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/product-harness-responsibility)<a href="https://agentmods.dev/rules/paperclipai/paperclip/product-harness-responsibility"><img src="https://agentmods.dev/badge/rules/paperclipai/paperclip/product-harness-responsibility/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/product-harness-responsibility"><img src="https://agentmods.dev/badge/rules/paperclipai/paperclip/product-harness-responsibility.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 | $0.00218 | $0.00218 |
| Opus 5.5 | $0.00087 | $0.00087 |
| Sonnet 5.5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
product-harness-responsibility 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.
What it actually says
Let the harness handle routine work
Applies to product design, implementation and review across UI, orchestration, setup, settings and user-facing errors.
If the system knows the next step and can safely perform it under existing authority, the harness owns it.
- Implement routine retries, reconnection, lease maintenance and finalization in the owning service. Do not turn orchestration gaps into user checklists.
- Each control and detail must enable a real decision, resolve uncertainty or help use a result. Keep incidental internal states and identifiers out of default views.
- Keep normal operation quiet. Show brief, contextual status only when useful, backed by observed server state. Never hide blockers or imply progress that has not occurred.
- Do not ask task users to certify infrastructure facts.
Review: Check that harness responsibility is implemented, visible details serve a purpose the user should affect.
Apply this rule to changed flows; unrelated redesign is not required.
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 · 27 lines · 218 tokens per session scan A 40001ce3a13c
product-harness-responsibility is a cursor rule published in the GitHub repository paperclipai/paperclip (102,719 stars, last pushed today), licensed MIT. It adds 218 tokens to every session, about $0.0009 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 2026-10-14.
Other cursor rules, from other repositories
kandev-pr-fixup
Kandev PR fixup workflow prompt for Cursor agents.
conventional-commits
Always use Conventional Commits for git commit messages.
database-schema
-- Users can belong to multiple ecosystems users (1) -----> (N) userecosystemmemberships (N) <----- (1) ecosystems.
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.