Tools Reference
The plugin registers two tools in OpenClaw: axiom_consensus for full multi-model consensus and axiom_verify for fact verification.
axiom_consensus
Run multi-model AI consensus via the Axiom Protocol. Sends a query to multiple LLMs and iteratively converges their responses using φ-convergence.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| query | string | Yes | The question or statement to achieve consensus on. |
| models | string[] | No | Array of model identifiers (min 2). Defaults to config defaultModels. |
| structure | string | No | Consensus structure: fugue, sonata, or concert. Defaults to config structure. |
| max_iterations | number | No | Max convergence iterations (1–7). Defaults to config maxIterations. |
Examples
Simple query with defaults:
axiom_consensus query="What is the capital of France?"Custom models and structure:
axiom_consensus query="Should we use SQL or NoSQL for this project?"
structure="sonata"
models=["openai/gpt-5.4", "anthropic/claude-sonnet-4-6", "google/gemini-2.5-flash"]Quick consensus with fewer iterations:
axiom_consensus query="Is Python dynamically typed?"
max_iterations=3Response Format
The tool returns a formatted result containing:
- D-score — divergence between models (0 = perfect consensus)
- Confidence — (1 - D) × 100%
- Iterations used — how many rounds were needed
- Structure — which consensus pattern was used
- Model positions — each model's response and distance from consensus
- Convergence path — D-score at each iteration
The result also includes a details object with structured data:
{
"consensus_reached": true,
"d_score": 0.032,
"confidence": "96.8%",
"iterations": 4,
"structure": "fugue"
}axiom_verify
Verify a factual claim via multi-model consensus. The tool wraps the claim in a verification prompt and uses the sonata structure (thesis → antithesis → synthesis) with 5 fixed iterations.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| claim | string | Yes | The factual statement to verify. |
| models | string[] | No | Model identifiers (min 2). Defaults to config defaultModels. |
Examples
axiom_verify claim="Python was created by Guido van Rossum in 1991"axiom_verify claim="The speed of light is approximately 300,000 km/s"
models=["openai/gpt-5.4", "anthropic/claude-sonnet-4-6"]Response Format
The verification tool returns a verdict with:
- Verdict — TRUE, FALSE, or UNCERTAIN
- D-score — agreement level between models
- Confidence — (1 - D) × 100%
- Models queried — number of models used
- Iterations — always 5 for verification
How verification works internally
The plugin wraps your claim in a prompt: "Verify this claim. Respond with TRUE, FALSE, or UNCERTAIN, followed by a concise explanation with evidence." It then runs sonata consensus to get multi-model agreement on the verdict.
D-Score Quick Reference
| D-Score Range | Level | Confidence |
|---|---|---|
| 0.00 – 0.05 | Strong consensus | 95–100% |
| 0.05 – 0.20 | High confidence | 80–95% |
| 0.20 – 0.40 | Moderate | 60–80% |
| 0.40 – 0.60 | Low confidence | 40–60% |
| 0.60 – 1.00 | No consensus | 0–40% |