refresh-stale-summaries
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.
$ npx -y skills add paperclipai/paperclip --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
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.
Agent definition
refresh-stale-summaries.mdroutineKey: 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
triggers:
- kind: schedule
label: Daily stale-summary refresh
enabled: false
cronExpression: "0 8 * * *"
timezone: UTC
signingMode: none
replayWindowSec: 0
issueTemplate:
surfaceVisibility: normalRefresh stale summary slots
This 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.
What this run must do
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.
Hard limits for this routine
- Read-and-report only. This routine must never change issues, workspaces, code, or agent configuration — its only write is the summary revision.
- Keep every read company-scoped. Do not cross company boundaries.
- Run on the low-cost model profile lane (`cheap`). Keep each summary short.
- Never fabricate status and never surface secrets from issue bodies or configs.
Output
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).
Read more
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
triggers:
- kind: schedule
label: Daily stale-summary refresh
enabled: false
cronExpression: "0 8 * * *"
timezone: UTC
signingMode: none
replayWindowSec: 0
issueTemplate:
surfaceVisibility: normalRefresh stale summary slots
This 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.
What this run must do
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.
Hard limits for this routine
- Read-and-report only. This routine must never change issues, workspaces, code, or agent configuration — its only write is the summary revision.
- Keep every read company-scoped. Do not cross company boundaries.
- Run on the low-cost model profile lane (`cheap`). Keep each summary short.
- Never fabricate status and never surface secrets from issue bodies or configs.
Output
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.
Repo: paperclipai/paperclip
Other agents on paperclip.
- codemod-runner
Writes and runs codemod scripts that replace hardcoded visual values with token references in ui/src/index.css. Use for Phase 2 of the design simplification run — mechanical refactors only.
Open agent - token-auditor
Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces doc/design/TOKEN-AUDIT.md and doc/design/COMPONENT-INVENTORY.md. Read-only on source — never modifies component files. Use for Phase 1 of the design simplification run.
Open agent - recent-agent-reflection
Bounded reflection sweep over recently active agents that produces evidence-backed coaching proposals only. Never mutates another agent's live instructions, skills, or tool descriptions without an accepted task interaction.
Open agent - coder
Use this template when hiring software engineers who implement code, debug issues, write tests, and coordinate with QA or engineering leadership.
Open agent - qa
Use this template when hiring QA engineers who reproduce bugs, validate fixes, capture screenshots, and report actionable findings.
Open agent - securityengineer
Use this template when hiring security engineers who own security posture: threat-model systems, review auth/crypto/input handling, triage supply-chain and LLM-agent risk, and drive concrete remediations.
Open agent

