Recurring agent work, on a schedule.

Save a prompt once. ProPR runs it every Monday, every night, or whenever you ask, researches your repositories or the web, and delivers a Markdown report. Approve the report and it becomes tasks.

Anatomy of a run

Trigger. A schedule, Run now, an HTTP call, chat, or propr automation run.
Report. The agent researches in an isolated run and writes Markdown.
Act, if you allow it. A second run turns the report into tasks, plans, goals, TODOs and PR comments.

A saved prompt with a job to do.

Write the instructions once. ProPR runs them with the same isolation, models and records as every other task.

Four automations with their coding agent, schedule and last run: one awaiting approval, one deferred — Each automation shows its agent, schedule and how the last run ended.

The weekly dependency review reads two repositories, northwind/storefront-web and northwind/orders-api; up to ten are allowed

The definition

A name, a prompt, the coding agent and model, and up to ten repositories. Leave the repositories out and the agent works from your prompt, input files and the web.

The automation prompt names dependency-policy.md, attached below it as an input file

Input files

Attach up to ten files: a checklist, a dependency policy, a list of competitors. Every run finds them in its workspace.

Previous reports switched on: the last two reports feed back into the next run

Memory across runs

Feed the last one to five reports into the next run, so a weekly review compares this week with the last.

Start a run from anywhere.

Every trigger lands in the same run history.

Run now
Start a run from the web UI.
HTTP
One POST starts a run from GitHub Actions, a webhook or an external cron.
MCP
Ask your chat client to run an automation, read its report and approve the next step. MCP from chat
CLI
propr automation starts runs, waits for them and prints the report.

Schedule

Pick a preset or write five-field cron, in UTC, as often as every 15 minutes. The editor previews the next run.

From a report to actions, at the autonomy you choose.

An optional acting step reads the report and files the work through ProPR's own tools. It cannot merge, deploy, change settings or push code; new code still arrives as a pull request for your review, under the same human approval steps that govern every AI-written change.

Autonomy set to Preview & approve: the acting step waits for approval before it uses ProPR tools — One switch per automation decides what happens after the report.

Monday 09:00: report, approval, tasks.A weekly dependency review fires on schedule and reports in Markdown. You approve with a note, and the acting step files two tasks and a TODO. The tasks start right away.

Dry run

The default. ProPR saves the report for you to read, and the run ends there.

A preview-mode run awaiting approval, with the note "Only fix auth-tokens." for the acting agent

Preview + approve

Read the report, then approve it with a note for the acting agent, or reject it and keep the report.

Auto

The acting step runs as soon as the report is ready and files tasks, plans, goals, TODOs and PR comments on its own.

It checks before it files.

The acting step looks for existing tasks and TODOs first, so a weekly report never files the same work twice. Every call it makes shows in the MCP Log.

What the acting agent did after approval: one task for auth-tokens, exactly as the note asked, after checking for duplicates — The acting step filed one task, as the note asked, after checking for duplicates.

Give each automation only what it needs.

Every automation reads its repositories. Add web access or ProPR tools where the job calls for them.

Per-automation capabilities: read repositories and web access on, ProPR tools off — Repository reads on by default; web access and ProPR tools switched per automation.

Capability	What the report step gets	Coding agents
Read repositories (default)	A read-only checkout of the selected repositories.	All five agents
Web access	Web search and page fetches while it researches.	All five agents; blocked natively when off on Claude Code and Codex
ProPR tools	Read-only access to tasks, goals and plans.	Claude Code and Codex

Preview + approve and Auto run on Claude Code and Codex with the instance's MCP server on. An extension profile adds your own MCP servers and skills.

Scheduled runs respect your subscription.

Before an unattended run starts, ProPR checks the agent's remaining capacity in Agent Tank. With a current reading at the pause threshold, 90% usage by default, ProPR skips the run when the weekly allowance is past it and defers the run when the session window is.

A scheduled run deferred because the agent's session usage is above the 90% pause threshold — A scheduled run deferred until the session window resets.

Four automations to start with.

Weekly dependency review

Every Monday the agent reviews the repository's dependencies and reports what needs attention. Approve with a note such as "Only fix auth-tokens" and the acting step files exactly that work.

Blocked pull requests

"Review open pull requests in these repositories and summarize which ones are blocked and why." A digest of stalled work that compares each run with the last.

An issue triage report: one payments issue to act on first, two likely duplicates, two issues missing reproduction steps

Nightly issue triage

Summarize new issues overnight, then ask your chat client what last night's triage found.

The competitor scan's capabilities: web access on, no repository to read

Competitor scan from chat

Web access, no repository. Tell your chat client to run the scan now and read the report when it lands.

Trigger it from CI.

The CLI waits for the run and prints the Markdown report, so a workflow step can save it.

npx propr-cli automation run "$AUTOMATION_ID" \
  --idempotency-key "$GITHUB_RUN_ID" \
  --source github-actions \
  --wait > report.md

Create in the web UI.

Create and edit automations in the web UI or over the REST API. MCP and the CLI start runs, read reports and decide on the acting step.

Read the details.

The Automations guide covers schedules, triggers and the capacity gate. The CLI reference covers propr automation, and the MCP documentation covers connecting a chat client.