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 skills add ArabelaTso/Skills-4-SE --skill test-guided-bug-detectorgit clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEWrote 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-guided-bug-detector)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/test-guided-bug-detector"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/test-guided-bug-detector/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-guided-bug-detector"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/test-guided-bug-detector.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 | $0.00082 | $0.02884 |
| Opus 5 | $0.00041 | $0.01442 |
| Sonnet 5 | $0.00016 | $0.00577 |
| Haiku 4.5 | $0.00008 | $0.00288 |
Grade A, and why
test-guided-bug-detector 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 7d 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 — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Guided Bug Detector
Analyze failing tests to detect and explain functional bugs in code.
Overview
When tests fail, they provide valuable clues about bugs in the code. This skill analyzes:
- Test failure output - Error messages, stack traces, assertion failures
- Test expectations - What the test expects to happen
- Actual behavior - What actually happened
- Code execution path - Which code was executed
- Suspicious patterns - Common bug patterns that match the failure
The goal is to identify the root cause bug and explain why the test exposes it.
Bug Detection Workflow
Failing Test Output
↓
Parse Failure Information
↓
Identify Test Expectations
↓
Trace Execution Path
↓
Analyze Discrepancy
↓
Identify Suspicious Code
↓
Explain Bug Mechanism
↓
Suggest Fix
Analysis Process
Step 1: Parse Test Failure
Extract key information from test output:
What to extract:
- Test name and location
- Failure type (assertion, exception, timeout, etc.)
- Expected vs actual values
- Stack trace
- Error messages
Example:
FAILED tests/test_calculator.py::test_divide - AssertionError: assert 0 == 5
Expected: 5
Actual: 0
Stack trace:
File "tests/test_calculator.py", line 15, in test_divide
assert divide(10, 2) == 5
File "src/calculator.py", line 8, in divide
return a // b
Step 2: Understand Test Intent
Determine what the test is trying to verify:
Questions to answer:
- What functionality is being tested?
- What are the inputs?
- What is the expected output?
- What properties should hold?
Example:
def test_divide():
# Intent: Verify division returns correct result
result = divide(10, 2)
assert result == 5 # Expects 10 / 2 = 5
Step 3: Trace Execution Path
Follow the code path from test to failure:
Trace elements:
- Function calls in stack trace
- Control flow decisions
- Data transformations
- Return values
Example trace:
test_divide()
→ divide(10, 2)
→ return a // b (integer division)
→ returns 5
→ assert 5 == 5 ✓ Should pass!
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.
- 7d ago First seen · 435 lines · 82 tokens per session scan A d6fb068b1937
test-guided-bug-detector is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (251 stars, last pushed 20d ago), licensed Apache-2.0. It adds 82 tokens to every session and 2,884 once invoked, about $0.0004 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
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
test-first-bugs
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.
java-code-review
Review Java code for bugs, duplicate code, correctness risks, maintainability improvements, and missing tests. By default review files modified in git; when the user explicitly names files, classes, packages, or a diff, review that scope instead. Generate a detailed review.md report with actionable comments and fixes.
run-checks
Run the project's full verification gate: every check the project defines as a pass/fail condition, built from its CI config, check scripts, and configured tools, or from a formatter-linter-test baseline when it declares none. Use when the user asks to "run checks", "run the verification gate", "run lint and tests"…
flake-triage
Decide whether a preview the visual-diff bot flagged actually regressed or is simply nondeterministic, using a repeat-render oracle at a single commit. Use when a PR's preview diff reports a changed preview whose source the PR does not touch, or when a render, GIF or filmstrip is suspected of being unstable.