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/resultsgit 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 | $0.01259 |
| Opus 5 | $0.00000 | $0.00629 |
| Sonnet 5 | $0.00000 | $0.00252 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade A, and why
results 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 3d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
results
crabbox results prints the structured test summary attached to a recorded
run. It answers "did the suite pass, and which cases failed?" without making
you page through the raw command log.
# Record a run, then read its results.
crabbox run --junit junit.xml -- go test ./...
crabbox results run_abcdef123456
crabbox results run_abcdef123456 --failed-only
crabbox results run_abcdef123456 --json
The run id is accepted as a positional argument or via --id. A coordinator
must be configured (CRABBOX_COORDINATOR or config set-broker), because
results are read back from the recorded run, not from the live box.
How results get attached
Results are attached only when crabbox run knows where to find remote JUnit
XML after the command exits. There are three ways to point it at the files.
On the command line:
crabbox run --junit junit.xml -- <command...>
crabbox run --junit junit.xml,reports/junit.xml -- <command...>
crabbox run --junit junit.xml --fail-on-test-failures -- <command...>
In repo config:
results:
junit:
- junit.xml
- reports/junit.xml
failOnFailures: true
Or let run scan common JUnit locations after the command:
crabbox run --results-auto -- <command...>
results:
auto: true
You can also set CRABBOX_RESULTS_JUNIT (comma-separated paths),
CRABBOX_RESULTS_AUTO, and CRABBOX_RESULTS_FAIL_ON_FAILURES in the
environment.
After the command finishes, the CLI reads each remote file from the workdir, parses the JUnit XML, and sends only the parsed summary to the coordinator. Raw XML is never stored. Multiple JUnit files are merged into one summary, so a multi-report setup still produces a single result record. Bad files produce named warnings without erasing valid summaries. Auto discovery accepts files up to 16 MiB and 64 MiB total; it skips larger reports explicitly instead of truncating them into invalid XML.
By default, result parsing does not replace the wrapped command's exit status.
With --fail-on-test-failures or results.failOnFailures: true, a command that
exits zero but produces parsed JUnit failures or errors becomes a failed run
with exit code 1. An existing command failure keeps its original exit code.
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.
- 3d ago First seen · 159 lines · 0 tokens per session scan A 9506cc0bd3bd
results is a command published in the GitHub repository openclaw/crabbox (1,343 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,259 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.