# Evidence Ledger

> Use after implementation, debugging, review, or release work to record claims and proof. Do not use when no claim or verification artifact is needed.

- Skill: `mattbaconz/evidence-ledger` (Agent Skill)
- Install (CLI): `npx skillmds@latest add mattbaconz/evidence-ledger`
- Raw SKILL.md: https://api.skillmd.com/api/skills/mattbaconz/evidence-ledger/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: mattbaconz (https://skillmd.com/u/mattbaconz)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/mattbaconz/evidence-ledger

---


# evidence-ledger

## Purpose

Record claims, commands, verification results, artifacts, and remaining risk for a task.

## Trigger

Use after a task has verification evidence that should be preserved for review or handoff.

## Workflow

1. Identify the task claim.
2. Record commands and results.
3. Record remaining risks.

## Output

Writes `.agent/evidence/<task-id>.md` when filesystem access is available.