This release adds 1 notable feature for engineering teams evaluating rollout.
Published 1mo
AI Coding Tools
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
ai-detection
ai-plugin
ai-writing
anti-slop
claude-code
claude-code-plugin
+9 more
cline-rules
content-quality
cursor-rules
humanizer
llm
prompt-engineering
typescript
windsurf-rules
writing-tools
Summary
AI summaryFixed JSON output for --stdin --json --quiet when quiet mode was enabled.
Full changelog
Patch release for deterministic safety, CLI output correctness, and release readiness.
Fixed
- Invalid
--stdin --diffoutput no longer prints corrupted humanized text when validation fails. --stdin --json --quietnow still emits the requested JSON report.- Inline code inside protected quoted prose restores correctly.
- Unsafe clause-final contractions stay full-form English.
- Parenthetical em-dash pairs no longer collapse into comma-splice output.
Added
- LLM mode now refuses secret-like content and points users to
--deterministicfor local-only rewrites. - Regression tests cover stdin output, nested placeholders, unsafe contractions, secret-like content, and em-dash parentheticals.
Changed
- Public plugin/package version signals are aligned at
0.5.6. *.reasoning.mdsidecars are gitignored.- PyPI metadata uses the modern SPDX license field.
- README and getting-started copy now use the lower-friction install path and more honest detector wording.
Verification
- GitHub Actions: Tests, Sync SSOT Mirrors, Pages, and Publish to PyPI are green.
- PyPI:
unslop 0.5.6is published.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About unslop
CLI that strips AI writing patterns (sycophantic openers, filler phrases, em-dash overuse)
Related context
Beta — feedback welcome: [email protected]