Countersign
by Kazemkhani
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_REGION | No | Bedrock region. | us-east-1 |
| COUNTERSIGN_DB | No | SQLite file for actions and ledger. | ./countersign.db |
| COUNTERSIGN_DATA | No | Household rules and catalogue. | ./data |
| COUNTERSIGN_JUDGE | No | Set to 'rules' to switch the model judge off (tests, offline); default 'bedrock'. | bedrock |
| COUNTERSIGN_HOST_KEY | No | Shared HMAC key between device and server. Use the same value in every terminal. | development key (warns) |
| COUNTERSIGN_SKILL_MODE | No | 'plugin' loads the Agent Skill through Strands AgentSkills; 'inline' pastes it into the prompt. | plugin |
| COUNTERSIGN_JUDGE_MODEL | No | Bedrock model or inference profile for the judge. | us.amazon.nova-premier-v1:0 |
| COUNTERSIGN_GUARDRAIL_ID | No | Optional Bedrock guardrail (prompt-attack filter) applied to listing text. | |
| COUNTERSIGN_ASSISTANT_MODEL | No | Bedrock model for the simulated assistant. | us.amazon.nova-pro-v1:0 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues