Skip to content

Releases: moduloTech/danger-claude

v0.5.2

23 Apr 05:25

Choose a tag to compare

Added

  • Install database client CLIs in the Docker image: postgresql-client (provides psql, pg_dump), default-mysql-client (provides mysql, mysqldump), and sqlite3.

v0.5.1

21 Apr 20:37

Choose a tag to compare

Added

  • Install wkhtmltopdf in the Docker image.

v0.5.0

21 Apr 15:24

Choose a tag to compare

Added

  • Automatically append a container-awareness system prompt to every claude invocation (interactive, -p, -c, -r). Informs Claude that it runs in a Docker container, that host services (databases, Redis, etc. from docker-compose) are reachable via host.docker.internal, and that non-interactive Ruby/Node commands should be prefixed with mise x ruby -- / mise x node -- since mise shims are not on PATH outside login shells.
  • --append-system-prompt TEXT CLI option that overrides the default container-awareness prompt with a custom text, forwarded as-is to claude --append-system-prompt.

v0.4.2

20 Apr 13:43

Choose a tag to compare

Added

  • Install jq (JSON processor) and poppler-utils (PDF utilities, provides pdftotext) in the Docker image.

v0.4.1

17 Apr 10:05

Choose a tag to compare

Fixed

  • Piped stdin context was silently ignored in interactive mode without a prompt argument (e.g. issue-md <URL> | danger-claude). The context is now passed as the initial prompt to Claude.

v0.4.0

14 Apr 10:50

Choose a tag to compare

Added

  • Stdin piping support: pipe any content into danger-claude as context. In print mode (-p), the piped content is prepended to the prompt. In interactive mode, it is mounted as /context/stdin inside the container. Stdin is reopened from /dev/tty after consumption so interactive Docker sessions retain a working TTY. Example: issue-md <URL> | danger-claude -p "fix this bug".
  • Positional prompt argument: danger-claude "explain this code" starts an interactive Claude session with that initial prompt, like the claude CLI itself.
  • -s / --shell now accepts an optional command: danger-claude -s "ls -la" runs the command in the container instead of opening a bash shell.
  • -P / --port MAPPING flag to expose container ports to the host (passed as -p to docker run). Supports multiple -P flags for multi-port setups.

Changed

  • Breaking: bare arguments are now treated as a Claude prompt instead of a Docker command. Use -s "command" to run arbitrary commands in the container (replaces -- command).

v0.3.1

07 Apr 16:03

Choose a tag to compare

Added

  • --add-host=host.docker.internal:host-gateway on Linux so containers can reach host services (e.g. Chrome DevTools).

v0.3.0

03 Apr 20:48

Choose a tag to compare

Added

  • -r / --resume SESSION_ID flag to resume a previous Claude session. Works in both print mode (-p -r) and interactive mode (-r alone).

v0.2.1

02 Apr 20:40

Choose a tag to compare

Added

  • --version CLI flag to display the current version.

v0.2.0

31 Mar 14:16

Choose a tag to compare

Added

  • New -m/--model MODEL option to select the Claude model (forwarded as --model to the claude CLI).
  • New -e/--effort LEVEL option to set effort level: low, medium, high (forwarded as --effort to the claude CLI).

Changed

  • -c (auto-commit) now instructs Claude to use Conventional Commits format (<type>: <description>) instead of free-form summary lines.