Commands for checking and repeating execution receipts. A receipt is a signed record of a command, its output, and its exit status.

Use them to create receipts for commands, verify their hashes and Ed25519 signatures, replay recorded runs, and compare their output and exit code.

They help confirm that a recorded execution has not been altered and check whether running it again produces the same result.

receipts — Command by thrashr888

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/thrashr888/agentkernel/receipts

Clone the repo

git clone --depth 1 https://github.com/thrashr888/agentkernel

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 359 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00359
Opus 5	$0.00000	$0.00179
Sonnet 5	$0.00000	$0.00072
Haiku 4.5	$0.00000	$0.00036

Measured 2d ago against content hash e395c459e59a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

receipts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/commands/receipts.md · 63 lines

What it actually says

agentkernel receipt

Verify and replay execution receipts generated by run and exec.

Generate a signed receipt

Use --receipt on run or exec:

agentkernel run --receipt ./run-receipt.json -- python3 -c "print('ok')"
agentkernel exec my-sandbox --receipt ./exec-receipt.json -- ls -la

Receipts are signed with a local Ed25519 key stored under ~/.agentkernel/receipts/.

Verify a receipt

agentkernel receipt verify <FILE>

This validates:

receipt payload hash
Ed25519 signature
signer key fingerprint consistency

Legacy unsigned receipts

For older receipts generated before signing support:

agentkernel receipt verify --allow-unsigned <FILE>

Replay a receipt

agentkernel receipt replay <FILE>

Replay behavior:

verifies the receipt first
re-runs the recorded invocation (run or exec)
prints replay stdout/stderr
compares replay output hash to the receipt
compares replay exit code to the receipt

Important notes:

receipt replay does not auto-add --receipt, so replay does not create a chained receipt unless you explicitly pass --receipt yourself in a separate command.
exec receipts require the referenced sandbox to exist and be running.
run receipts with state-dependent flags (--branch, --keep) can replay differently if your local sandbox state has changed.

For legacy unsigned receipts, use:

agentkernel receipt replay --allow-unsigned <FILE>

receipt replay exits with the replay command's exit code if replay fails.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 63 lines · 0 tokens per session scan A e395c459e59a

Subscribe to this mod's changes

receipts is a command published in the GitHub repository thrashr888/agentkernel (58 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 359 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Debugging agent ai claude-code codex microkernel

receipts

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

agentkernel receipt

Generate a signed receipt

Verify a receipt

Legacy unsigned receipts

Replay a receipt

What this file has done since we first saw it

Other commands, from other repositories

awesome-chatgpt

agentlas-cloud

commit

webapp-testing

pr

create-issue