Paperclip
paperclipai/paperclip
Interact with the Paperclip control plane API for task coordination and governance.
Manage Paperclip AI companies, agents, issues, projects, goals, routines, costs, and secrets via REST API.
Install Paperclip AI
$ npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill paperclip-ai -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Yesterday-AI/paperclip-plugin-company-wizard paperclip-ai --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Yesterday-AI/paperclip-plugin-company-wizard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/paperclip-ai .claude/skills/paperclip-ai && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "paperclip-ai" agent skill from https://github.com/Yesterday-AI/paperclip-plugin-company-wizard/tree/main/.claude/skills/paperclip-ai into .claude/skills/paperclip-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperclip-ai", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Yesterday-AI/paperclip-plugin-company-wizard/tree/main/.claude/skills/paperclip-aiType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill paperclip-ai -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Yesterday-AI/paperclip-plugin-company-wizard paperclip-ai --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yesterday-AI/paperclip-plugin-company-wizard.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/paperclip-ai .agents/skills/paperclip-ai && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "paperclip-ai" agent skill from https://github.com/Yesterday-AI/paperclip-plugin-company-wizard/tree/main/.claude/skills/paperclip-ai into .agents/skills/paperclip-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperclip-ai", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill paperclip-ai -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Yesterday-AI/paperclip-plugin-company-wizard paperclip-ai --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yesterday-AI/paperclip-plugin-company-wizard.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/paperclip-ai .cursor/skills/paperclip-ai && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "paperclip-ai" agent skill from https://github.com/Yesterday-AI/paperclip-plugin-company-wizard/tree/main/.claude/skills/paperclip-ai into .cursor/skills/paperclip-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperclip-ai", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Yesterday-AI/paperclip-plugin-company-wizard.git --path .claude/skills/paperclip-ai--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill paperclip-ai -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Yesterday-AI/paperclip-plugin-company-wizard paperclip-ai --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yesterday-AI/paperclip-plugin-company-wizard.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/paperclip-ai .gemini/skills/paperclip-ai && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "paperclip-ai" agent skill from https://github.com/Yesterday-AI/paperclip-plugin-company-wizard/tree/main/.claude/skills/paperclip-ai into .gemini/skills/paperclip-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperclip-ai", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Yesterday-AI/paperclip-plugin-company-wizard paperclip-aiInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill paperclip-ai -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Yesterday-AI/paperclip-plugin-company-wizard.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/paperclip-ai .github/skills/paperclip-ai && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "paperclip-ai" agent skill from https://github.com/Yesterday-AI/paperclip-plugin-company-wizard/tree/main/.claude/skills/paperclip-ai into .github/skills/paperclip-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperclip-ai", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill paperclip-ai -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Yesterday-AI/paperclip-plugin-company-wizard paperclip-ai --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Yesterday-AI/paperclip-plugin-company-wizard.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/paperclip-ai .opencode/skills/paperclip-ai && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "paperclip-ai" agent skill from https://github.com/Yesterday-AI/paperclip-plugin-company-wizard/tree/main/.claude/skills/paperclip-ai into .opencode/skills/paperclip-ai/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperclip-ai", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
paperclip-ai- GitHub stars
- 186
- Token cost
- ~2.5k tokens
- SKILL.md length
- 361 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Manage Paperclip AI companies, agents, issues, projects, goals, routines, costs, and secrets via REST API.
- Works in 7 steps: company create — creates the company → goal create --level company — set the… → agent hire for the CEO — triggers Board… → …
- Creating companies
- SKILL.md covers Quick Reference, Concepts, Task Hierarchy and Workflow: Creating a Company, plus 2 more sections
- Runs Shell scripts from its folder; needs PAPERCLIP_PASSWORD and OPENAI_KEY
What it does
Paperclip AI is an agent skill from Yesterday-AI/paperclip-plugin-company-wizard. Manage Paperclip AI companies, agents, issues, projects, goals, routines, costs, and secrets via REST API. Use when creating companies, hiring agents, assigning tasks, managing budgets, approving hires, or checking dashboards on a Paperclip instance.
