattermost is a team chat platform, and the bridge receives events over a WebSocket, a live connection for messages.

In plain words
What is it for?
Use them when changing platform adapters, message handling, the gateway service, tests, deployment, or service restart procedures.
Why use it?
They document the build checks, tests, internal message flow, and safe restart method, including a command sequence that must not be used because it can leave the service stopped.

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/chrisromp/copilot-bridge/agents-md
Clone the repo
git clone --depth 1 https://github.com/ChrisRomp/copilot-bridge

Made for: Codex, OpenCode.

Per session 2,205 This file is loaded in full into every session.
When invoked 2,205 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 $0.02205 $0.02205
Opus 5 $0.01103 $0.01103
Sonnet 5 $0.00441 $0.00441
Haiku 4.5 $0.00220 $0.00220

Measured 2d ago against content hash 6674d4a4e6c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-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 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 · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — copilot-bridge

Repo: https://github.com/ChrisRomp/copilot-bridge

Keep this file up to date as the architecture evolves or new conventions emerge. If you make structural changes, add a new platform adapter, or change key patterns, update the relevant section here.

For project overview, configuration, chat commands, and deployment, see README.md.

Build & Check

npm install                                   # install dependencies
npx tsc --noEmit                              # type-check (always run before deploying)
npm run dev                                   # run with watch mode (tsx watch)
npm test                                      # vitest suite
npx vitest run src/path/to/file.test.ts       # single test file

Restart the running service after changes:

scripts/restart-gateway.sh
# Or: launchctl kickstart -k gui/$(id -u)/com.copilot-bridge

⚠️ NEVER use launchctl unload && launchctl loadunload kills the bridge process (including your session), so the load half never executes and the service stays down.

Internal Architecture

Message Flow

  1. MattermostAdapter receives a WebSocket event, normalizes it to InboundMessage
  2. index.ts serializes handling per channel via promise chains (channelLocks), checks for slash commands, then forwards to SessionManager.sendMessage()
  3. SessionManager creates/resumes a CopilotSession via CopilotBridge (SDK wrapper), wiring up permission and user-input handlers
  4. SDK session events flow back through sessionManager.onSessionEvent()handleSessionEvent() in index.ts
  5. StreamFormatter converts SDK events to FormattedEvent, which are routed to StreamingHandler for edit-in-place message updates

Event Serialization

Both inbound messages and session events are serialized per-channel via separate promise chains (channelLocks and eventLocks). This prevents race conditions on stream auto-start and permission resolution.

Read the full file on GitHub · 149 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 · 149 lines · 2,205 tokens per session scan A 6674d4a4e6c7

Subscribe to this mod's changes

copilot-bridge AGENTS.md is an instructions file published in the GitHub repository ChrisRomp/copilot-bridge (20 stars, last pushed 1mo ago), licensed MIT. It adds 2,205 tokens to every session, about $0.0110 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 2026-08-30.

Related

Other instructions, from other repositories

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 · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens