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.

difficultyIntermediate
categoryOperations
sourceOriginal

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

FieldValue
NameAgent Handoff Continuity
CategoryOperations
TriggerBefore pausing or switching agents
ObjectivePrevent the next agent from starting with amnesia and bravado.
Allowed inputsRelevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop
Allowed actionsDefine 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.
VerificationA new agent can state goal, current state, proof, blockers, and next action without reading the whole transcript.
Stop conditionStop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required.
BudgetSet a time, turn, token, retry, file, or dollar cap before running the loop.
Approval boundaryHuman approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments.
Safe outputDraft, report, checklist, table, or approval-gated recommendation
Works withClaude, ChatGPT, Gemini, any tool-using AI assistant

Steps

  1. Define the exact scope, source of truth, and approval boundary.
  2. Inspect current state and rank the highest-risk gap.
  3. Make one small, reversible improvement.
  4. Run the stated verification and record evidence.
  5. 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.

Get the MCP server + agent pack

Tags

handoffstateagents

Related loops

Browse all 68 loops