Shift

SHIFT — Multi-Identity Delegation Skill

One agent. Many specialists. One conversation.

⚠️ SECURITY AND PRIVACY — READ BEFORE ENABLING

What SHIFT Accesses

SHIFT reads from your OpenClaw workspace:

• ~/.openclaw/workspace/MEMORY.md — excerpts attached to delegation context
• ~/.openclaw/workspace/.shift/config.yaml — your persona and cost settings
• Session files it creates in ~/.openclaw/workspace/.shift/sessions/

SHIFT writes to:

• ~/.openclaw/workspace/.shift/sessions/<runId>/ — per-delegation session files
• ~/.openclaw/workspace/.shift/cost-tracking.json — delegation cost tracking
• ~/.openclaw/workspace/.shift/personas/*.yaml — your persona overrides

What SHIFT Transmits

When you enable delegation, the following are sent to whatever model providers you configure for each persona:

• Your message content
• Conversation history (last N turns, controlled by contextBridge.historyTurns)
• Active file contents and MEMORY.md excerpts relevant to the task
• Delegation metadata (runId, timestamps, persona name)

You control which models are used. SHIFT does not ship with or store credentials — it uses the model providers configured in your OpenClaw agent config. Review your provider's data handling policy.

Data Exposure Risk

If your workspace files or MEMORY.md contain secrets (API keys, credentials, private data), and those files are referenced in a delegated task, that content will be transmitted to your configured model provider.

Mitigations:

• Do not delegate tasks that reference sensitive file paths
• Set contextBridge.historyTurns to a low number (e.g., 3)
• Use costManagement.trackOnly: true during evaluation to observe behavior without enforcement
• Use trusted or self-hosted model providers for sensitive work

Setup Script

scripts/setup.sh creates local directories only. It does NOT:

• Make network calls
• Escalate privileges
• Modify system files
• Access credentials

Cost and Consultations

Consultations spawn additional model calls. Costs are tracked in cost-tracking.json per delegation. Set costManagement.trackOnly: true to monitor before enforcing limits.

Recommendations

1. Start with costManagement.trackOnly: true to observe costs
2. Set contextBridge.historyTurns to a small number (5 or less)
3. Set contextBridge.archiveAfterMinutes: 30 for faster cleanup
4. Do not delegate tasks referencing sensitive file paths
5. Review model providers' data policies before sensitive work

Triggers on: any message that might benefit from specialized handling — coding tasks, research, analysis, quick lookups, or anything that warrants delegating to a sub-identity.

When SHIFT triggers, you read and follows the procedures below to: classify the task, delegate to the right sub-identity, handle consultation between sub-identities, and synthesize the final response in his own voice.

SHIFT Procedures

Follow these steps for every message that triggers SHIFT.

STEP 1 — Fast Path Check

Before anything, check if this message is trivially handled by you directly.

Bypass delegation (return none) if message is ONLY:

• Greetings: hi, hey, hello, yo, sup
• Acknowledgments: thanks, thank you, ty, ok, sure, got it, makes sense, cool, nice
• Meta: that was fast, nice one, lol, haha

If none of those match, proceed to STEP 2.

STEP 2 — Load Config

Read the SHIFT config at:

~/.openclaw/workspace/.shift/config.yaml

If the file doesn't exist, run the setup script first:

bash ~/.openclaw/workspace/skills/shift/scripts/setup.sh

From config, extract:

• displayMode — hidden or transparent
• fastPath — conservative or off
• costManagement.enabled, costManagement.costBudgetPerHour, costManagement.alertThreshold
• contextBridge.historyTurns, contextBridge.sessionFolder
• personas — enabled personas and their settings

STEP 3 — Cost Budget Check

If costManagement.enabled: true:

Read ~/.openclaw/workspace/.shift/cost-tracking.json:

{
  "hourStart": "2026-03-18T15:00:00Z",
  "totalSpend": 0.87,
  "delegations": [...]
}

If current UTC hour > hourStart (new hour): → Reset totalSpend: 0, update hourStart to current hour.

If totalSpend >= costBudgetPerHour: → You handle the task directly. Say: "Handling this one myself to stay within your cost budget." Return budget_exceeded.

If totalSpend >= alertThreshold * costBudgetPerHour: → Send a quiet warning: "Approaching delegation budget limit for this hour."

STEP 4 — Route to Persona

Using the enabled personas from config, classify the user's message.

Keyword Scoring

For each enabled persona, count keyword matches in the user's message (case-insensitive, whole-word). Raw score = matches / total keywords.

If raw score >= minConfidence: Add to candidates.

Runner special case: Runner has requireExplicit: true. It only triggers if the message is predominantly a Runner task, not just containing a keyword. If the message has strong code/research keywords, Runner is NOT a match even if it has Runner keywords.

Tie-Breaking

If multiple personas score above threshold: → Higher score wins. If tied: codex > researcher > runner.

Default

If no persona scores above threshold → You handle directly. Return none.

STEP 5 — Prepare Delegation Context

Generate a unique runId:

run-{YYYYMMDD}-{HHMM}-{persona}-{sequence}
Example: run-20260318-1551-codex-001

Create the session folder:

~/.openclaw/workspace/.shift/sessions/{runId}/

Write INBOUND.json

{
  "runId": "<runId>",
  "timestamp": "<ISO UTC>",
  "persona": "<matched persona>",
  "userMessage": "<exact user message>",
  "masterConversationHistory": <last N turns from conversation>,
  "activeFiles": <files mentioned>,
  "masterSummary": "<brief summary of conversation so far>"
}

Write CONTEXT.md

Pull from:

• ~/.openclaw/workspace/MEMORY.md (keyword-matched relevant sections)
• Any active file contents mentioned in the conversation
• Persona-specific context needs (from the persona definition in config)

Format:

# Context for {persona}

## Project/Memory (relevant)
...

## Active Files
...

## Persona Context Needs
...

STEP 6 — Build Task Prompt

Construct the prompt for the sub-agent:

# You are {persona_name}

## Persona
{persona voice, tone, strengths, blind spots from config}

## Your Task
{user's exact message}

## Context
Before starting, read:
- /path/to/INBOUND.json — your input and conversation history
- /path/to/CONTEXT.md — relevant project context

## Your Protocol
1. Read INBOUND.json and CONTEXT.md
2. Execute your task
3. If you need to consult another sub-identity and your persona allows it:
   - Write your question to the session folder as CONSULT-INBOUND.md
   - Set a timeout: min(remaining_time * 0.5, your consultationTimeout)
   - Spawn the target sub-identity using sessions_spawn
   - Wait for them to write CONSULT-OUTBOUND.md
   - Read their response and continue with that context
4. Write your final result to /path/to/OUTBOUND.md
5. Include a ConsultationLog if you consulted anyone
6. End your response with [DONE]

STEP 7 — Spawn Sub-Agent

sessions_spawn({
  model: personaConfig.model,
  task: taskPrompt,
  label: `shift-${persona}-${runId}`,
  timeoutSeconds: personaConfig.timeout,
  attachments: [
    { name: "INBOUND.json", content: <inboundJsonString> },
    { name: "CONTEXT.md", content: <contextMdString> }
  ]
})

Track elapsed time. If elapsed > timeout * 0.7: → Send status to user: "{persona} is still working on this..."