history

history is a command for coding agents from openclaw/crabbox. It costs 0 tokens per session (579 once invoked), scanned A, original, MIT.

A command that lists recorded remote command runs from a Crabbox broker. Each run includes its state and execution details, such as the command, phase, exit code, duration, and start time.

In plain words
What is it for?
Use it to view runs for a lease, owner, or organization, filter by running, succeeded, or failed state, limit results, or export raw records as JSON.
Why use it?
It makes it easier to inspect past runs and filter them without searching through logs manually.

Command

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/openclaw/crabbox/history
Clone the repo
git clone --depth 1 https://github.com/openclaw/crabbox

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for history

README.md
[![agentmods](https://agentmods.dev/badge/commands/openclaw/crabbox/history.svg)](https://agentmods.dev/commands/openclaw/crabbox/history)
Your own site
<a href="https://agentmods.dev/commands/openclaw/crabbox/history"><img src="https://agentmods.dev/badge/commands/openclaw/crabbox/history.svg" alt="Measured on agentmods" height="20"></a>
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 579 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00579
Opus 5 $0.00000 $0.00290
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 4d ago against content hash 60d0ddd1045a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

history 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 4d 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/history.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

history

crabbox history lists recorded remote command runs from the broker. Each run is created by crabbox run (and run-backed flows such as crabbox job run or capsule replay) and persists its state, phase, exit code, duration, and telemetry on the coordinator. This command requires a configured broker; without one it returns an error.

crabbox history
crabbox history --lease cbx_0a1b2c3d4e5f
crabbox history --owner [email protected]
crabbox history --org example-org --json
crabbox history --state failed --limit 100

Flags

--lease <lease-id>   Filter to runs on a single lease.
--owner <email>      Filter to runs owned by an email.
--org <name>         Filter to runs scoped to an org.
--state <state>      Filter by state: running, succeeded, or failed.
--limit <n>          Maximum runs to return (default 50, broker-capped at 500).
--json               Print the raw run records as JSON.

Output

The default output prints one line per run with the run ID, lease ID, lease slug, state, phase, exit code, duration, start time, an optional resource summary, and the executed command:

run_a1b2c3d4 cbx_0a1b2c3d4e5f swift-crab succeeded phase=command.finished exit=0 duration=42.1s started=2026-05-29T10:15:04Z resources=load=0.42 mem=38% disk=12% command=npm test

Missing values render as - (for example a still-running run has no exit code). The resources=… segment appears only when a coordinator-backed Linux run captured telemetry. --json emits the full run records, including the start/end telemetry snapshots, JUnit result summaries, and classification fields (blockedStage, retryLikely) when present.

Use a run ID from this list with logs, events, or attach to inspect a specific run.

  • logs — print captured run logs.
  • events — print phase and stream events.
  • attach — follow a live run's events.
  • results — parsed test-result summaries.
  • History and logs — concept overview.

Read the full file on GitHub · 54 lines

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.

  1. 4d ago First seen · 54 lines · 0 tokens per session scan A 60d0ddd1045a

Subscribe to this mod's changes

history is a command published in the GitHub repository openclaw/crabbox (1,362 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 579 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.