What makes Broedkrumme Kalibr notable?

984 downloads. Trust evidence available

How should Broedkrumme Kalibr be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Broedkrumme Kalibr

Captures agent outcomes and LLM telemetry for continuous self-improvement and optional intelligent model routing. Skill: Broedkrumme Kalibr Owner: broedkrummen Summary: Captures agent outcomes and LLM telemetry for continuous self-improvement and optional intelligent model routing. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-24T10:15:37.473Z | auto - Initial release of Kalibr skill. - Captures agent outcomes for tracking and analysis. - Collects LLM telemetry data. - Supports optional intelligent model routing. - Enable

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

984

Updated

Oct 11, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 984 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 984 downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.0release · observed Feb 24, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.0release
- Initial release of Kalibr skill. - Captures agent outcomes for tracking and analysis. - Collects LLM telemetry data. - Supports optional intelligent model routing. - Enables self-improvement tracking for agents.
Observed Feb 24, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s176tqmpjtkpkhfdzyb4m64qts83hexw:broedkrumme-kalibr

Node.js workspace detected. Install dependencies securely: run `npm ci --ignore-scripts` to prevent post-install lifecycle triggers from running arbitrary code, then selectively audit the dependency tree.
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-broedkrummen-broedkrumme-kalibr/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

4,899 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

# Kalibr

Agent self-improvement and telemetry. Captures agent outcomes and LLM calls for continuous improvement.

## Features

- Outcome capture
- LLM telemetry
- Intelligent model routing (optional)
- Self-improvement tracking

## Config

```json
{
  "apiKey": "your-kalibr-api-key",
  "tenantId": "your-tenant-id",
  "apiUrl": "https://kalibr-intelligence.fly.dev",
  "enableRouting": false,
  "captureOutcomes": true,
  "captureLlmTelemetry": true
}
```

_meta.json

{
  "ownerId": "kn7b72aym67gcmwkp05van1d8s800a7m",
  "slug": "broedkrumme-kalibr",
  "version": "1.0.0",
  "publishedAt": 1771928137473
}

skill-card.md

## Description:

Captures agent outcomes and LLM telemetry for continuous self-improvement and optional intelligent model routing.

This skill is ready for commercial/non-commercial use.

## Publisher:

[broedkrummen](https://clawhub.ai/user/broedkrummen)

### License/Terms of Use:

ISC

## Use Case:

Developers and agent operators use this plugin to record agent run outcomes and LLM usage data for Kalibr-backed analysis. They can optionally allow Kalibr to influence model routing for agent runs.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Telemetry and outcome capture can send session identifiers, tool history, token counts, and failure metadata to the configured Kalibr service.

Mitigation: Use only a trusted Kalibr endpoint and disable captureOutcomes or captureLlmTelemetry unless organizational policy permits sending that data.

Risk: When routing is enabled, the external service can influence model selection and tool-call parameters.

Mitigation: Keep enableRouting disabled unless that behavior is explicitly desired and review any routed model or parameter changes in sensitive workflows.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/broedkrummen/skills/broedkrumme-kalibr)

## Skill Output:

**Output Type(s):** [text, configuration, API calls]

**Output Format:** [Plain text status output, structured status responses, and SDK-mediated telemetry or outcome reports.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May override model and provider selection, and may merge service-provided tool parameters, when routing is enabled.]

## Skill Version(s):

1.0.0 (source: server release metadata and package.json)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

openclaw.plugin.json

{
  "id": "kalibr",
  "configSchema": {
    "type": "object",
    "additionalProperties": false,
    "properties": {
      "apiKey": { "type": "string" },
      "tenantId": { "type": "string" },
      "apiUrl": { "type": "string", "default": "https://kalibr-intelligence.fly.dev" },
      "defaultGoal": { "type": "string", "default": "openclaw_agent_run" },
      "enabled": { "type": "boolean", "default": true },
      "enableRouting": { "type": "boolean", "default": false },
      "captureOutcomes": { "type": "boolean", "default": true },
      "captureLlmTelemetry": { "type": "boolean", "default": true }
    },
    "required": ["apiKey"]
  },
  "uiHints": {
    "apiKey": { "label": "Kalibr API Key", "sensitive": true },
    "tenantId": { "label": "Tenant ID" },
    "apiUrl": { "label": "Intelligence Service URL", "placeholder": "https://kalibr-intelligence.fly.dev" },
    "defaultGoal": { "label": "Default Goal", "placeholder": "openclaw_agent_run" },
    "captureLlmTelemetry": { "label": "Capture LLM Call Telemetry" },
    "captureOutcomes": { "label": "Report Run Outcomes" },
    "enableRouting": { "label": "Enable Intelligent Model Routing", "description": "Use Kalibr decide() to override model selection before each agent run" }
  }
}

package.json

{
  "name": "kalibr",
  "version": "1.0.0",
  "description": "",
  "main": "index.js",
  "scripts": {
    "test": "echo \"Error: no test specified\" && exit 1"
  },
  "keywords": [],
  "author": "",
  "license": "ISC"
}

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular