--- description: Archive completed and abandoned tasks allowed-tools…

Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.

prompt
→ Claude
--- description: Archive completed and abandoned tasks allowed-tools: Read, Write, Edit, Glob, Grep, Bash(git: ), Bash(mv: ), Bash(mkdir: ), Bash(ls: ), Bash(find: ), Bash(jq: ), TaskCreate, TaskUpdate, AskUserQuestion argument-hint: [--dry-run] model: sonnet --- # /todo Command Archive completed and abandoned tasks to clean up active task list. ## Arguments - --dry-run - Show what would be archived without making changes ## Execution ### 1. Parse Arguments dry run = "--dry-run" in $ARGUMENTS ### 2. Scan for Archivable Tasks Read specs/state.json and identify: - Tasks with status = "completed" - Tasks with status = "abandoned" Read specs/TODO.md and cross-reference: - Entries marked [COMPLETED] - Entries marked [ABANDONED] ### 2.5. Detect Orphaned Directories Scan for project directories not tracked in any state file. CRITICAL : This step MUST be executed to identify orphaned directories. bash # Get orphaned directories in specs/ (not tracked anywhere) orphaned in specs=() for dir in specs/[0-9] /; do [ -d "$dir" ] || continue project num=$(basename "$dir" | cut -d -f1) # Check if in state.json active projects in active=$(jq -r --arg n "$pr
claude-code

Source: benbrastmckie

More testing loops

Ship the release

/goalnew

Run tests and update changelog until both pass without altering the public API.

prompt
→ Claude
/goal ship the release --success "tests pass and changelog updated" --constraints "do not touch the public API" --mode ordered
testingmedium risk

/ralph-loop "fix all tests" --max-iterations 5 (iterates until…

/ralphnew

Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.

prompt
→ Claude
/ralph-loop "fix all tests" --max-iterations 5 (iterates until passing
testingmedium risk

Trim what loads before first paint

Reduce the data downloaded before the first screen appears, with tests and screenshots guarding behavior and appearance.

prompt
→ Claude
Reduce the data [web app] downloads before its first screen appears. First record passing tests, mobile and desktop screenshots, and compressed transferred bytes—the data actually downloaded. Use the build report only to suggest candidates. Defer, compress, or remove one item, then rebuild and rerun every check. Keep it only if tests pass, screenshots are pixel-identical, and bytes decrease; otherwise revert. Stop when no safe candidate remains, progress stalls, or approval is needed. Return measurements, changes, and untested states.
testingmedium risk