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/behavior-preservation-checkerWrote 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/behavior-preservation-checker)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/behavior-preservation-checker"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/behavior-preservation-checker/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/behavior-preservation-checker"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/behavior-preservation-checker.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 | $0.00081 | $0.02111 |
| Opus 5 | $0.00041 | $0.01056 |
| Sonnet 5 | $0.00016 | $0.00422 |
| Haiku 4.5 | $0.00008 | $0.00211 |
Grade A, and why
behavior-preservation-checker 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 11d 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior Preservation Checker
Overview
Validate that a migrated or refactored codebase preserves the original behavior by automatically comparing runtime behavior, test results, execution traces, and observable outputs between two repository versions.
Core Workflow
1. Setup Repositories
Prepare both repositories for comparison:
# Clone or locate repositories
ORIGINAL_REPO=/path/to/original
MIGRATED_REPO=/path/to/migrated
# Ensure both are at comparable states
cd $ORIGINAL_REPO && git checkout main
cd $MIGRATED_REPO && git checkout main
2. Run Behavior Comparison
Use the comparison script to analyze behavioral differences:
python scripts/behavior_checker.py \
--original $ORIGINAL_REPO \
--migrated $MIGRATED_REPO \
--output behavior_report.json
3. Review Results
Examine the generated report for:
- Test result differences
- Execution trace divergences
- Output mismatches
- Performance regressions
- API contract violations
4. Fix Deviations
Follow actionable guidance to resolve behavioral differences.
Comparison Methods
Method 1: Test-Based Comparison
Run the same test suite on both repositories and compare results:
Workflow:
- Identify common test suite (or create equivalent tests)
- Run tests on original repository
- Run tests on migrated repository
- Compare pass/fail status, assertions, and outputs
Example:
# Run on original
cd $ORIGINAL_REPO
pytest tests/ --json-report --json-report-file=original_results.json
# Run on migrated
cd $MIGRATED_REPO
pytest tests/ --json-report --json-report-file=migrated_results.json
# Compare
python scripts/compare_test_results.py \
original_results.json \
migrated_results.json
Method 2: Execution Trace Comparison
Capture and compare execution traces:
Workflow:
- Instrument code to capture function calls, arguments, and return values
- Run identical inputs through both versions
- Compare execution traces for divergences
What ships with it
6 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.
- 11d ago First seen · 344 lines · 81 tokens per session scan A 552fdaca166f
behavior-preservation-checker is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (252 stars, last pushed 21d ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,111 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 2026-08-30.
Other skills, from other repositories
321-frameworks-spring-boot-testing-unit-tests
Use when you need to write unit tests for Spring Boot applications — including pure unit tests with @ExtendWith(MockitoExtension.class) for @Service/@Component, slice tests with @WebMvcTest and @MockitoBean for controllers, @JsonTest for JSON serialization, parameterized tests with @CsvSource/@MethodSource, test…
702-technologies-wiremock
Use when you need framework-agnostic WireMock guidance — stub design, JSON or programmatic mappings, precise request matching, response bodies and faults, classpath fixtures, isolation and reset between tests, verification of calls, dynamic ports and base URLs, and avoiding flaky stubs — without choosing Spring Boot…
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.
codex-qa
QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real /.codex. The first-party method drives the real codex app-server against an isolated CODEXHOME plus a LOCAL mock model (no real API call), and proves a plugin hook fired by…
refactor-safely
Restructure existing code safely without changing externally observable behavior. Composes context, design, architecture, code quality, and testing guardrails into a characterization-first refactoring workflow. Use when the user says 'refactor this', 'clean this up', 'untangle this module', 'move this to the right…
wio
Testing workflow skill for finding high-value test candidates, writing focused tests, generating realistic workloads, reviewing test value, and diagnosing test-suite health. Use for prompts about what to test next, adding or improving tests, reviewing whether a test is worth keeping, low-signal or flaky tests…