operational-rigorlisted

The execution discipline for any non-trivial task — task contract before work, action gates before irreversible steps, scope control during, verification by execution, adversarial self-review, and honest completion reporting. Use at the START of any implementation/fix/refactor/automation task; BEFORE claiming anything is done, fixed, working, or complete; BEFORE any push, deploy, delete, send, purchase, or state-changing MCP call; when a task balloons or retries keep failing; and whenever you are about to report results to the user. The latest load moment is observable — you are about to take your first mutating action (edit, write, state-changing command); loading earlier is better, and if you notice you are already past it, load now. If in doubt whether this applies, it applies.
firaen22/claude-rulebook · ★ 0 · AI & Automation · score 62

Install: claude install-skill firaen22/claude-rulebook

# Operational Rigor Cache over `~/.claude/CLAUDE.md` R0–R7 and `~/.claude/harness/20-judgment-rubrics.md`. The harness is the source of truth — on any conflict, the harness wins (R8). Apply the rubrics mechanically: check the boxes, follow the verdict. ## 1 · Task contract — before touching anything Classify the ASK by intent, not grammar ("can you fix X?" is a task): **question-shaped** (wants to know or decide) → findings + a recommendation (reads and non-mutating runs in scope, edits and outward actions not); **plan-first** (ambiguous scope, irreversible/outward actions, or a plan requested) → plan, then stop for approval; **task-shaped** → proceed under the contract below. A mixed ask is a task whose report also answers the question. Unsure of the CLASS → plan-first (unsure how to *implement* a clearly task-shaped, reversible ask changes nothing). When the answer lives only in your own inference — nothing to open, run, or fetch — say so and label it a judgment call instead of dressing it in process. Write down, before the first edit: - **GOAL** — what will exist that doesn't now, in one sentence. - **ACCEPTANCE** — testable statements, edge behavior explicit (empty / zero / negative / null-undefined-NaN / oversized) — unstated edges are the shared blind spot of every model tier. - **OUT OF BOUNDS** — files/behaviors this task must not touch. - **SURFACES** (mutating/destructive tasks) — what you expect to write, delete, or send to; provisional at contract time,