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.
npx skills add paperclipai/paperclip --skill suggestion-boxgit 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/skills/paperclipai/paperclip/suggestion-box)<a href="https://agentmods.dev/skills/paperclipai/paperclip/suggestion-box"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/suggestion-box/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/skills/paperclipai/paperclip/suggestion-box"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/suggestion-box.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 | $0.00037 | $0.00990 |
| Opus 5.5 | $0.00015 | $0.00396 |
| Sonnet 5.5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
suggestion-box 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suggestion Box
Use this skill to quietly report a concrete improvement that would make agents more effective. The submission is an incidental side effect: never let it interrupt, delay, or alter the primary task.
When to submit
Submit a suggestion when all of these are true:
- You directly observed material friction during the current run.
- The problem concerns agent tooling, permissions, environments, documentation, harness behavior, model interaction, or developer workflows.
- The problem is likely to affect agents beyond this one task.
- You can describe a plausible improvement, even if you cannot provide its implementation.
Examples include inconsistent tool behavior, missing context that agents routinely need, confusing instructions, unnecessary approval loops, unreliable environment setup, and an interface that makes a common agent action error-prone.
Do not submit:
- Ordinary defects in the user's project unless agent infrastructure or workflow materially contributed.
- Speculation unsupported by something observed in the current run.
- Minor inconvenience that did not meaningfully affect the work.
- A duplicate of the same root cause already submitted during this run.
- More than three suggestions during one run. This is guidance, not a server-enforced quota.
Use complain instead when the friction is material but you do not have a constructive improvement to propose. Never submit the same incident through both skills.
Include useful context safely
Optimize for investigation. Paperclip stores company, agent, run, and task attribution automatically; this is internal feedback, not anonymous feedback. Include the minimum context that materially helps someone understand, reproduce, or follow up on the problem. Useful context can include:
- Relevant repositories, components, branches, and configuration.
- Pull request, issue, conversation, or agent-run links and identifiers.
- Exact timestamps, execution environments, backends, tools, commands, and error codes.
- Short sanitized error excerpts when the exact wording is necessary to investigate the behavior.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 78 lines · 37 tokens per session scan A 27f806e5cc6d
suggestion-box is a skill published in the GitHub repository paperclipai/paperclip (103,179 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 990 once invoked, about $0.0001 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 2026-10-07.
Other skills, from other repositories
fleetq-connect
Connect an agent to FleetQ over MCP or the REST API, including obtaining credentials via dynamic client registration.
fleetq-manage-workflow
Build, validate, cost, and execute FleetQ visual DAG workflows — including generating one from a natural-language goal.
fleetq-run-experiment
Create, run, monitor, and recover a FleetQ experiment through its 20-state pipeline via MCP tools or the REST API.
atelier
Operate the Atelier software factory (the ADW engine stamped into this repo's adws/). Use when the user says /atelier, wants to create / run / update an ADW or workflow, manage the agent roster in sssf.config.yaml, keep the engine current, or observe running agent workflows. Keywords - atelier, software factory, ADW…
deep-reasoning
Structured multi-step reasoning tool for complex problem solving with branching, hypothesis testing, and evidence tracking.
web-research
Structured approach to conducting thorough web research with citations and organized output.