Paperclip is a Node.js server and React application for coordinating AI agents as a business team, with goals, organizational roles, budgets, governance, and work tracking in one interface. It is used by people managing multiple agents or autonomous agent organizations across tools such as OpenClaw, Claude Code, Codex, and Cursor. The catalogue includes skills, agents, an MCP add-on, and an instruction for working with Paperclip.
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/paperclipai/paperclipWrote 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/paperclipai/paperclip/chat-channel-platform-boundaries)<a href="https://agentmods.dev/rules/paperclipai/paperclip/chat-channel-platform-boundaries"><img src="https://agentmods.dev/badge/rules/paperclipai/paperclip/chat-channel-platform-boundaries/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/paperclipai/paperclip/chat-channel-platform-boundaries"><img src="https://agentmods.dev/badge/rules/paperclipai/paperclip/chat-channel-platform-boundaries.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 | $0.00000 | $0.00647 |
| Opus 5.5 | $0.00000 | $0.00259 |
| Sonnet 5.5 | $0.00000 | $0.00129 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
chat-channel-platform-boundaries 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chat channel platform boundaries
Scope and purpose
This rule applies to server/src/services/chat-channels/ and its sibling
server/src/services/chat-channels.ts service entry point. Keep each platform's
implementation cohesive while letting common workflows support different
platforms through explicit contracts.
Required structure
- Put platform-specific code in
chat-channels/<platform>/. This includes payload parsing, SDK and transport calls, protocol details, credential and setup behavior, message formatting, and platform-specific workarounds. - Use the existing platform directories, such as
telegram/,slack/,discord/,github/,microsoft-teams/, andimessage-photon/. Organize files within each directory by responsibility, such asmessages.tsorsetup.ts. - Keep shared product behavior in the service or cohesive workflow modules,
such as
inbound/,interactions/, andpublications/. Shared code owns common company isolation, authorization, task lifecycle, ordering, and persistence invariants. Provider details must not bypass those invariants. - Use explicit typed inputs, outputs, capabilities, or callbacks at the boundary. Shared workflows should consume normalized values rather than interpret one platform's raw payloads. Pass the dependencies a module needs instead of a large mutable service context.
- Reuse existing contracts and shared implementations when their behavior is actually common. Preserve meaningful platform differences. Add a new abstraction only when a concrete workflow needs it.
- When extracting code, preserve transaction ownership, queue ordering, idempotency, runtime state lifetime, and callback timing. Moving code must not create duplicate state or a second owner for a side effect.
Examples and allowed exceptions
- Telegram edited-message parsing belongs in
telegram/messages.ts; a shared delivery workflow can consume its normalized message or lifecycle event. - Shared orchestration may import platform modules and select an implementation by provider name. Small registration tables and dispatch branches are valid; the selected branch should delegate protocol behavior to the platform module.
- Keep behavior used by several platforms in a shared module when its inputs and semantics are independent of those platforms. Do not make one platform import another platform's implementation merely to reuse a helper.
- Existing code outside these boundaries can be migrated incrementally. Apply the rule to new or materially changed behavior; an unrelated fix does not require moving the whole subsystem.
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.
- 2d ago First seen · 61 lines · 0 tokens per session scan A f4b1528657ad
chat-channel-platform-boundaries is a cursor rule published in the GitHub repository paperclipai/paperclip (102,719 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 647 tokens. 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 2026-10-14.
Other cursor rules, from other repositories
frontend-architecture
// Request interceptor for ecosystem ID const injectEcosystemId = (config: any) => { let ecosystemId = window.getCurrentEcosystemId() || localStorage.getItem('ecosystemId'); if (ecosystemId && config.headers) { config.headers['X-Ecosystem-ID'] = ecosystemId; } return config; }.
backend-architecture
Cursor rule "backend-architecture" from EricLortie/laborforge-release, covering backend architecture and api structure, core backend components, api endpoints structure, core modules and ai provider integrations.
titanclip-packages
Shared packages — db, shared, adapters, plugin SDK.
titanclip-server
TitanClip server — Express ESM, routes, heartbeat, adapters.
kandev-pr-fixup
Kandev PR fixup workflow prompt for Cursor agents.
core
Rails 8 Core Principles Guide.