Gstack Guard — Workflow

Overview

How the gstack-guard skill works, step by step.

Source Workflow

Claude skill workflow.

Step-by-step Workflow

<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --> <!-- Regenerate: bun run gen:skill-docs -->

/guard — Full Safety Mode

Activates both destructive command warnings and directory-scoped edit restrictions. This is the combination of /careful + /freeze in a single command.

Dependency note: This skill references hook scripts from the sibling /careful and /freeze skill directories. Both must be installed (they are installed together by the gstack setup script).

mkdir -p ~/.gstack/analytics
echo '{"skill":"guard","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true

Setup

Ask the user which directory to restrict edits to. Use AskUserQuestion:

  • Question: "Guard mode: which directory should edits be restricted to? Destructive command warnings are always on. Files outside the chosen path will be blocked from editing."
  • Text input (not multiple choice) — the user types a path.

Once the user provides a directory path:

  1. Resolve it to an absolute path:
FREEZE_DIR=$(cd "<user-provided-path>" 2>/dev/null && pwd)
echo "$FREEZE_DIR"
  1. Ensure trailing slash and save to the freeze state file:
FREEZE_DIR="${FREEZE_DIR%/}/"
eval "$(~/.claude/skills/gstack/bin/gstack-paths)"
STATE_DIR="$GSTACK_STATE_ROOT"
mkdir -p "$STATE_DIR"
echo "$FREEZE_DIR" > "$STATE_DIR/freeze-dir.txt"
echo "Freeze boundary set: $FREEZE_DIR"

Tell the user:

  • "Guard mode active. Two protections are now running:"
  • "1. Destructive command warnings — rm -rf, DROP TABLE, force-push, etc. will warn before executing (you can override)"
  • "2. Edit boundary — file edits restricted to <path>/. Edits outside this directory are blocked."
  • "To remove the edit boundary, run /unfreeze. To deactivate everything, end the session."

What's protected

See /careful for the full list of destructive command patterns and safe exceptions. See /freeze for how edit boundary enforcement works.

Execution Logic

The skill executes when its trigger fires (slash command, natural-language match, or direct invocation). It reads its references, applies its rules, and produces the documented outputs.

Edge Cases

See the source skill's references/ and scripts/ folders for edge-case handling.

Failure Handling

A skill failure surfaces as a tool error or a partial output; never a silent skip. Re-run with --verbose (where applicable) for diagnostics.

Integration Notes

  • Claude — invoked via the Skill tool with skill: "gstack-guard".
  • Codex — referenced from AGENTS.md if mirrored.
  • Antigravity — referenced from the workspace agent rules if mirrored.
  • HQ Project — listed on the landing page Skills section + post-login sidebar.
  • MD Project (md.sgnk.ai) — file rendered from Skills/Gstack Guard/workflow.md.
  • Obsidian — file rendered with frontmatter + tags.

Usage Examples

Invoke via slash command or natural language matching the skill description.

Source: (none)