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.
git clone --depth 1 https://github.com/udah1/cursor-chat-bridgeWrote 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.
[](https://agentmods.dev/rules/udah1/cursor-chat-bridge/chat-bridge-mode)<a href="https://agentmods.dev/rules/udah1/cursor-chat-bridge/chat-bridge-mode"><img src="https://agentmods.dev/badge/rules/udah1/cursor-chat-bridge/chat-bridge-mode/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.
<a href="https://agentmods.dev/rules/udah1/cursor-chat-bridge/chat-bridge-mode"><img src="https://agentmods.dev/badge/rules/udah1/cursor-chat-bridge/chat-bridge-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01312 | $0.01312 |
| Opus 5.5 | $0.00525 | $0.00525 |
| Sonnet 5.5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade C, and why
chat-bridge-mode scanned grade C 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
or irreversible actions (deleting data, force-push, `rm -rf`, spending money, sending How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
remote chat mode (מצב שיחה מרוחק)
The user can drive this session from an external chat channel (GitHub issue, Telegram
topic, Discord channel) via the cursor-chat-bridge MCP tools (bridge_*). The channel is
chosen by activeAdapter in config, or per-session via bridge_start(adapter).
Activation
Start when the user asks — in any language — to begin remote chat / remote control / bridge mode. Recognize intent, not exact words. Examples that should trigger it:
- Hebrew: "מצב שיחה מרוחק", "התחל מצב שיחה מרוחק", "מצב בקרה מרחוק", "תפעיל שליטה מרחוק", "מצב טלגרם" / "מצב גיטהאב" (also selects that channel)
- English: "remote chat mode", "start remote mode", "bridge mode on", "control me from chat", "telegram mode" / "github mode" (also selects that channel)
On activation:
- Call
bridge_start. Pass atitlethat concisely names THIS conversation the way it appears in Cursor's chat list — a ≤6-word summary of the conversation's topic (e.g. "GitHub Actions autopublish", not the folder name and not a generic label). Cursor doesn't expose its auto-generated title to tools, so you produce the equivalent. Also passadapterif the user named a platform (Telegram/GitHub/Discord). The channel thread/channel is named from this title; the workspace is shown separately in the thread's description. - Capture the
sessionhandle from thebridge_startresponse and remember it for this conversation. Passingsession=<handle>is now REQUIRED on every subsequentbridge_*call (bridge_send,bridge_await,bridge_send_and_await,bridge_stop,bridge_status) — they error without it. This is what keeps multiple conversations (even in the same workspace) on their own separate threads. To RE-start an existing session, pass that same handle back tobridge_start. - If
bridge_startreturns setup guidance instead (channel not configured), follow it to onboard the user, then callbridge_startagain. If it returns a fail-closed message (no submit handshake / stale / more than one chat submitted at once), do NOT retry blindly: follow its guidance — usually re-send “start remote chat mode” from just THIS chat, or runnpx cursor-telegram-chat@latest installthen FULLY quit + reopen Cursor if hooks aren't loaded. bridge_start never guesses an identity, so it won't cross threads. - If the
bridge_startresponse includes an UPDATE AVAILABLE note, mention it and ask the user — via the normal Cursor question UI (the remote loop hasn't started yet) — whether to update now withnpx cursor-telegram-chat@latest install(then reload Cursor). If they decline, just continue. - Confirm briefly in Cursor, then continue the actual work the user asked for.
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.
- 2mo ago First seen · 82 lines · 1,312 tokens per session scan C fe2d5da9bc1f
chat-bridge-mode is a cursor rule published in the GitHub repository udah1/cursor-chat-bridge (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,312 tokens to every session, about $0.0052 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.