Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEnpx agentmods add skills/arabelatso/skills-4-se/test-case-reducerWrote 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/arabelatso/skills-4-se/test-case-reducer)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/test-case-reducer"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/test-case-reducer/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/arabelatso/skills-4-se/test-case-reducer"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/test-case-reducer.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 | $0.00100 | $0.02257 |
| Opus 5 | $0.00050 | $0.01128 |
| Sonnet 5 | $0.00020 | $0.00451 |
| Haiku 4.5 | $0.00010 | $0.00226 |
Grade A, and why
test-case-reducer 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.
How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Case Reducer
Automatically reduce bug-triggering test cases to minimal form while guaranteeing the reduced test still reproduces the same failure.
Core Concept
Test case reduction works by:
- Identify: Parse the test case and identify reducible elements
- Remove: Systematically try removing elements (lines, statements, inputs)
- Validate: Run the test after each removal to verify failure is preserved
- Iterate: Continue until no further reduction is possible
Workflow
1. Prepare the Test Case
Ensure you have:
- A test case that consistently reproduces the failure
- A way to run the test (command, script, test framework)
- A clear failure condition (oracle)
2. Define the Oracle
The oracle determines if the test still exhibits the expected failure:
Exit code:
- Test fails with specific exit code (e.g., non-zero)
- Example:
--oracle exit_code --expected 1
Exception type:
- Test raises specific exception
- Example:
--oracle exception --expected ValueError
Output pattern:
- Test output contains specific text
- Example:
--oracle output_pattern --expected "division by zero"
Assertion:
- Test fails on specific assertion
- Example:
--oracle assertion --expected AssertionError
3. Choose Reduction Strategy
Aggressive (fastest, smallest result):
- Binary search reduction first
- Delta debugging second
- Greedy line-by-line cleanup
- Use when: Test execution is fast, minimal size is critical
Balanced (recommended):
- Delta debugging only
- Good balance of speed and quality
- Use when: Standard reduction needs
Conservative (safest, most readable):
- Greedy line-by-line only
- Preserves more context
- Use when: Readability matters, test is already small
4. Run the Reduction
Using the provided script:
python scripts/reduce_test.py test_file.py \
--command "python test_file.py" \
--oracle exit_code \
--expected 1 \
--strategy balanced
Or manually apply reduction algorithms (see references/algorithms.md).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 380 lines · 100 tokens per session scan A 56670afcee80
test-case-reducer is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (252 stars, last pushed 22d ago), licensed Apache-2.0. It adds 100 tokens to every session and 2,257 once invoked, about $0.0005 per session on Opus 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 2026-09-03.
Other skills, from other repositories
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
trace
Trace Elixir call trees from entry points via mix xref. Use when debugging data flow, planning signature changes, or understanding how a bug reaches code.
code-review-web
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug…
bim-consistency-checker
Check BIM model consistency: naming conventions, parameter completeness, spatial relationships, and data integrity across model elements.
022-root-cause-analysis
Use when a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis point of view needs evaluation, or when a maintainer directly asks to find the…