agent-execution-receipts

This skill inspects signed execution receipts and correlates them with provider audit logs to determine whether an agent action has local evidence, a…

by WriterOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (writer)

Agents: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
License: Apache-2.0 (permissive)
Pin: 9dd6c92pinned Oct 9, 2026
Context cost: about 290 tokenswhen the skill loads
GitHub stars: 15on writer/cerebro
Scripts: None found

What it does

“Inspect signed Codex execution receipts, import provider audit events, and explain whether an action has local evidence, a candidate correlation, or a provider binding.”

The author's description, from SKILL.md

Generated summary from the skill's own text

This skill inspects signed execution receipts and correlates them with provider audit logs to determine whether an agent action has local evidence, a candidate provider correlation, or a cryptographically verified provider binding. It verifies receipt signatures, imports CloudTrail events, and identifies unattributed provider mutations.

When to use it

Verify which agent actions reached a cloud provider with authentication
Audit agent-originated changes and their provider attribution status
Correlate local execution records with CloudTrail or provider audit logs
Identify provider mutations that lack agent action attribution

When not to

Process name or user agent strings are sufficient for attribution
Trusting user-imported JSON as provider-bound evidence
Environments without signed execution receipt infrastructure

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add writer/cerebro --skill agent-execution-receipts

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install writer/cerebro agent-execution-receipts@9dd6c92664bc6d15430a821b97995b4a53294a6d

Installs the commit we checked (9dd6c92).

Copy by hand

Download the folder at 9dd6c92 and put it in .claude/skills/agent-execution-receipts for Claude Code and in .agents/skills/agent-execution-receipts for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 9dd6c92

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "agent-execution-receipts" by Writer.

Source, pinned to commit 9dd6c92664bc6d15430a821b97995b4a53294a6d:
https://github.com/writer/cerebro/tree/9dd6c92664bc6d15430a821b97995b4a53294a6d/plugins/cerebro-agent-receipts/skills/agent-execution-receipts

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/agent-execution-receipts/ for Claude Code and .agents/skills/agent-execution-receipts/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/writer/agent-execution-receipts

SKILL.md at the pin

---
name: agent-execution-receipts
description: Inspect signed Codex execution receipts, import provider audit events, and explain whether an action has local evidence, a candidate correlation, or a provider binding.
---

# Agent Execution Receipts

Use this skill when the user asks who or what ran a command, whether an agent action reached a provider, or which agent-originated changes lack provider attribution.

## Procedure

1. Open the Cerebro Agent Receipts app or read `receipts.ndjson` from the configured receipt directory.
2. Verify each receipt signature and the append-only digest chain before using it as evidence.
3. Import a CloudTrail `LookupEvents` response when provider observations are available.
4. Report one of three states without collapsing them:
   - `Local evidence only`: a signed local receipt exists.
   - `Candidate correlation`: one provider event has a one-to-one evidence match, but no trusted binding.
   - `Provider bound`: an authenticated provider event passes the configured account, dedicated role, action ID, action, and time checks.
5. Start from the provider-event population and identify every provider mutation without a completed one-to-one action match.

Never treat a process name, user agent, `startedBy` value, local transcript, session-wide identifier, or user-imported JSON as provider-bound attribution.

From writer/cerebro at 9dd6c92, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at 9dd6c92

Files

SKILL.md1.4 KB · 9d39a31395a6

1 file, 1.4 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 9dd6c92

All 13 skills from Writer

Open roles at Writer

5 of 15 open roles on the jobs board

Security engineer, detection and response (UK)
London, UK (Remote)
Security engineer, application security (UK)
London, United Kingdom (Hybrid)
Infrastructure engineer
New York City, NY, USA | Seattle, WA, USA | San Francisco, CA, USA | London, UK (Hybrid)
Staff security engineer, application security
New York City, NY, United States | Seattle, WA, United States | San Francisco, CA, United States (Hybrid)
AI engineer (UK)
London, UK (Hybrid)

See all 15 roles at Writer on the jobs board

agent-execution-receipts

What it does

When to use it

When not to

Install

Copy for your agent

SKILL.md at the pin

Files

More from Writer

practice-registry

account-targeting-and-research

b2b-content-and-campaigns

business-case-and-proposal

competitive-and-objections

customer-facing-quality-gate

claude-security

sensitive-logging-audit

security-audit

assess-patch-risk

attack-path-analysis

deep-security-scan

Open roles at Writer

What it does

When to use it

When not to

Install

Copy for your agent

SKILL.md at the pin

Files

More from Writer

Related in Security

Open roles at Writer