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/paperclip.sh`).
It sits in Backend & APIs, covering REST APIs. The repository describes itself as: Bootstrap AI agent companies from modular templates. The licence is MIT.
When your agent uses it
- Creating companies
- Assigning tasks
- Managing budgets
- Approving hires
Example prompts
- “/paperclip-ai”
Requirements
- A Bash shell
- A credential in OPENAI_KEY
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- company create — creates the company
- goal create --level company — set the company mission goal
- agent hire for the CEO — triggers Board approval
- approval approve — Board approves the hire
- project create — create a project linked to the goal
- issue create — give the CEO their first strategic task
- CEO breaks it down into sub-issues, hires team, delegates
What it can do on your machine
Read from SKILL.md and the folder at commit 3eeca7d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Shell), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
PAPERCLIP_PASSWORDOPENAI_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Paperclip AI loads about 2.5k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 361 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from Yesterday-AI/paperclip-plugin-company-wizard at commit 3eeca7d, republished under its MIT licence (© Yesterday-AI). 361 words, ~2,476 tokens.
Download SKILL.mdSave it as
.claude/skills/paperclip-ai/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- paperclip-ai
- description
- Manage Paperclip AI companies, agents, issues, projects, goals, routines, costs, and secrets via REST API. Use when creating companies, hiring agents, assigning tasks, managing budgets, approving hires, or checking dashboards on a Paperclip instance.
Paperclip AI
Manage zero-human AI companies on a Paperclip instance. Companies have org charts, agents, issues (tickets), projects, goals, budgets, routines, and governance.
Quick Reference
All commands go through the wrapper script:
{baseDir}/scripts/paperclip.sh <command> [subcommand] [options]Environment
export PAPERCLIP_API_URL="https://your-instance.up.railway.app"
export PAPERCLIP_EMAIL="your-board-email"
export PAPERCLIP_PASSWORD="your-board-password"
export PAPERCLIP_COMPANY_ID="optional-default-company-id"Companies
# List all companies
{baseDir}/scripts/paperclip.sh company list
# Create a company
{baseDir}/scripts/paperclip.sh company create "Atlas Corp" "Map every job in DACH"
# Get company details
{baseDir}/scripts/paperclip.sh company get <company-id>
# Update company
{baseDir}/scripts/paperclip.sh company update <company-id> --name "New Name" --description "New desc"
# Export company (portability)
{baseDir}/scripts/paperclip.sh company export <company-id>Agents
# List agents in a company
{baseDir}/scripts/paperclip.sh agent list --company-id <id>
# Create an agent directly
{baseDir}/scripts/paperclip.sh agent create "Research Lead" "researcher" "Senior Researcher" "claude_local" --company-id <id>
# Hire via governance (triggers Board approval)
{baseDir}/scripts/paperclip.sh agent hire "Research Lead" "researcher" "Senior Researcher" "claude_local" --company-id <id>
# Get agent details / configuration
{baseDir}/scripts/paperclip.sh agent get <agent-id>
{baseDir}/scripts/paperclip.sh agent config <agent-id>
# Agent lifecycle
{baseDir}/scripts/paperclip.sh agent pause <agent-id>
{baseDir}/scripts/paperclip.sh agent resume <agent-id>
{baseDir}/scripts/paperclip.sh agent terminate <agent-id>
{baseDir}/scripts/paperclip.sh agent wakeup <agent-id>
# List agent API keys
{baseDir}/scripts/paperclip.sh agent keys <agent-id>Adapter types: claude_local, codex_local, cursor, openclaw_gateway, process, http, opencode_local, pi_local, hermes_local
Projects
# List projects
{baseDir}/scripts/paperclip.sh project list --company-id <id>
# Create project (linked to goal)
{baseDir}/scripts/paperclip.sh project create --name "Phase 1" --description "Initial research" --goal-id <goal-id> --lead-agent-id <agent-id> --company-id <id>
