The bound list

Does AgentGuard bound your agent?

A brake on your agents that only you control: verifiable, no third party, no data leaves your machine for AgentGuard. Each post uses a fresh install and real output. A green verdict means the integration can stop the call before dispatch. Partial and no verdicts state exactly where the host leaves a bypass.

Posts

provenance receipts

Kimi model provenance: weights origin and hosting jurisdictionregistry example

Reproduce how the local registry classifies one model ID across four routes, and see exactly what a signed provenance record does and does not prove.

guarded provider client

Does AgentGuard bound OpenRouter?yes

The client wrapper stopped spend-cap and capability violations before network dispatch. The allowed call produced a signed receipt, and the four-entry chain verified offline.

guarded client before proxy

Does AgentGuard bound LiteLLM?yes

A real local LiteLLM proxy saw one allowed call and neither refusal. Direct access to the proxy remains a bypass, so ingress must be restricted to guarded callers.

mandatory local hook

Does AgentGuard bound Claude Code?partial

The pre-tool hook really blocks estimated spend and named destructive actions. Claude Code does not expose exact per-tool token cost here, and the integration does not enforce a generic capability tier.

MCP decision tool

Does AgentGuard bound Cursor?no

The MCP server returns real signed spend decisions, but Cursor is not forced to consult it and the current tool has no capability input. This post shows the failed probe.

MCP extension

Does AgentGuard bound Goose?advisory

The MCP tool can return signed policy decisions to Goose, but MCP alone is not an unavoidable call-path interposer. Treat the older setup as agent-consulted decision support.

buzz-acp harness

Does AgentGuard bound Buzz agents?advisory

The harness exposes AgentGuard decisions through MCP. It is useful signed policy evidence, but the current MCP server is not by itself a mandatory interposer.

The format

Every post answers the same question the same way, so a new one is a short job, not a project:

1. Identify the exact interception point. 2. Install the published package in a fresh scratch directory. 3. Capture an allowed signed decision, a spend refusal, and a capability refusal. 4. Verify offline and reject a tamper. If the host cannot produce one of those outcomes, the badge and post say so.