routines

routines is a skill for Claude Code from Yesterday-AI/paperclip-plugin-company-wizard. It costs 67 tokens per session (2,298 once invoked), scanned A, original, MIT.

A skill for Paperclip, a system that schedules work for AI agents. It uses recurring schedules, webhooks, or API calls to start agent tasks when needed.

In plain words
What is it for?
Use it to create and manage scheduled or triggered agent tasks, including their timing and concurrency rules.
Why use it?
It avoids having agents repeatedly check for work on a timer, which can waste computing and language-model usage.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to create and manage scheduled or triggered agent tasks, including their timing and concurrency rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yesterday-ai/paperclip-plugin-company-wizard/routines
Install

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.

Any agent
npx skills add Yesterday-AI/paperclip-plugin-company-wizard --skill routines
Clone the repo
git clone --depth 1 https://github.com/Yesterday-AI/paperclip-plugin-company-wizard

Made for: Claude Code.

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 routines

README.md
[![agentmods](https://agentmods.dev/badge/skills/yesterday-ai/paperclip-plugin-company-wizard/routines/github.svg)](https://agentmods.dev/skills/yesterday-ai/paperclip-plugin-company-wizard/routines)
Your own site
<a href="https://agentmods.dev/skills/yesterday-ai/paperclip-plugin-company-wizard/routines"><img src="https://agentmods.dev/badge/skills/yesterday-ai/paperclip-plugin-company-wizard/routines/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 routines

Your own site · 80×15
<a href="https://agentmods.dev/skills/yesterday-ai/paperclip-plugin-company-wizard/routines"><img src="https://agentmods.dev/badge/skills/yesterday-ai/paperclip-plugin-company-wizard/routines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00067 $0.02298
Opus 5 $0.00034 $0.01149
Sonnet 5 $0.00013 $0.00460
Haiku 4.5 $0.00007 $0.00230

Measured 12d ago against content hash 02224e840381, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

routines scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "$PAPERCLIP_API_URL/api/agents/me" \
.claude/skills/routines/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Routines — Recurring Agent Tasks

Routines are Paperclip's scheduling primitive. Instead of agents burning tokens on timer heartbeats polling for work, routines fire only when needed — on a cron schedule, webhook, or explicit API call — and create a targeted heartbeat run for the assigned agent.

Why Routines > Always-On Heartbeats

Approach Token cost Responsiveness
Heartbeat every 5 min ~288 runs/day, most idle High but wasteful
Routines (cron + webhook) Only fires when scheduled or triggered Same responsiveness, fraction of the cost

The key insight: clean up heartbeats = token reducing = cheaper.

Quick Start

1. Find your IDs

# Company ID
curl -s "$PAPERCLIP_API_URL/api/agents/me" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY" | jq '.companyId, .id'

# Agents in company
curl -s "$PAPERCLIP_API_URL/api/companies/{companyId}/agents" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY" | jq '.[] | {id, name, role}'

# Projects
curl -s "$PAPERCLIP_API_URL/api/companies/{companyId}/projects" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY" | jq '.[] | {id, name}'

2. Create a routine

curl -s -X POST "$PAPERCLIP_API_URL/api/companies/{companyId}/routines" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Daily standup check",
    "description": "CEO reviews all in_progress issues and nudges stalled agents",
    "assigneeAgentId": "{ceo-agent-id}",
    "projectId": "{project-id}",
    "priority": "medium",
    "status": "active",
    "concurrencyPolicy": "skip_if_active",
    "catchUpPolicy": "skip_missed"
  }'

3. Add a cron trigger

curl -s -X POST "$PAPERCLIP_API_URL/api/routines/{routineId}/triggers" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "kind": "schedule",
    "cronExpression": "0 9 * * 1-5",
    "timezone": "Europe/Amsterdam"
  }'

Read the full file on GitHub · 239 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. 12d ago First seen · 239 lines · 67 tokens per session scan A 02224e840381

Subscribe to this mod's changes

routines is a skill published in the GitHub repository Yesterday-AI/paperclip-plugin-company-wizard (171 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 2,298 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.