Operations
For the people who keep the company running: vendor renewals, runbook hygiene, cross-team status, recurring-meeting documentation. Whether you sit in BizOps, RevOps, IT, or the founder's chair, the patterns repeat.
Weekly cross-team status digest
Monday standup walks in with the picture already in everyone's head.
One sub-agent per department fans out and pulls progress from Linear / Slack / Notion; the coordinator rolls everything up into a single cross-team status doc by Friday afternoon. Monday standup walks in with the picture already in everyone's head.
How to set it up
- 1
Install the operations plugin
Install in Cowork ↗claude plugin install operations@pace - 2
Authorize Linear (or Jira), Slack, Notion
Whichever ones your teams actually use. OAuth opens for each on first use.
- 3
Create the scheduled routine
In Cowork, open Routines → New routine → Schedule · Weekly · Friday · 14:00.
- 4
Paste this as the routine prompt
Edit the team list to match your org structure.
Routine prompt Run status-report. Spawn one sub-agent per team to pull progress signals from the last 7 days: - Engineering: closed Linear tickets, merged PRs, incidents - Product: spec updates, sprint progress - Sales: closed-won, pipeline movement (top-line) - Marketing: shipped campaigns, performance - Customer Support: ticket volume, escalations A coordinator sub-agent rolls them into one Friday digest: "what shipped" at the top, blockers + risks in the middle, next-week focus at the bottom. Post to #leadership-friday in Slack and mirror to docs.pace/status/<YYYY-MM-DD> in Notion.
- 5
Click Run now to verify
Read the first digest carefully : adjust the per-team scope until the rollup matches how your org actually thinks about "progress". Once it's right, Fridays at 14:00 are hands-off.
Vendor renewal heads-up, 60 days out
Reads the vendor register, finds contracts renewing in the next 60 days, runs vendor-evaluation against current usage and alternatives, and posts a brief to the owner with a recommend / renegotiate / replace call. No-op on days with no upcoming renewals.
How to set it up
- 1
Create the scheduled routine in Cowork
In Cowork, open Routines → New routine → Schedule. Match the cadence described in the trigger above.
- 2
Paste this as the routine prompt
Vendor renewal scan prompt Every weekday at 9am, scan the vendor register for contracts renewing in the next 60 days. For each one, run vendor-evaluation against current usage data and recent comparable alternatives. Produce a brief: current usage, contract value, renewal-or-renegotiate-or-replace recommendation, three specific reasons. Post to the contract owner. No-op on days with no upcoming renewals (don't ping the channel).
- 3
Click Run now to verify
Eyeball the first run for accuracy. Once it looks right, the routine fires on its trigger from then on. Assumes the plugin from the marquee above is already installed and connectors authorized.
Document the recurring meeting that has no document
You walk Claude through how the recurring meeting actually runs (verbally or by pasting notes). It produces the runbook: agenda template, what to prep, who owns what, how decisions get logged. Drops it into Notion under the right team space. The next time someone new owns the meeting, they have a place to start.
How to set it up
- 1
Create the Cowork hook
In Cowork, open Hooks → New hook. Match the trigger described above (file upload, message, schedule).
- 2
Paste this as the routine prompt
Document-process prompt I want to document the [recurring meeting name] so the next person who owns it can run it solo. I'll paste the meeting notes and Slack threads; you walk me through what makes the meeting work, what the agenda template should be, what to prep, who owns what, how decisions get logged. Produce a runbook in Notion under the right team space. Plan mode parks it for my review.
- 3
Click Run now to verify
Eyeball the first run for accuracy. Once it looks right, the routine fires on its trigger from then on. Assumes the plugin from the marquee above is already installed and connectors authorized.
Runbook updated automatically after every incident
When an incident closes in PagerDuty, a routine pulls the incident timeline, the resolution thread from Slack, and any changes made to fix it. Drafts an update to the relevant runbook (or creates a new one) with the new failure mode and the fix. Plan mode parks the diff for the on-call engineer's approval. Tribal knowledge stops dying with the on-call shift.
How to set it up
- 1
Create the API-triggered routine
In Cowork, open Routines → New routine → API. Save and copy the routine URL + bearer token; point the upstream webhook at it (e.g. calendar provider, Intercom webhook, PagerDuty webhook, depending on the trigger).
- 2
Paste this as the routine prompt
Incident runbook update prompt When a PagerDuty incident closes, pull the incident timeline, the resolution thread from #incident-XYZ, and any changes made to fix it. Read the relevant runbook for this service. Draft an update: add the new failure mode + the resolution to the runbook. If no runbook exists for this failure mode, create one. Park the diff in plan mode for the on-call engineer to approve.
- 3
Click Run now to verify
Eyeball the first run for accuracy. Once it looks right, the routine fires on its trigger from then on. Assumes the plugin from the marquee above is already installed and connectors authorized.