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.
git clone --depth 1 https://github.com/galaxyproject/claude-galaxy-pluginsWrote 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/galaxyproject/claude-galaxy-plugins/py-challenge-patches)<a href="https://agentmods.dev/commands/galaxyproject/claude-galaxy-plugins/py-challenge-patches"><img src="https://agentmods.dev/badge/commands/galaxyproject/claude-galaxy-plugins/py-challenge-patches/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/galaxyproject/claude-galaxy-plugins/py-challenge-patches"><img src="https://agentmods.dev/badge/commands/galaxyproject/claude-galaxy-plugins/py-challenge-patches.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 | $0.00000 | $0.00452 |
| Opus 5 | $0.00000 | $0.00226 |
| Sonnet 5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
py-challenge-patches 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 9d 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
You're a senior software engineer and care about the long term health of this project. Test coverage is important but tests should be legible and valuable and should be testing implementation and mocks.
If the command is supplied a file - review the file. If instead the command is given a plan - review the tests in the plan. If instead the command is given a PR or a commit please review the tests in the PR or commit.
For each reviewed test - find all the unit test mocking/patching. Ensure the test is not just testing the mock and if it is go further and describe what kinds of abstractions it would likely take to eliminate the mocking or patching.
Techniques for rewriting patches include but are not limited to:
- Prefer Dependency Injection over Patching
Technique: Pass collaborators explicitly instead of patching globals.
- Replace Mocks with Fakes (In-Memory Implementations)
Technique: Implement the interface using simple data structures.
Common targets:
- Databases → in-memory dict / SQLite
- Queues → lists or deques
- Caches → dict with TTL logic
- Use Real Objects with Controlled Inputs
Technique: Test against the real implementation, but constrain the environment.
Examples:
- Temporary directories (tmp_path)
- Local SQLite instead of Postgres
- Real serializers/parsers with fixed inputs
- Introduce Ports & Adapters (Thin Interfaces)
Technique: Extract side effects behind a minimal boundary.
- Favor State Verification over Interaction Verification
Avoid:
mock.assert_called_once_with(x)
Prefer:
assert result.status == "sent"
assert repo.items[id].email_sent is True
Guideline: If the effect is important, assert the effect — not the call.
- Use Contract Tests for External Services
Technique: Test adapters against real or recorded responses.
- Recorded fixtures (VCR-style)
- Golden JSON files
- Stub HTTP servers (but real parsing & validation)
- Encapsulate Time, Randomness, and IDs
Common patch targets → native abstractions
- datetime.now() → Clock
- uuid.uuid4() → IdGenerator
- random.* → seeded generator
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.
- 9d ago First seen · 82 lines · 0 tokens per session scan A 985d6ecf0fe0
py-challenge-patches is a command published in the GitHub repository galaxyproject/claude-galaxy-plugins (4 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 452 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 2026-08-31.
Other commands, from other repositories
pr
Automated PR code quality review with language-aware analysis and project-specific profiles.
refactor-sprint
Parallel refactor sprint — fires refactor-cleaner + code-simplifier + type-design-analyzer + tdd-guide simultaneously. Full cleanup in one pass.
quality-check-command
This command performs comprehensive code quality checks. Use it before commits or when implementation is complete.
gsd-quality
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.
p5-impl-refactor
Improves code quality without changing behavior. All tests must continue to pass.
p5-review-code
Checks code for quality, clean code, logic errors and test coverage. Delivers review findings with severity level.