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.
Borrowing it
Nothing to install: this file belongs to paperclipai/paperclip. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/paperclipai/paperclip/master/.agents/skills/garden-inbox/SKILL.mdgit 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/garden-inbox)<a href="https://agentmods.dev/skills/paperclipai/paperclip/garden-inbox"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/garden-inbox/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/garden-inbox"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/garden-inbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00054 | $0.01015 |
| Opus 5 | $0.00027 | $0.00508 |
| Sonnet 5 | $0.00011 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
garden-inbox 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 11d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Garden Inbox
Use the bundled script for every stage. Keep the workflow strictly ordered: scan → confirm → apply.
Safety contract
- Treat
scanas read-only. It may read inbox, workspace, close-readiness, and local Git metadata only. - Treat
confirmas a confirmation-card write only. It must not archive inbox entries or mutate issue fields, branches, or workspaces. - Run
applyonly after a resolvedrequest_checkbox_confirmationinteraction. It archives only accepted option IDs that also occur in the originatingcandidates.json. - Remember that inbox archive state is per-user presentation state. It is reversible and does not change the underlying issue.
- Never substitute issue status changes, branch deletion, workspace cleanup, or issue deletion for inbox archiving.
Inputs
Require PAPERCLIP_API_URL and PAPERCLIP_API_KEY. The script strips a trailing /api from the URL. It resolves the target user from the run JWT payload's responsible_user_id; use --user-id <uuid> only for an explicit target override.
Use a run-owned output directory when available:
RUN_DIR="${PAPERCLIP_RUN_SCRATCH_DIR:-${PAPERCLIP_TASK_SCRATCH_DIR:-.}}/garden-inbox"
mkdir -p "$RUN_DIR"
1. Scan
node .agents/skills/garden-inbox/scripts/garden-inbox.mjs scan \
--output-dir "$RUN_DIR" \
--stale-days 60
Inspect garden-inbox-report.md and candidates.json. The report groups every inbox row into exactly one bucket:
The scan reads Mine separately for each included issue status so the endpoint's global 500-row cap does not silently omit older rows. If any single-status query reaches that cap, both outputs mark coverage as possibly truncated; do not treat that scan as complete.
- A: merged/archived workspace and all linked work terminal; selected by default.
- B: terminal or workspace-gone work idle beyond the threshold; selected by default.
- C: stale work with commits ahead of base; never selected by default.
- D: keep; never offered for archiving.
What ships with it
2 files 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.
- 11d ago First seen · 101 lines · 54 tokens per session scan A 654c623635fa
garden-inbox is a skill published in the GitHub repository paperclipai/paperclip (80,385 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,015 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.