# Verify signed agent-run evidence offline with Tracekit

> Check an authorized Tracekit bundle against pinned signer keys and report integrity verdicts separately from execution and completeness claims.

- Skill: `agentskillexchange/verify-signed-agent-run-evidence-offline-with-tracekit` (Agent Skill)
- Install (CLI): `npx get-skill add agentskillexchange/verify-signed-agent-run-evidence-offline-with-tracekit`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/verify-signed-agent-run-evidence-offline-with-tracekit/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-11-15
- Page: https://skillmd.com/skills/agentskillexchange/verify-signed-agent-run-evidence-offline-with-tracekit

---


# Verify signed agent-run evidence offline with Tracekit

Check an authorized Tracekit bundle against pinned signer keys and report integrity verdicts separately from execution and completeness claims.

## Prerequisites

Python, tracekit-ai verifier, authorized .tkb evidence bundle and independently trusted signer public key

## Installation

Install or set up from the source-backed instructions:

Install the upstream verifier with pip install --no-deps tracekit-ai for the documented v1 sample bundles; install appropriate dependencies for other supported formats and integrations. Obtain fixture bundles and signer.pub from a trusted upstream checkout. No agent hooks or signer service are required for this offline verification workflow.

- Source: https://github.com/Cygnux-Labs/Tracekit

## Documentation

- https://github.com/Cygnux-Labs/Tracekit#readme

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/verify-signed-agent-run-evidence-offline-with-tracekit/)

