Borrowing it
Nothing to install: this file belongs to RoboFinSystems/robosystems. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RoboFinSystems/robosystems/main/.claude/commands/test.mdgit clone --depth 1 https://github.com/RoboFinSystems/robosystemsWrote 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.
[](https://agentmods.dev/commands/robofinsystems/robosystems/test)<a href="https://agentmods.dev/commands/robofinsystems/robosystems/test"><img src="https://agentmods.dev/badge/commands/robofinsystems/robosystems/test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/robofinsystems/robosystems/test"><img src="https://agentmods.dev/badge/commands/robofinsystems/robosystems/test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00015 | $0.00565 |
| Opus 5.5 | $0.00006 | $0.00226 |
| Sonnet 5.5 | $0.00003 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
test 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 1mo 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run just test-all and fix failures to 100% completion.
Strategy
- Run the full gate:
just test-all 2>&1 | grep -E "[0-9]+ passed|[0-9]+ failed|^FAILED |^error:|Recipe .* failed|warnings summary" | tail -20— usetimeout: 600000on the Bash call (the suite takes 5–6 min; the default 2-min Bash timeout kills it). - Iterate per-module: when fixing, use
just test <module>(e.g.just test routers) for faster turnaround. Plain| tail -20works fine here — output is short. - Stop when green: don't re-run the full suite to "confirm" — once it passes, you're done.
What just test-all actually runs
In order: just test (pytest) → just test-dbt quickbooks → just lint fix → just lint → just format → just typecheck → just cf-lint-all → just lint-actions.
That matters for reading the output: only the first stage produces a pytest summary. A dbt build failure, a ruff/basedpyright failure, or a CloudFormation/workflow lint failure will not produce a failed count — it surfaces as a recipe failure line instead. So a green pytest count alone is not proof the gate passed.
For the code-quality half without the ~6-minute test run, use just test-code — that's the combination the git hooks enforce.
Why the grep
With plain | tail -N the pytest summary scrolls away behind the later stages' output. Each alternative anchors something specific:
[0-9]+ passed— the summary count (9785 passed,) but NOT test names liketest_passed_validation[0-9]+ failed— the failure count (1 failed,) but NOT names liketest_logs_failed_revocation^FAILED— line-start anchor catches failure headers without matchingPASSEDlines whose name containsfailed^error:andRecipe .* failed— just's recipe-failure lines, which is how the non-pytest stages reportwarnings summary— pytest's warnings-section header
Success = a [0-9]+ passed line, no failed/FAILED, AND no recipe-failure line. All three conditions, not just the first.
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.
- 1mo ago First seen · 33 lines · 15 tokens per session scan A a2f36416ed97
test is a command published in the GitHub repository RoboFinSystems/robosystems (29 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 565 once invoked, about $0.0001 per session on Opus 5.5. 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
slm-loop
Run a task as a bounded, gate-verified loop backed by SuperLocalMemory — iterate until an independent gate passes, never on the agent's own claim.
rclone_test_makefiles
Make a random file hierarchy in a directory.
rclone_test_changenotify
Log any change notify requests for the remote passed in.
coverage
Add test coverage to existing code.
gsd-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
gsd:add-tests
Generate tests for a completed phase based on UAT criteria and implementation.