Borrowing it
Nothing to install: this file belongs to backblaze-labs/genblaze. 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/backblaze-labs/genblaze/main/.claude/skills/test-package/SKILL.mdgit clone --depth 1 https://github.com/backblaze-labs/genblazeWrote 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/skills/backblaze-labs/genblaze/test-package)<a href="https://agentmods.dev/skills/backblaze-labs/genblaze/test-package"><img src="https://agentmods.dev/badge/skills/backblaze-labs/genblaze/test-package/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/skills/backblaze-labs/genblaze/test-package"><img src="https://agentmods.dev/badge/skills/backblaze-labs/genblaze/test-package.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00519 |
| Opus 5.5 | $0.00020 | $0.00208 |
| Sonnet 5.5 | $0.00010 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
test-package 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 2mo 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.
What it actually says
Run targeted tests — $ARGUMENTS
Parse $ARGUMENTS:
-
If
$ARGUMENTSischanged:- Run
git diff --name-only origin/main...HEADandgit diff --name-only(working tree). - Union the paths. For each path, map to its owning package:
libs/core/**→corecli/**→clilibs/connectors/<name>/**→<name>libs/spec/**→core(schemas are consumed by core)docs/**,examples/**, root-level configs → no test run (report and stop)
- Run tests for each affected package (see mapping below). Stop on first failure.
- Run
-
Otherwise treat
$ARGUMENTSas one package name. Valid values:core,cli- Connectors:
openai,google,runway,luma,decart,replicate,elevenlabs,stability-audio,lmnt,gmicloud,s3,langsmith
Test command mapping
| Package | Command |
|---|---|
core |
cd libs/core && pytest tests/ -v |
cli |
cd cli && pytest tests/ -v |
any connector <name> |
cd libs/connectors/<name> && pytest -v |
Quick subset (single file under core)
If the user hints at one file (e.g. "just the pipeline test"), run
cd libs/core && pytest tests/unit/<file>.py -v per the CLAUDE.md guidance.
Report
- Pass/fail per package, with pytest's summary line.
- If any failure, surface the failing test name and the first traceback — do not proceed to other packages.
- Remind the user that
make testis still the full-suite gate before PR.
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.
- 2mo ago First seen · 44 lines · 49 tokens per session scan A c1a5f4906b37
test-package is a skill published in the GitHub repository backblaze-labs/genblaze (550 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 519 once invoked, about $0.0002 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 skills, from other repositories
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
unity-pipeline
Drive a running Unity Editor or development Player from the command line via the unity-pipeline package — install the package, keep the editor ticking while unfocused, run the edit→recompile→runtests loop, evaluate C#, and hot-reload files at runtime. Use when an agent needs to control a live Unity instance, automate…
horse-integration-tests
Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.
om-module-scaffold
Build a complete standalone business app, module, or CRUD vertical slice using Open Mercato discovery, commands, APIs, ACL/setup, UI, events, search, migrations, and tests. Use for customer management, deal-pipeline changes, CRM lead capture, library/booking/rental systems, "create a module", "add CRUD entity"…
red-team-review
Unified adversarial review, two modes. Strategic Matrix v4.3 (MTA-004) for arguments/plans/decisions: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA → Blind Spot/Kill Switch → Summary. Deliverable Audit for built artefacts (assignments, reports, code outputs): isolated fresh-context hunt against the brief…
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.