codemod-runner
AgentWrites and runs codemod scripts that replace hardcoded visual values with token references in ui/src/index.css. Use for Phase 2…
Bounded, paused-by-default sweep that regenerates summary slots whose underlying scope has changed since the last revision. Spends no tokens until an operator enables its schedule or runs it manually. Read-and-report only — it never mutates issues, workspaces, or code.
Claude Code
$ npx -y skills add paperclipai/paperclip --agent claude-code
Cursor
Cursor also loads subagents from .claude/agents, so copy this file there to use it in Cursor.
routineKey: refresh-stale-summaries
title: Refresh stale summary slots
description: Bounded, paused-by-default sweep that regenerates summary slots whose underlying scope has changed since the last revision. Spends no tokens until an operator enables its schedule or runs it manually. Read-and-report only — it never mutates issues, workspaces, or code.
assigneeRef:
resourceKind: agent
resourceKey: summarizer
status: paused
priority: medium
concurrencyPolicy: coalesce_if_active
catchUpPolicy: skip_missed
variables:
- name: staleAfterHours
label: Refresh slots older than (hours)
type: number
defaultValue: 24
required: false
options: []
- name: maxSlots
label: Max slots to refresh per run
type: number
defaultValue: 10
required: false
options: []
- name: scopeKinds
label: Scope kinds to include
type: select
defaultValue: all
required: false
options:
- all
- project
- workspaces_overview
- project_workspace
- execution_workspace
triggers:
- kind: schedule
label: Daily stale-summary refresh
enabled: false
cronExpression: "0 8 * * *"
timezone: UTC
signingMode: none
replayWindowSec: 0
issueTemplate:
surfaceVisibility: normalThis routine is **paused by default** and spends no tokens until an operator enables its schedule or triggers a manual run. The first release of the Summarizer is manual-generation-first; this routine exists so operators can opt into scheduled refreshes without background spend by default.
1. Select summary slots whose scope has changed since their last revision and whose `lastGeneratedAt` is older than `{{staleAfterHours}}` hours. Restrict to `{{scopeKinds}}` when a specific kind is chosen. Cap the set at `{{maxSlots}}`, most-stale first. 2. For each selected slot, run the `summarize-status` skill as the operating procedure: read the current revision, read the company-scoped state you need to understand where things are, and write one new Markdown revision back to the slot. 3. Skip slots with no meaningful change since their last revision — do not spend tokens rewriting an unchanged summary.
A single bounded routine issue that links the slots refreshed this run, plus a summary comment listing: scopes summarized, revisions written, slots skipped as unchanged, and any slot that could not be read (with the unblock owner).
Open-source orchestration for teams of AI agents. If OpenClaw is an employee, Paperclip is the company. Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business.
Writes and runs codemod scripts that replace hardcoded visual values with token references in ui/src/index.css. Use for Phase 2…
Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces…
Bounded reflection sweep over recently active agents that produces evidence-backed coaching proposals only. Never mutates another…
Complete migration plan for converting command-based system to intelligent agent-based system
Accessibility standards and assistive features — remapping, text scaling, colorblind modes, screen reader support.
Use this agent to verify that tasks marked as 'review' have been properly implemented according to their specifications. This…