scanlisted

## Repository context. Gather first Collect these with **individual** Bash calls, one command per call, never combined into a single invocation: - Current branch, `git branch --show-current` - Recent commits, `git log --oneline -10` - Shallow clone, `git rev-parse --is-shallow-repository` Treat a failure (not a repository, git unavailable) as an unknown value and carry on. Keep these as separate body Bash calls rather than pre-compute lines: the harness runs a skill's whole pre-compute block as one shell invocation, and a worktree-isolated session refuses a compound command that contains git. ## Pre-computed context Lane config: !`ls "${CLAUDE_PROJECT_DIR:-.}/.claude/bugs.md" 2>/dev/null || echo "absent — bundled default lanes apply"` ## Variables Arguments: `$ARGUMENTS` ## Purpose `/bugs:scan` is the front of the bug lifecycle: it hunts defects **nobody has observed yet**, in code that is resting. Every other finding-producer in reach needs an oracle first, a diff, a failing test, a stack trace, a factual claim, a comment marker. This one needs none of them. One invocation is **one bounded pass**: hunt a target (or a rotated lane), verify each candidate through a separate fresh-context gate, report what survives in the plugin's five-field shape, stop. That makes it equally usable interactively ("find a bug in the billing module"), from a `/loop`, or as a daily operator routine, the same bounded unit either way. The design premise, taken from published practice: pe