Knowledge

Memory Bank Continuity

Give stateless agents a project spine.

Use when

Agent work spans multiple sessions, contributors, or tools and context keeps getting rebuilt from scratch.

Cadence

At the start and end of multi-session agent work

Verification

Project brief, active context, decisions, tech constraints, and progress are current enough for a fresh agent to continue safely.

Advanced spec

Structured loop spec

FieldValue
NameMemory Bank Continuity
CategoryKnowledge
TriggerAt the start and end of multi-session agent work
ObjectiveGive stateless agents a project spine.
Allowed inputsRelevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop
Allowed actionsAt session start, read the project brief, active context, tech constraints, system patterns, and progress files.; During work, record durable decisions, current blockers, changed commands, and important path references.; At session end, update active context and progress with what changed, what passed, what failed, and what comes next.; Do not store secrets, raw transcripts, or giant code dumps in memory files.; Verify a fresh-agent handoff can state goal, current state, commands, blockers, and next action.
VerificationProject brief, active context, decisions, tech constraints, and progress are current enough for a fresh agent to continue safely.
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 public, destructive, financial, legal, account, or production-impacting actions.
Safe outputDraft, report, checklist, table, or approval-gated recommendation
Works withClaude, ChatGPT, Gemini, any tool-using AI assistant
Runbook

Steps

  1. At session start, read the project brief, active context, tech constraints, system patterns, and progress files.
  2. During work, record durable decisions, current blockers, changed commands, and important path references.
  3. At session end, update active context and progress with what changed, what passed, what failed, and what comes next.
  4. Do not store secrets, raw transcripts, or giant code dumps in memory files.
  5. Verify a fresh-agent handoff can state goal, current state, commands, blockers, and next action.
Copy prompt

Prompt

Run the Memory Bank Continuity loop. Read the repo's project brief, active context, tech constraints, system patterns, and progress files before work. During and after the session, update durable decisions, blockers, changed commands, important paths, verification evidence, and next action. Do not store secrets, raw transcripts, or giant code dumps. Verify the handoff lets a fresh agent continue without rereading the whole chat.
Metadata

Tags

memory bankproject contextdocsagent continuity
Next loops

Related