Authorization notice. Paperclip Guide is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.
Who it is forA team lead who has agents ready and needs to keep humans in charge of what they produce and what counts as finished.
The problemAgents can mark work as done without anyone checking it, and it is hard to see who decided what.
The outcomeAgents working through projects, tasks, Cases, Decisions and Artifacts, with approvals gating key steps and a watchdog double-checking completion.
What you need first
- A machine to run Paperclip: a Mac, a Linux box, or Windows with WSL2, or a VM or cloud server
- Node.js 24.11 or newer
- At least one AI account for your agents: a Claude subscription or API key, an OpenAI account for Codex, or a local model through Ollama
- Optional: a Hermes agent running on another machine, if you want to bring one in
- Optional: a Flare account, for the Flare chapter
Steps
- Follow chapter 6 (guide/06-give-them-work.md) to create a project and assign tasks to your agents.
- Use Cases, Decisions and Artifacts to record what the agents produce, as the chapter describes.
- Follow chapter 7 (guide/07-approvals-and-watchdogs.md) to set approvals so the board signs off on key actions.
- Hire the Watchdog using prompts/hire/ and confirm it reviews tasks marked done.
- Use prompts/tasks/ to run the test-the-team task and check the results.
Prompt for your agent
Using the repo theNetworkChuck/paperclip-guide, follow chapters 6 and 7 to create one project in Paperclip with a test task for <agent name>. Report the task status, any approval requests, and the Watchdog's verdict. Verify that the task cannot be closed without the required approval.
Caveat. The guide describes approvals and watchdogs but its exact behavior depends on the Paperclip version you install, which the guide tested as 2026.916.1.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page