# Get / update project
{baseDir}/scripts/paperclip.sh project get <project-id>
{baseDir}/scripts/paperclip.sh project update <project-id> --status in_progressProject statuses: backlog, planned, in_progress, completed, cancelled
Goals
# List goals
{baseDir}/scripts/paperclip.sh goal list --company-id <id>
# Create goal (hierarchical)
{baseDir}/scripts/paperclip.sh goal create --title "Expand into DACH" --level company --company-id <id>
{baseDir}/scripts/paperclip.sh goal create --title "Research Immobilien" --level team --parent-id <goal-id> --owner-agent-id <agent-id> --company-id <id>
# Get / update goal
{baseDir}/scripts/paperclip.sh goal get <goal-id>
{baseDir}/scripts/paperclip.sh goal update <goal-id> --status achievedGoal levels: company, team, agent, task
Goal statuses: planned, active, achieved, cancelled
Issues (Tasks)
# List issues (filterable)
{baseDir}/scripts/paperclip.sh issue list --company-id <id>
{baseDir}/scripts/paperclip.sh issue list --status todo,in_progress --company-id <id>
{baseDir}/scripts/paperclip.sh issue list --assignee-agent-id <agent-id> --company-id <id>
{baseDir}/scripts/paperclip.sh issue list --project-id <project-id> --company-id <id>
# Create an issue
{baseDir}/scripts/paperclip.sh issue create --title "Research Immobilienwirtschaft" --description "Phase 1: Identify all company types" --priority high --assignee-agent-id <agent-id> --company-id <id>
# Create a sub-issue
{baseDir}/scripts/paperclip.sh issue create --title "WEG-Hausverwaltungen" --parent-id <parent-issue-id> --company-id <id>
# Create issue linked to project and goal
{baseDir}/scripts/paperclip.sh issue create --title "Research task" --project-id <id> --goal-id <id> --company-id <id>
# Update issue
{baseDir}/scripts/paperclip.sh issue update <issue-id> --status in_progress
{baseDir}/scripts/paperclip.sh issue update <issue-id> --assignee-agent-id <agent-id>
# Comment on an issue
{baseDir}/scripts/paperclip.sh issue comment <issue-id> --body "Research complete, 25 Spielwiesen identified"
# Checkout/release (atomic task assignment)
{baseDir}/scripts/paperclip.sh issue checkout <issue-id> --agent-id <agent-id>
{baseDir}/scripts/paperclip.sh issue release <issue-id>Issue statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled
Priority: critical, high, medium, low
Routines (Scheduled Tasks)
# List routines
{baseDir}/scripts/paperclip.sh routine list --company-id <id>
# Create routine (cron-based)
{baseDir}/scripts/paperclip.sh routine create --name "Daily standup" --schedule "0 9 * * *" --assignee-agent-id <agent-id> --company-id <id>
# Get / update / delete
{baseDir}/scripts/paperclip.sh routine get <routine-id>
{baseDir}/scripts/paperclip.sh routine update <routine-id> --schedule "0 */6 * * *"
{baseDir}/scripts/paperclip.sh routine delete <routine-id>
# Manually trigger
{baseDir}/scripts/paperclip.sh routine run <routine-id>Approvals (Governance)
# List pending approvals
{baseDir}/scripts/paperclip.sh approval list --status pending --company-id <id>
# Get approval details
{baseDir}/scripts/paperclip.sh approval get <approval-id>
# Approve / reject
{baseDir}/scripts/paperclip.sh approval approve <approval-id> --note "Looks good"
{baseDir}/scripts/paperclip.sh approval reject <approval-id> --note "Too expensive"
# Request revision / resubmit
{baseDir}/scripts/paperclip.sh approval request-revision <approval-id> --note "Needs more detail on budget"
{baseDir}/scripts/paperclip.sh approval resubmit <approval-id>
# Comment on approval
{baseDir}/scripts/paperclip.sh approval comment <approval-id> --body "What's the expected ROI?"Cost & Budget
# Company cost summary
{baseDir}/scripts/paperclip.sh cost summary --company-id <id>
# Cost breakdown by agent / project / provider
{baseDir}/scripts/paperclip.sh cost by-agent --company-id <id>
{baseDir}/scripts/paperclip.sh cost by-project --company-id <id>
