--- description: Print current vault stats — sources…
Community ralph loop for quality, sourced from github. Verified exit condition, evaluator-gated.
--- description: Print current vault stats — sources, concepts, entities, stubs, recent activity. when to use: Use for a quick read on where the vault stands. Read-only; writes nothing. Reads from wiki/.meta/ sidecar cache — O(1) regardless of vault size. Triggered by phrases like "status", "vault stats", "what's in the wiki", "how many sources". allowed-tools: Read, Bash, Glob, Grep --- # Wiki Status Print a one-screen summary of the current vault. Read-only — never writes. ## Source of truth Read from wiki/.meta/sources.json and wiki/.meta/backlinks.json . These are O(1) to read regardless of vault size. If either is missing or older than the newest file under wiki/sources/ , wiki/concepts/ , or wiki/entities/ , run python3 scripts/build meta.py first. ## What to report ### Counts | Layer | Count | |---|---| | Sources ( wiki/sources/ ) | N | | Concepts (full pages) | N | | Concepts (stubs) | N | | Entities (full pages) | N | | Entities (stubs) | N | | Syntheses | N | | Outputs | N | Derive "full pages" vs "stubs" from each page's type: frontmatter (via a grep over the first ~15 lines of each file — or use wiki/.meta/backlinks.json + per-type counts). Exclude
claude-code
More quality loops
--- name: gsd:manager description: Interactive command center for…
Community ralph loop for quality, sourced from github. Verified exit condition, evaluator-gated.
--- name: gsd:manager description: Interactive command center for managing multiple phases from one terminal argument-hint: "[--analyze-deps]" allowed-tools: - Read - Write - Bash - Glob - Grep - AskUserQuestion - Skill - Agent requires: [phase] --- <objective> Single-terminal command center for managing a milestone. Shows a dashboard of all phases with visual status indicators, recommends optimal next actions, and dispatches work — discuss runs inline, plan/execute run as background agents. Designed for power users who want to parallelize work across phases from one terminal: discuss a phase while another plans or executes in the background. Creates/Updates: - No files created directly — dispatches to existing GSD commands via Skill() and background Task agents. - Reads .planning/STATE.md , .planning/ROADMAP.md , phase directories for status. After: User exits when done managing, or all phases complete and milestone lifecycle is suggested. </objective> <execution context> @/Users/emilwareus/conductor/workspaces/exlint/islamabad/.claude/get-shit-done/workflows/manager.md @/Users/emilwareus/conductor/workspaces/exlint/islamabad/.claude/get-shit-done/ref
qualitymedium risk
Clean up the slop
Review your recent diff for debug code, dead branches, and bad names, then fix with minimal edits until lint and tests pass.
/goal the recent diff is clean and convention-aligned — review it for debug code, dead branches, and bad names, fix with minimal edits until `npm run lint && npm test` passes; stop after 4 turns
qualitylow risk
Repair accessibility, highest-impact first
Confirm barriers against an agreed standard, fix the one with the greatest user impact, and rerun the same checks.
Check [scope] against [accessibility standard, such as WCAG 2.2 AA] with automated scans and available keyboard, screen-reader, and other manual tests. Confirm each issue, rank it by harm, and fix the highest-impact blocker. Rerun the same checks, affected task, and regression tests. Keep only verified fixes. Stop when no blocker remains, progress stalls, verification is unavailable, or approval is required. Never silence a check or weaken the target. Return issues, fixes, evidence, exceptions, and untested needs.
qualitymedium risk