Operations
Agent Handoff Continuity
Prevent the next agent from starting with amnesia and bravado.
Use when
Long-running agent work crosses sessions, tools, repos, or humans.
Cadence
Before pausing or switching agents
Verification
A new agent can state goal, current state, proof, blockers, and next action without reading the whole transcript.
Structured loop spec
| Field | Value |
|---|---|
| Name | Agent Handoff Continuity |
| Category | Operations |
| Trigger | Before pausing or switching agents |
| Objective | Prevent the next agent from starting with amnesia and bravado. |
| Allowed inputs | Relevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop |
| Allowed actions | Define the exact scope, source of truth, and approval boundary.; Inspect current state and rank the highest-risk gap.; Make one small, reversible improvement.; Run the stated verification and record evidence.; Stop on success, budget, no progress, or approval required. |
| Verification | A new agent can state goal, current state, proof, blockers, and next action without reading the whole transcript. |
| Stop condition | Stop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required. |
| Budget | Set a time, turn, token, retry, file, or dollar cap before running the loop. |
| Approval boundary | Human approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments. |
| Safe output | Draft, report, checklist, table, or approval-gated recommendation |
| Works with | Claude, ChatGPT, Gemini, any tool-using AI assistant |
Steps
- Define the exact scope, source of truth, and approval boundary.
- Inspect current state and rank the highest-risk gap.
- Make one small, reversible improvement.
- Run the stated verification and record evidence.
- Stop on success, budget, no progress, or approval required.
Prompt
Run the Agent Handoff Continuity loop. Use it when Long-running agent work crosses sessions, tools, repos, or humans. Work in bounded iterations: inspect current state, choose the highest-risk gap, make one reversible improvement, verify it, and record evidence. Stop when A new agent can state goal, current state, proof, blockers, and next action without reading the whole transcript. or when blocked, budget exhausted, or approval is required.Run in Claude Code
Paste this into Claude Code (or any tool-using agent) to run the loop bounded: one change per round, the same verification every round, durable state files, and explicit stop conditions.
Run the "Agent Handoff Continuity" loop from AI Loop Library (https://ailooplibrary.com/loops/agent-handoff-continuity/) as a bounded loop.
Goal: Prevent the next agent from starting with amnesia and bravado.
Rules: one change per round; run the same verification every round (A new agent can state goal, current state, proof, blockers, and next action without reading the whole transcript.); append each round to docs/loops/agent-handoff-continuity/progress.md and update docs/loops/agent-handoff-continuity/state.json; stop on verifier pass, 8 rounds, 3 consecutive failed verifications, no progress, a blocker, or anything needing human approval (money, production, outbound, deletion). Finish with a proof report: rounds used, changes made, verification output, remaining risk, and the next human decision.