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-debloatinggit 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-debloating)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/test-guided-debloating"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/test-guided-debloating/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-debloating"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/test-guided-debloating.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 82 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00129 | $0.01310 |
| Opus 5 | $0.00064 | $0.00655 |
| Sonnet 5 | $0.00026 | $0.00262 |
| Haiku 4.5 | $0.00013 | $0.00131 |
Grade A, and why
test-guided-debloating 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Guided Debloating
Remove unnecessary code from a repository while preserving exactly the behavior exercised by a given test suite.
Workflow
1. Understand Requirements
Inputs needed:
- Target repository path
- Test command to run the test suite
- Programming language/framework
Clarify scope:
- Which tests define required behavior (all tests, specific test files, integration tests only)?
- Should test files themselves be preserved (yes, never modify tests)?
- Are there any files that must be kept regardless of coverage (configuration, documentation)?
2. Run Coverage Analysis
Generate test coverage data to identify exercised code. See coverage_tools.md for language-specific commands.
Python example:
pytest --cov=. --cov-report=json --cov-report=html
JavaScript example:
npm test -- --coverage --coverageReporters=json --coverageReporters=html
Java example:
mvn clean test jacoco:report
Verify:
- Coverage report generated successfully
- All tests pass
- Coverage data includes all source files
3. Analyze Coverage Data
Use scripts/analyze_coverage.py to identify removal candidates:
python scripts/analyze_coverage.py coverage.json --output analysis.json
The script identifies:
- Uncovered files (0% coverage) - safest to remove
- Partially covered files - require manual review
- Uncovered lines - potential dead code within files
Manual review checklist:
- Are uncovered files truly unused (check imports)?
- Do uncovered functions have side effects?
- Are there dynamic imports or reflection?
- Is this a library with public API requirements?
4. Incremental Removal
Remove code incrementally, validating after each step. See debloating_strategy.md for detailed strategy.
Removal order (safest to riskiest):
- Unused imports
# Remove unused import statements # Run tests after removal
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 · 207 lines · 129 tokens per session scan A 79df218e37b6
test-guided-debloating is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (252 stars, last pushed 22d ago), licensed Apache-2.0. It adds 129 tokens to every session and 1,310 once invoked, about $0.0006 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
analysis-to-delivery
A routing guide for turning a new feature request into an analysis and development workflow.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.