ktg-plugin-marketplace/plugins/human-friendly-style/CHANGELOG.md
2026-05-29 11:53:00 +02:00

2.5 KiB

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[1.1.0] - 2026-05-29

Added

  • Irreversible-action carve-out in output-styles/human-friendly.md — a new directive (9th) that overrides the hide-by-default noise reduction for state-changing, unrecoverable operations: production deploys, deletes, force-push / git-history rewrites, database migrations and destructive queries, and bulk file edits. For these, Claude shows the exact command and target verbatim before running and reports the same verbatim after, even unprompted, so the user can approve and audit. When reversibility is uncertain, the action is treated as irreversible. Documented as best-effort model guidance, not an enforced guard — a hard guarantee would require a hook, which is deliberately out of scope for this zero-runtime plugin.
  • "Getting more detail" section in the README surfacing the escape hatch that already lived in the style: ask once for the raw form, set a standing preference for the session, or turn the style off via /config / /output-style. Also notes the irreversible-action exception.

Changed

  • README directive table grows from eight rows to nine; prose "eight directives" reference updated to "nine"; version badge 1.0.01.1.0.
  • .claude-plugin/plugin.json description extended to mention irreversible actions are always shown verbatim.

[1.0.0] - 2026-05-04

Added

  • Initial release of human-friendly-style as a shared output style for ktg-plugin-marketplace
  • output-styles/human-friendly.md — the style file with frontmatter (name, description, keep-coding-instructions: true) and full instruction set covering tone, language matching, hidden-by-default noise, prose-first formatting, and honest uncertainty handling
  • .claude-plugin/plugin.json manifest (v1.0.0, MIT, marketplace metadata)
  • Professional README with badges, problem/solution narrative, eight-directive table, before/after example, architecture diagram, install + activation steps, cross-plugin use guidance, compatibility matrix, and versioning policy
  • CLAUDE.md describing component layout, activation flow, and frontmatter contract
  • GOVERNANCE.md establishing fork-and-own adoption model, contribution policy (issues yes, PRs no), and version stability guarantees — aligned with marketplace-wide governance pattern