paperclip: Skill for Claude Code

.agents/skills/prepare-paperclip-pr/SKILL.md

prepare-paperclip-pr is a skill for Claude Code, Codex from paperclipai/paperclip. It costs 21 tokens per session (983 once invoked), scanned A, original, MIT.

A procedure for preparing work on a Git branch as a pull request, which is a proposed change for review before it is added to the main codebase.

In plain words
What is it for?
Use it to turn branch work into a pull request against Paperclip’s master branch, including logical commits, a standard description, and verification.
Why use it?
It makes sure changes are committed, placed in the correct worktree, and accompanied by the expected checks and pull-request details. This helps reviewers receive a complete, reviewable contribution.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is paperclipai/paperclip's own configuration. It tells Claude Code and Codex how to work on paperclip itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paperclip configures →

About the project

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.

paperclipai/paperclip · 80,385 stars · on GitHub · paperclip.ing

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/paperclipai/paperclip/master/.agents/skills/prepare-paperclip-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/paperclipai/paperclip

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for prepare-paperclip-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/paperclipai/paperclip/prepare-paperclip-pr/github.svg)](https://agentmods.dev/skills/paperclipai/paperclip/prepare-paperclip-pr)
Your own site
<a href="https://agentmods.dev/skills/paperclipai/paperclip/prepare-paperclip-pr"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/prepare-paperclip-pr/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.

agentmods 80×15 button for prepare-paperclip-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/paperclipai/paperclip/prepare-paperclip-pr"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/prepare-paperclip-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 983 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00983
Opus 5 $0.00010 $0.00491
Sonnet 5 $0.00004 $0.00197
Haiku 4.5 $0.00002 $0.00098

Measured 11d ago against content hash 61e9ff0adcf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prepare-paperclip-pr 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.

.agents/skills/prepare-paperclip-pr/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare Paperclip PR

The standard Paperclip procedure for turning branch work into a reviewed, green pull request against paperclipai/paperclip master. Apply it once per PR (if a task splits a branch into several PRs, run the whole procedure for each one).

0. Preconditions — worktree safety

  • Do all PR work in a git worktree on a dedicated branch. The main ~/paperclip checkout typically runs the live Paperclip server — never check out branches there. If you are already on a worktree/branch, verify it (git rev-parse --git-dir, git branch --show-current) and proceed.
  • If the main checkout is unexpectedly off master, fix that first without losing work (usually: move that branch's work into a worktree).
  • Confirm which remote/ref you are targeting (normally master on the paperclipai/paperclip repo; the task may name a specific remote such as origin or public-gh).

1. Commit everything — lose no work

  • Make logical commits of all uncommitted changes before anything else. Do not stash and forget; do not leave files behind. If commits are missing, make them.
  • Commit messages must end with exactly: Co-Authored-By: Paperclip <[email protected]>

2. Get changes cleanly on top of master

  • Fetch the target remote and rebase (or otherwise replay) your branch on top of the target master so the PR has no merge conflicts.
  • Re-verify after rebase: build/tests relevant to the change still pass at whatever depth the task warrants.

3. Guardrails checklist (every PR)

  • Never commit pnpm-lock.yaml — the repo has actions that manage it. If it is already in a commit, rewrite/drop that change before pushing.
  • Never change .github/workflows/* unless the underlying commit was explicitly about that and the task calls it out.
  • No design screenshots / wireframe images committed to the repo unless they are genuinely part of the work product.
  • Migrations: numbered incrementally with no conflicts against master. If master moved and took your number, renumber on top. Make migrations idempotent so users who already applied the old number are safe.
  • Greptile file limit: keep each PR under 100 changed files; if a PR exceeds that, split it into two.

Read the full file on GitHub · 86 lines

Changes

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.

  1. 11d ago First seen · 86 lines · 21 tokens per session scan A 61e9ff0adcf8

Subscribe to this mod's changes

prepare-paperclip-pr is a skill published in the GitHub repository paperclipai/paperclip (80,385 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 983 once invoked, about $0.0001 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.