Chapter 9: OpenClaw model migration

Updated: 2026-06-08 · Migration plan for carrying the useful OpenClaw operating model into the new Paperclip agent company.

What was reviewed

The review covered the current OpenClaw runtime instructions, heartbeat/autonomy policy, local queue and human ToDo files, daily and long-term memory notes, work-session ledger, dream question ledger, custom workflow skills, cron/job state, task-run ledger, and the existing Paperclip COO/PM/Development/Testing agent contracts.

Sensitive config was treated only as policy shape. Credentials, auth profiles, tokens, and provider keys should not be copied into Paperclip prompts, skills, tasks, or public docs.

Main finding

Contracts to migrate

Role split

OpenClaw's strongest pattern is the split between orchestration, PM, Development, and independent Testing. Paperclip should keep that small-company shape:

• COO: owns intake, routing, liveness checks, recovery, and concise operator summaries.
• PM: owns portfolio audit, issue readiness, queue hygiene, requirement/task linkage, and human-decision triage.
• Development: owns scoped implementation, branches, PRs, checks, and evidence.
• Testing: owns independent acceptance, no-edit compliance, browser/check evidence, and requested-change findings.

Work-session supervision

OpenClaw learned not to call work active without evidence. Paperclip should encode this as a task contract: every PM, Development, or Testing task needs expected first checkpoint, evidence type, timeout, and recovery owner.

Launch fields

Before Development or Testing starts, PM or COO must define the target issue/PR, role, repository, branch/worktree strategy, allowed files, acceptance criteria, checks, evidence, checkpoint, non-goals, and recovery plan. Development should refuse tasks that omit fields that could change behavior or scope.

Portfolio PM audit

The PM routine should continue to audit the full obot-claw portfolio before selecting Development work. It should inspect Projects, Requirements, Tasks, PRs, Hub status, human ToDos, dirty worktree risk, parent/sub-issue links, and stale blockers. The local AUTONOMOUS_QUEUE.md file should become transitional backup once Paperclip/GitHub task sync is active.

Human ToDo gate

Before creating any Jeremy ToDo, PM must ask whether PM, Development, Testing, or a new specialist agent can do the work instead. If Jeremy truly owns the decision, the linked issue or PR must contain an explicit @jwildfire question or instruction with the decision criteria and evidence.

GitHub PR flow

Development should inherit the OpenClaw PR discipline: write only inside approved obot-claw repositories, capture repo freshness before editing, use branches and PRs for repo changes, assign Obot where appropriate, request Jeremy review when ready, and monitor checks through durable task/routine state instead of long silent polling.

Telegram/OpenClaw bridge

OpenClaw should remain the human front door, but it should address the COO rather than direct agent execution. Telegram output must stay short, plain text, and artifact-backed. The bridge should expose allowlisted actions such as health, latest status, review next queue item, start approved task, check failures, summarize latest artifact, and pause/stop where supported.

Memory migration

Schedule migration

Do not copy every OpenClaw cron job into Paperclip immediately. The old isolated cron path repeatedly produced startup stalls and main-session reminder fallbacks. Paperclip routines should be promoted in stages.

1. Daily read-only PM portfolio review. First scheduled Paperclip routine. No repo edits, no Development launch.
2. PR review watch. Add once Paperclip can leave anti-spam state and durable findings.
3. COO status summary. Summarize only after durable Paperclip/GitHub artifacts exist.
4. Development task creation. Enable only after same-day PM readiness evidence is reliable.
5. Testing verification. Add independent acceptance tasks before any work is presented as ready.
6. Nightly briefing and framework review. Migrate only after Paperclip scheduling proves multi-day reliability.
7. Private dream synthesis. Migrate last, only after private-memory boundaries are explicit.

Do not migrate

• Do not reproduce OpenClaw isolated agentTurn cron as the production executor.
• Do not copy raw credentials, auth profiles, tokens, or provider keys into Paperclip.
• Do not enable broad OpenClaw skill/plugin access inside Paperclip agents.
• Do not allow Telegram free text to become a command or unrestricted Paperclip task.
• Do not allow autonomous merges.
• Do not expose private memory wholesale to all agents.
• Do not retire OpenClaw schedules until Paperclip equivalents have passed on the same cadence with rollback available.

Agent-specific updates

Proposed Paperclip tasks

1. Migrate OpenClaw supervision and launch-field contracts. Owner: COO. Output: updated agent instructions and task templates.
2. Port portfolio PM audit into Paperclip PM. Owner: PM. Output: PM skill/template with portfolio audit checklist and helper references.
3. Port GitHub PR flow into Development and Testing. Owner: Development, verified by Testing. Output: PR-flow contract plus testing acceptance checklist.
4. Define Paperclip memory boundaries. Owner: PM. Output: policy for GitHub public memory, Paperclip operational memory, and private OpenClaw memory.
5. Design Paperclip routine migration. Owner: COO. Output: routine migration map and first read-only PM schedule.
6. Design Telegram/OpenClaw COO bridge. Owner: COO. Output: allowlisted actions and plain-text formatting contract.

Acceptance gates

Recommended next step

Then run a no-edit PM task against the rollout queue. The PM should review the Chapter 8/9 rollout tasks and produce a readiness note without changing repositories.