{baseDir}/scripts/paperclip.sh cost by-provider --company-id <id>
{baseDir}/scripts/paperclip.sh cost finance --company-id <id>
# Budget overview (includes policies + active incidents)
{baseDir}/scripts/paperclip.sh budget overview --company-id <id>Secrets
# List / create / update / delete secrets
{baseDir}/scripts/paperclip.sh secret list --company-id <id>
{baseDir}/scripts/paperclip.sh secret create --name "OPENAI_KEY" --value "sk-..." --company-id <id>
{baseDir}/scripts/paperclip.sh secret update <secret-id> --value "sk-new..." --company-id <id>
{baseDir}/scripts/paperclip.sh secret delete <secret-id> --company-id <id>Dashboard, Activity & Org Chart
{baseDir}/scripts/paperclip.sh dashboard --company-id <id>
{baseDir}/scripts/paperclip.sh activity --agent-id <id> --company-id <id>
{baseDir}/scripts/paperclip.sh activity --entity-type issue --action created --company-id <id>
{baseDir}/scripts/paperclip.sh org --company-id <id>
{baseDir}/scripts/paperclip.sh healthConcepts
- Company = autonomous AI business with a mission, org chart, and budget
- Agent = AI employee (Claude, Codex, Cursor, etc.) with a role, title, and adapter
- Goal = hierarchical objective (company → team → agent → task)
- Project = scoped work with a lead agent, target date, and linked goal
- Issue = unit of work (ticket). Has status, priority, assignee, parent/children
- Routine = recurring scheduled task (cron, webhook, or API-triggered)
- Approval = governance gate. Agent hires and CEO strategy require Board approval
- Heartbeat = scheduled wake cycle. Agents check their issues and act
- Cost event = token usage tracked per agent, per issue, per project, per goal
- Budget policy = spending limit with auto-pause enforcement
Task Hierarchy
Goal (company) → Goal (team) → Project → Issue → Sub-issue
All work traces back to company goals for alignment and cost attribution.
Show full SKILL.md (142 more words)Show less
Workflow: Creating a Company
company create— creates the companygoal create --level company— set the company mission goalagent hirefor the CEO — triggers Board approvalapproval approve— Board approves the hireproject create— create a project linked to the goalissue create— give the CEO their first strategic task- CEO breaks it down into sub-issues, hires team, delegates
Auth
The script signs in with email + password via POST /api/auth/sign-in/email (BetterAuth), then uses the returned session cookie for all subsequent requests. Set PAPERCLIP_EMAIL and PAPERCLIP_PASSWORD env vars.
API Notes
- All responses are JSON
- Issues support single-assignee atomic checkout (prevents double-work)
- Costs are tracked per agent, per issue, per project, per goal
- Budget policies auto-pause agents when spending limits are exceeded
- Routines replace expensive always-on agent heartbeats with scheduled execution
- Company export/import enables portability and templating
© Yesterday-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (scripts) in .claude/skills/paperclip-ai of Yesterday-AI/paperclip-plugin-company-wizard.
- SKILL.md
- scripts/paperclip.sh
Open the folder on GitHubat commit 3eeca7d
Compare with similar skills
Paperclip AI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Paperclip AI this skillYesterday-AI/paperclip-plugin-company-wizard | 186 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Paperclippaperclipai/paperclip | 100k | — | ~9.6k | Automated safety check: Pass | MIT | |
| Nodejs Backend Patternsever-works/ever-works | 162 | 18 repos | ~4k | Automated safety check: Pass | AGPL-3.0 | |
| OpenAPI to MCP Servermcp-use/mcp-use | 11k | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Use Yaakmountain-loop/yaak | 19k | — | ~1.9k | Automated safety check: Pass | MIT | |
| API DesignerJeffallan/claude-skills | 12k | 1 repos | ~2k | Automated safety check: Pass | MIT |
Similar skills
Nodejs Backend Patterns
ever-works/ever-works
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices.
