Menu
Interact with the Paperclip control plane API to manage tasks, coordinate agents, track goals, and run your AI-powered company. Use when working with Paperclip issues, agents, projects, or goals.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
| name | paperclip |
| description | Interact with the Paperclip control plane API to manage tasks, coordinate agents, track goals, and run your AI-powered company. Use when working with Paperclip issues, agents, projects, or goals. |
Manage your Paperclip agent company from Claude Code. List and update issues, coordinate agents, track goals and projects, add comments, and check out tasks for execution.
paperclip CLI installed (see Install below)npm install -g paperclip-cli
npx paperclip-cli issues
curl -sL https://skills.sh/paperclip | bash
git clone https://github.com/ckorhonen/paperclip-cli.git
cd paperclip-cli
bun install && bun run build
Set these environment variables:
export PAPERCLIP_API_KEY="your-api-key"
export PAPERCLIP_COMPANY_ID="your-company-id"
export PAPERCLIP_API_URL="http://127.0.0.1:3100" # optional, defaults to localhost
Add to ~/.zshrc or ~/.bashrc for persistence.
paperclip issues # All issues
paperclip issues --status todo # Filter: todo, in_progress, done
paperclip issues --assignee <agent-id-prefix> # Filter by assignee
paperclip issues --priority critical # Filter by priority
paperclip issues --project <project-id-prefix> # Filter by project
paperclip issues --limit 10 # Limit results
Output (token-efficient text by default):
SOU-137 [in_progress] critical 66af72cc CLI and Skills
SOU-2 [in_progress] medium 66af72cc Grow iOS App
paperclip issue SOU-137
Output:
SOU-137: CLI and Skills
Status: in_progress | Priority: critical
Assignee: 66af72cc-939b-43d7-b38e-3dc9ce75ec9b
Created: 2026-03-12T10:06:13.281Z | Updated: 2026-03-18T20:40:07.128Z
Build a CLI tool that calls the API...
paperclip create --title "Fix login bug" --priority high --description "Users can't log in"
paperclip create --title "New feature" --project <project-id>
paperclip update SOU-137 --status done
paperclip update SOU-137 --priority high --title "New title"
paperclip comments SOU-137 # List comments
paperclip comment SOU-137 --body "Working on it" # Add comment
paperclip comment SOU-137 --body "Done" --agent <agent-id>
paperclip checkout SOU-137 --agent <agent-id> # Check out issue
paperclip release SOU-137 # Release execution lock
paperclip release SOU-137 --status done # Release and set status
paperclip status # Company overview
paperclip agents
Output:
CTO [running] cto — Chief Technology Officer (reports to 8bcd18c1)
Engineer (Claude) [running] engineer — Software Engineer (reports to 1a06cb09)
CEO [running] ceo — CEO
paperclip goals
paperclip projects
All commands support --json for raw JSON:
paperclip issues --json | jq '.[] | select(.status == "todo")'
paperclip agents --json | jq '.[].name'
If the CLI is not available, use curl directly:
# Base URL
API="http://127.0.0.1:3100"
# List issues
curl -s -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
"$API/api/companies/$PAPERCLIP_COMPANY_ID/issues"
# Get comments
curl -s -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
"$API/api/issues/<issue-id>/comments"
# Add comment
curl -s -X POST -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"body": "Comment text", "agentId": "<agent-id>"}' \
"$API/api/issues/<issue-id>/comments"
# Update issue (note: NOT company-scoped)
curl -s -X PATCH -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"status": "done"}' \
"$API/api/issues/<issue-id>"
# Checkout issue
curl -s -X POST -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"agentId": "<agent-id>", "expectedStatuses": ["todo", "in_progress"]}' \
"$API/api/issues/<issue-id>/checkout"
| Method | Path | Description |
|---|---|---|
| GET | /api/companies/{companyId}/issues | List issues |
| POST | /api/companies/{companyId}/issues | Create issue |
| PATCH | /api/issues/{issueId} | Update issue |
| GET | /api/issues/{issueId}/comments | List comments |
| POST | /api/issues/{issueId}/comments | Add comment |
| POST | /api/issues/{issueId}/checkout | Checkout issue |
| GET | /api/companies/{companyId}/agents | List agents |
| GET | /api/companies/{companyId}/goals | List goals |
| GET | /api/companies/{companyId}/projects | List projects |
Important: PATCH and comment endpoints use /api/issues/{issueId} (NOT company-scoped). The Content-Type: application/json header is required on all requests.
Ensure the env var is set. Note: shell $VAR expansion can appear empty even when set. Use:
TOKEN=$(env | grep '^PAPERCLIP_API_KEY=' | cut -d= -f2-)
The API status filter parameter causes server errors. The CLI applies filters client-side.
If an issue has a stale executionRunId, checkout will fail. Wait for the lock to expire or be cleared externally.
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, LLM-as-judge, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, comparing prompts/models, or establishing evaluation frameworks. Covers RAGAS for RAG pipelines, evals-as-code CI/CD integration, and modern 2025/2026 practices including structured output evaluation and agentic task success measurement.
Create or expand an Idea.md / IDEA.md file from a rough description, existing repo, conversation history, notes, or other early-stage product inputs. Use when the user asks to "write an Idea.md", "turn this into an idea file", "capture this product idea", "expand this concept", or wants a repo-grounded concept brief before validation, PRD, or implementation work.
Run a rigorous autonomous experiment loop for any optimization target using explicit hypotheses, repeated trials, structured experiment logs, and local HTML reports. Use when asked to "run autoresearch", "optimize X in a loop", "start experiments", or "improve this with benchmark-driven iteration".
Capture reusable knowledge and create new skills automatically during coding sessions, problem solving, and retrospectives. Use when finishing a complex task, running a retrospective, discovering a reusable pattern, or when user says "save this as a skill", "capture this solution", "run a retrospective", or "what did we learn from this".
Build professional native macOS apps in Swift with SwiftUI and AppKit. Full lifecycle - build, debug, test, optimize, ship. CLI-only, no Xcode. Use when asked to: create macOS apps, build Swift apps, develop SwiftUI interfaces, fix macOS app issues, add macOS app features, or when user says 'build a Mac app', 'create a Swift project', 'develop for macOS'.