Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Agent Decision Receipts

Mint tamper-evident, post-quantum-signed receipts for consequential agent actions and verify them offline from the certificate alone.

Security & ReviewAdvanced★ 26,260⑂ 3,699AI score 7/10Last updated: Aug 30, 2026

What it does

When an autonomous agent performs a side-effecting action (deploy, delete, pay, grant access, or a model decision affecting a person), this skill guides you to mint a signed receipt instead of relying on an editable log.

  • Decision 1: does this action need a receipt? (side-effecting + consequential + later-provable)
  • Decision 2: build the action manifest (agent_id, operation, target, policy) and sign it
  • Decision 3: verify by recomputing sha256(canonical(evidence)) and checking each signature leg — no DB, no network

Crypto is delegated to the open-source openagentontology package (Ed25519 plus post-quantum ML-DSA-65 / SLH-DSA legs). The skill is explicit about scope: not log analysis, not a hosted notary, not a legal opinion.

Who it's for

  • Platform/SRE engineers running agents with production write access
  • AI compliance owners needing per-decision evidence (EU AI Act Article 12, ISO 42001)
  • Teams that must retain defensible evidence for audits, insurers, or disputes

Examples

  1. A deploy agent ships to prod/api: mint a receipt naming the governing policy and store it beside the release artifact.
  2. A high-risk AI system auto-denies a claim: mint a receipt carrying only inputs_hash, satisfying Article 12 record-keeping without storing PII.
  3. Six months later an auditor receives just the receipt file and runs verify_receipt to confirm integrity and authenticity fully offline.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alirezarezvani/claude-skills/HEAD/.gemini/skills/agent-decision-receipts/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .gemini/skills/agent-decision-receipts folder from the GitHub repo alirezarezvani/claude-skills into my ~/.claude/skills/agent-decision-receipts/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alirezarezvani/claude-skills.git && mkdir -p ~/.claude/skills && cp -r claude-skills/.gemini/skills/agent-decision-receipts ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/alirezarezvani/claude-skills.git
  2. Copy the skill into your Claude skills folder: mkdir -p ~/.claude/skills && cp -r claude-skills/.gemini/skills/agent-decision-receipts ~/.claude/skills/
  3. Install the signing library if you want minting/verification: pip install "openagentontology[pq]" (manifest building works without it).
  4. Restart Claude Code and try a prompt like "Mint a decision receipt for this production deploy" to confirm the skill loads.
  5. Keep your signing key in a secret manager, separate from the receipts, and never commit it to version control.
View source on GitHub ↗License: MIT