By ddaanet
Shell scripting gotchas skill plus automatic shellcheck feedback on edited shell files
Claude Code plugin: shell scripting gotchas knowledge plus automatic shellcheck feedback.
shell-gotchasSelf-triggering skill that loads when Claude writes or edits shell scripts (.sh/.bash files, shebang lines, git hooks, bats tests, wrapper scripts, Makefile recipes). Covers what shellcheck cannot catch:
paste, sed -i, date, stat, bash 3.2 on macOS, …)set -e blind spots, exit-status loss, quoting, filename safety, read disciplineGIT_DIR), submodule escape, linked worktrees, Claude Code sandbox specificsDetailed catalogs live in skills/shell-gotchas/references/.
A PostToolUse hook runs shellcheck on every shell file Claude writes or edits (detected by extension or shebang) and feeds findings back to Claude automatically. When shellcheck is not installed, the first shell-file edit of a session shows a one-time notice that lint feedback is inactive; missing jq disables the hook silently.
shellcheck and jq on PATH for the hook (the skill works without them)/plugin marketplace add ddaanet/claude-plugins
/plugin install shell-scripting@ddaanet
Local testing:
claude --plugin-dir /path/to/shell-scripting
Built test-first: baseline subagent runs (without the skill) showed agents handle famous gotchas in greenfield code but ship latent GNU-isms when editing existing scripts, print success messages on failed paths, and lose exit statuses behind substitutions. The skill body targets those observed failures; the catalogs serve as lookup.
Content is research-grounded, not memory-derived: every claim was verified against primary sources (POSIX.1-2024, GNU/BSD man pages, bash NEWS, Greg's Wiki, githooks(5), Claude Code docs) or empirically (shellcheck 0.10.0, git 2.47), and the reference catalogs carry inline citations. The fact-check pass corrected the original improvised version in several places — including claims that shellcheck misses things it catches, and a suppression syntax that was itself a shellcheck parse error.
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub ddaanet/claude-plugins --plugin shell-scriptingPre-/clear task snapshot for Claude Code: agent writes current task + open decisions; at next session start, a hook scrapes the prior transcript and injects task + last-N prompts + files touched into the fresh agent automatically.
Opinionated agent framework for Claude Code
Forces `git status` to run with the Claude Code command sandbox disabled, so it reports the real working tree instead of phantom sandbox-mount entries.
Candidature assistée : préparation, lettre de motivation, CV adapté, relecture, suivi des retours. Stockage Notion. Contenu français.
Commit-msg git hook that replaces conventional-commit prefixes (feat:, fix:, docs:, ...) with gitmoji emojis. Installs the per-repo hook automatically on SessionStart whenever the plugin is enabled in the current repo.
MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.