agent-receipt SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 9 indexed copies. Same content hash, so the same checks give both the same grade.

agent-receipt from getedgehq/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

mdr add getedgehq/skills/agent-receipt@git:20260920.deb764a

Pins git:20260920.deb764a in mdr.lock. Pin the fingerprint instead.

Audit grade

A, 17 of 17 checks passed

Kind

SKILL.md skill

Repository

getedgehq/skills

Path

evals/agent-receipt/2026-09-19/invalid-undisclosed-schema/s1/with.meta/skill/agent-receipt/SKILL.md

Versions recorded

1

Latest version

git:20260920.deb764a, committed Sep 20, 2026

Size

1,151 bytes

Repository stars

5

License

Apache-2.0

Create a compact, evidence-backed proof-of-work receipt for a completed AI agent run. Use when the user wants to summarize what an agent actually built, how long it took, what changed, tests run, interventions, deployment status, or skills used.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent Receipt

1. Gather only evidence available in the current run/repo.
2. Never infer a passed test, deployment, duration, or intervention count. Use `unknown` instead.
3. Write a local JSON manifest with: project, agent, duration_minutes, interventions, files_changed, tests_passed, tests_total, verification, deployed, skills_used, and evidence.
4. Run `scripts/receipt.py <manifest> --out <public-result.json>`. The public result contains evidence hashes and counts, never raw evidence values.
5. Run `scripts/render.py <public-result.json> --svg <card.svg> [--png <card.png>]`.
6. Keep the source manifest and raw evidence local unless the user explicitly approves publishing selected evidence.
7. Publishing is a separate external action. Confirm destination and visibility immediately before uploading unless the current request already authorizes it.

Read the whole file at its exact version.

How to install

mdr add getedgehq/skills/agent-receipt@sha256:e3fc9dbd509c6e00

[![mdr](https://markdownregistry.com/badge/art_hpr5m4fs35srkeoa.svg)](https://markdownregistry.com/a/art_hpr5m4fs35srkeoa)

Versions

The registry has recorded 1 version of this file, committed on Sep 20, 2026.

Audit of the latest version

Source

API

GET https://markdownregistry.com/api/v1/artifacts/art_hpr5m4fs35srkeoa
GET https://markdownregistry.com/api/v1/resolve?ref=getedgehq/skills/agent-receipt
GET https://markdownregistry.com/api/v1/blob/e3fc9dbd509c6e00e4f829d1ce041d9c71d591c5eff790eeb6dc4cad1d104c2b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from getedgehq/skills

Every file in getedgehq/skills

Other files named agent-receipt

Browse by kind, by grade A, or by owner.