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.
npx agentmods add commands/openclaw/crabbox/receiptgit clone --depth 1 https://github.com/openclaw/crabboxWhat 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 | $0.00640 |
| Opus 5 | $0.00000 | $0.00320 |
| Sonnet 5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
receipt 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
receipt
crabbox receipt <run-id> retrieves a brokered run's committed terminal
receipt, retained log, and terminal run record. It verifies the Ed25519
signature and exact coordinator-observable bindings before printing JSON.
crabbox receipt run_a1b2c3d4
crabbox receipt run_a1b2c3d4 --expected-signer sha256:<64-hex-digits>
Verification covers the run ID, lease ID, slug, provider, raw command digest, final exit code, sync and command duration, coordinator start timestamp, client-observed end timestamp, retained log hash, truncation state, public key, and signer fingerprint. For an untruncated log it also independently checks the full stream hash.
The receipt's command end timestamp is client-observed. Verification rejects an end before the coordinator start or more than 30 seconds after the coordinator-observed terminal timestamp. It does not prove the client could not backdate its own signed timestamp.
If the retained log is truncated, the receipt still signs the client's full
observed stream hash, but the coordinator cannot independently recompute that
hash from its retained tail. The receipt records log_truncated: true; the
retained tail hash remains independently verified.
If the run has no committed receipt, the command exits without inferring success or failure from logs, events, or lease state. The execution evidence remains ambiguous.
The coordinator record is durable, but the caller still needs its run ID.
Interactive use can capture the printed recording run ... line. Automation
that must recover after losing client output should use run --lease-output <file> on a supported retained run; the handle is written before remote
execution and includes runID.
The signer is self-signed. A passing receipt proves integrity under the embedded
key, not signer continuity, a human identity, or an external hardware trust
root. Use --expected-signer sha256:<hex> to require a fingerprint obtained
through a trusted channel or pinned by an orchestration campaign.
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 · 62 lines · 0 tokens per session scan A 6d33ec973b68
receipt is a command published in the GitHub repository openclaw/crabbox (1,343 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 640 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.