agentleFS
matthewdonsemail-labmatthewdonsemail-lab/log/skills/lifecycle/SKILL.md

lifecycle

Skill63 starsChanged 3 days agoMITView on GitHub

The account lifecycle (rule 35): one XState machine per Facebook account from import to its host, the browser opened once per local day and kept open, onboarding (proxy, sign-in, checks, profile, name, location, a day of warm-up) and host (watching, acting, overnight). Use when the owner asks where an account is, what it has left, what happens on a checkpoint or restriction, or to change the lifecycle.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

lifecycle

Hard boundaries

  1. The browser stays open. One open per account per local day (plus one crash reopen); every action is a step or a tab inside it; every close has a logged reason (top of AGENTS.md, rule 35). Never add a command that opens a browser of its own.
  2. The machine is the spec. Change the lifecycle in src/platformKit/lifecycle/machine.ts and its tests, then regenerate the doc: log facebook lifecycle states --write. Never hand-edit the generated tree.
  3. Final is final. Restricted, banned, lost and deactivated: the record stays in Twenty; nothing resumes them. A /checkpoint page is never pressed through: the checkpoint watch sets the account DEACTIVATED and the machine closes the browser for checkpoint and ends in deactivated. Only a video selfie or ID waits in needsPerson.
  4. Live only with the owner's go. Warm-up likes, publish and replies need liveActions (rule 8).

The routine

log facebook lifecycle                       # where every account is, and what it has left
log facebook lifecycle --account <name>      # one, with its standing
log facebook lifecycle states                # the state tree from the machine itself

A field the lifecycle reads is added through scripts/twenty/twentySetup.mjs and the client regenerated. A fact it reads from a past run (a rename, a location) is backfilled only from that run's recording (rule 25), never guessed.

Full description: docs/lifecycle.md. Requirements: docs/specs/accountLifecycle.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.