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 ckorhonen/claude-skills --skill paperclipgit clone --depth 1 https://github.com/ckorhonen/claude-skillsWrote 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/ckorhonen/claude-skills/paperclip)<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/paperclip"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/paperclip/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/ckorhonen/claude-skills/paperclip"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/paperclip.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 | $0.00043 | $0.01648 |
| Opus 5 | $0.00022 | $0.00824 |
| Sonnet 5 | $0.00009 | $0.00330 |
| Haiku 4.5 | $0.00004 | $0.00165 |
Grade C, and why
paperclip scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sL https://skills.sh/paperclip | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL https://skills.sh/paperclip | bash How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paperclip
Overview
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.
When to Use
- Listing, creating, or updating issues/tasks
- Checking out issues for agent execution
- Viewing agent status and assignments
- Tracking company goals and project progress
- Adding comments to issues
- Getting a quick status overview of the company
Prerequisites
paperclipCLI installed (see Install below)- Environment variables configured
Install
Via npm (recommended)
npm install -g paperclip-cli
Via npx (no install)
npx paperclip-cli issues
Via skills.sh
curl -sL https://skills.sh/paperclip | bash
From source
git clone https://github.com/ckorhonen/paperclip-cli.git
cd paperclip-cli
bun install && bun run build
Configuration
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.
CLI Commands
List issues
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
Get issue detail
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...
What ships with it
3 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 · 240 lines · 43 tokens per session scan C 7bfd7c485793
paperclip is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,648 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.