Validate a PromptSpeak frame. Returns validation report with errors, warnings, and suggestions.

Validate multiple frames at once. Useful for validating delegation chains.

Execute an action under PromptSpeak frame governance. The gatekeeper validates and enforces constraints.

Check if an action would succeed without executing. Returns decision and coverage analysis.

Execute multiple actions under a single frame. Supports sequential or parallel execution with optional stop-on-failure.

Delegate a task from parent agent to child agent. Enforces inheritance rules and constraint propagation.

Revoke an active delegation.

List delegations for an agent.

Get current state of an agent including drift metrics and circuit breaker status.

Get overall system state including all agents, operations, and drift alerts.

Reset agent state. Can reset circuit breaker, drift metrics, and/or baseline.

Recalibrate agent drift baseline. Optionally provide a new baseline configuration.

Immediately halt an agent by opening its circuit breaker.

Resume a halted agent.

Get drift history for an agent.

Register a new policy overlay.

Activate a registered policy overlay.

Get current configuration including active overlay and thresholds.

Export current configuration for backup.

Import configuration from backup.

Set a confidence threshold. This is the hidden knob for operators.

Get all confidence thresholds.

Set multiple confidence thresholds at once.

Set a feature flag.

Get all feature flags.

Get audit log entries.

List all pending holds awaiting human approval. Returns holds for risky operations that were blocked pending review.

Approve a held execution request. The operation will proceed with optional modifications.

Reject a held execution request. The operation will not proceed.

Configure hold behavior and thresholds. Controls when operations are held for human review.

Get hold statistics and history.

Scan code content for security vulnerabilities. Returns findings classified by severity (critical, high, medium, low, info).

Scan code and enforce security policy. Blocks on critical findings, holds high-severity for review, warns on medium, logs low/info.

Configure security detection patterns. List, enable, disable, or change severity of patterns.

Create a new directive symbol in the registry.

Symbol IDs follow the pattern:

• Public companies: Ξ.{TICKER}.{PERIOD} (e.g., Ξ.NVDA.Q3FY25)

• People: Ξ.I.{NAME}.{CONTEXT} (e.g., Ξ.I.JENSEN_HUANG.BIO)

• Events: Ξ.E.{TYPE}.{ID} (e.g., Ξ.E.EARNINGS.NVDA.20241120)

• Sectors: Ξ.S.{SECTOR}.{CONTEXT} (e.g., Ξ.S.SEMICONDUCTORS.2024)

• Tasks: Ξ.T.{PROJECT}.{ID} (e.g., Ξ.T.PORTFOLIO_REVIEW.001)

• Knowledge: Ξ.K.{DOMAIN}.{TOPIC} (e.g., Ξ.K.CHEMISTRY.WATER)

• Queries: Ξ.Q.{DATASET}.{ID} (e.g., Ξ.Q.DEEPSEARCHQA.001)

Retrieve a directive symbol by ID. Returns the full symbol with all grounding context.

Update an existing symbol. Creates a new version with updated hash.

List symbols with optional filtering.

Delete a symbol from the registry.

Bulk import symbols from external data (HuggingFace, JSON, etc.).

Get statistics about the symbol registry.

Format a symbol for inclusion in a prompt. Returns LLM-ready text.

Record human verification of a symbol claim.

Use this tool to upgrade or dispute claims based on human review:

• VERIFIED: Human expert has confirmed the claim is accurate

• CORROBORATED: Additional evidence supports the claim

• DISPUTED: Human reviewer found the claim to be incorrect or misleading

Important: Accusatory claims (fraud, violations) should be DISPUTED if they lack evidence or have plausible alternative explanations.

List symbols that require human review.

Returns symbols flagged for review due to:

• Accusatory claims without sufficient evidence

• Missing alternative explanations

• High-stakes claims (fraud, violations, diagnoses)

• Low confidence scores

Use this to find claims that need human validation before action.

Add an alternative explanation to a symbol's findings.

CRITICAL for preventing false positives: When a pattern-based finding could have multiple explanations, document them here. Adding high-likelihood alternatives automatically reduces confidence in the original claim.

Examples:

• "9 identical payments" → Alternative: "Monthly insurance premium financing"

• "Large round numbers" → Alternative: "Negotiated contract amounts"

• "Vendor with single customer" → Alternative: "Subsidiary company"