OpenAPI to MCP Server
mcp-use/mcp-use
Turns an OpenAPI or Swagger spec into an MCP server with the mcp-use TypeScript SDK, mapping each operation to a tool, wiring auth, testing and deploying.
Use Yaak
mountain-loop/yaak
A skill your agent uses when the user mentions Yaak, a Yaak workspace, or the yaak command, or asks to call, hit, or smoke test HTTP/REST endpoints, save or organize API requests for reuse or manual…
API Designer
Jeffallan/claude-skills
Designs REST and GraphQL APIs from resource modeling to an OpenAPI 3.1 contract, with versioning, pagination and RFC 7807 error handling.
RuView CLI, API and WASM
ruvnet/RuView
Covers the RuView `wifi-densepose` command line binary, its Axum REST API and the WebAssembly builds for browsers and ESP32, for embedding or scripting RuView.
More from Yesterday-AI/paperclip-plugin-company-wizard
Release
Yesterday-AI/paperclip-plugin-company-wizard
Prepare a new release by updating CHANGELOG.md, verifying documentation (README.md, CLAUDE.md, AGENTS.md, ROADMAP.md, docs/), bumping patch version in package.json, building, and suggesting publish…
Routines
Yesterday-AI/paperclip-plugin-company-wizard
Set up and manage Paperclip Routines — recurring scheduled tasks that replace expensive always-on heartbeats.
Setup Routines
Yesterday-AI/paperclip-plugin-company-wizard
Analyze a Paperclip company's issue history, agent health, recurring failure patterns, and project architecture to design and provision tailored routines with cron/webhook triggers.
Related
Categories
Questions about Paperclip AI
What does Paperclip AI do?
Manage Paperclip AI companies, agents, issues, projects, goals, routines, costs, and secrets via REST API. Paperclip AI is an agent skill from Yesterday-AI/paperclip-plugin-company-wizard. Manage Paperclip AI companies, agents, issues, projects, goals, routines, costs, and secrets via REST API.
When should I use Paperclip AI?
Paperclip AI fits situations like: creating companies; assigning tasks; managing budgets; approving hires.
How do I install Paperclip AI in Claude Code?
Run `npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill paperclip-ai -a claude-code`. Or copy the skill folder (.claude/skills/paperclip-ai in Yesterday-AI/paperclip-plugin-company-wizard) into .claude/skills/paperclip-ai in your project. Claude Code loads it when a task matches its description.
How do I install Paperclip AI in Codex?
Run `npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill paperclip-ai -a codex`. Or copy the skill folder (.claude/skills/paperclip-ai in Yesterday-AI/paperclip-plugin-company-wizard) into .agents/skills/paperclip-ai in your project. Codex loads it when a task matches its description.
Can I use Paperclip AI in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill paperclip-ai -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paperclip-ai, .gemini/skills/paperclip-ai, .github/skills/paperclip-ai and .opencode/skills/paperclip-ai in your project.
What does Paperclip AI need to run?
Going by SKILL.md and its folder, Paperclip AI needs a shell for the scripts in its folder and credentials named PAPERCLIP_PASSWORD and OPENAI_KEY. Our summary lists: A Bash shell; A credential in OPENAI_KEY.
Does Paperclip AI access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Paperclip AI safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Paperclip AI use?
Paperclip AI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Paperclip AI use?
About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Paperclip AI?
Skills that share tags, products or a category with Paperclip AI: Paperclip (paperclipai/paperclip, 100k stars), Nodejs Backend Patterns (ever-works/ever-works, 162 stars), OpenAPI to MCP Server (mcp-use/mcp-use, 11k stars) and Use Yaak (mountain-loop/yaak, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Paperclip AI?
Yesterday-AI (a GitHub organization) maintains it in Yesterday-AI/paperclip-plugin-company-wizard, which has 186 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on April 22, 2026.
Source: Yesterday-AI/paperclip-plugin-company-wizard on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.