Borrowing it
Nothing to install: this file belongs to swarm-ai-research/swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/swarm-ai-research/swarm/main/.skills/regression-check/SKILL.mdgit clone --depth 1 https://github.com/swarm-ai-research/swarmWrote 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/swarm-ai-research/swarm/regression-check)<a href="https://agentmods.dev/skills/swarm-ai-research/swarm/regression-check"><img src="https://agentmods.dev/badge/skills/swarm-ai-research/swarm/regression-check/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/swarm-ai-research/swarm/regression-check"><img src="https://agentmods.dev/badge/skills/swarm-ai-research/swarm/regression-check.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 | $0.00029 | $0.00391 |
| Opus 5 | $0.00015 | $0.00196 |
| Sonnet 5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
regression-check 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.
What it actually says
EXECUTE NOW
Mode: $ARGUMENTS
Parse:
tests— run pytest suite onlybaseline— re-run baseline scenario and compare metricsfullor empty — run both tests and baseline comparison
Step 1: Run tests
python -m pytest tests/ -v --tb=short
Report pass/fail count. If any failures, list them.
Step 2: Run baseline scenario
python -m swarm run scenarios/baseline.yaml --seed 42 --epochs 10 --steps 10
Step 3: Compare against last known-good
Read the most recent baseline run from memory at .letta/memory/runs/latest.md.
If a previous baseline exists, compare:
- Welfare: delta and percentage change
- Toxicity: delta
- Acceptance rate: delta
- Quality gap: delta
Flag any metric that changed by more than 10% as a potential regression.
Step 4: Report
## Regression Check
### Tests
- {passed}/{total} passed
- Failures: {list or "none"}
### Baseline comparison
| Metric | Previous | Current | Delta | Status |
|--------|----------|---------|-------|--------|
| Welfare | ... | ... | ... | OK/DRIFT |
| Toxicity | ... | ... | ... | OK/DRIFT |
### Verdict
{CLEAN — no regressions detected}
{REGRESSED — {details}}
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 · 67 lines · 29 tokens per session scan A f3df8bc3424c
regression-check is a skill published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 391 once invoked, about $0.0001 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
cmd_flutter_test
Run Flutter/Dart tests, report failures, and incrementally fix test issues. Covers unit, widget, golden, and integration tests.
bats-testing-patterns
Master Bash Automated Testing System (Bats) for comprehensive shell script testing. Use when writing tests for shell scripts, CI/CD pipelines, or requiring test-driven development of shell utilities.
csharp-testing
C# and .NET testing patterns with xUnit, FluentAssertions, mocking, integration tests, and test organization best practices.
verification-loop
A comprehensive verification system for Claude Code sessions.
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.