make-no-mistakes

Scaffold a .atomic-design-rules.json at the current repo root so the make-no-mistakes atomic-design hooks (PreToolUse ownership enforcement + PostToolUse drift telemetry) start enforcing for this repo. No-op if the file already exists.

Audit a repo for consumer-driven contract drift — a producer (Edge Function / server) and a consumer (frontend) validating the same payload with separate schemas that have silently diverged (the FE↔EF validation-drift pattern). Emits a findings doc, an OpenSpec remediation change, Bilingual Linear issues, and 4-cure scaffold proposals. Accepts a target path as $ARGUMENTS.

Audit a repo for DDD bounded-context boundary leakage — a module owned by one context importing another context's internals instead of going through a shared/published interface (Conway's-Law drift), plus domain purity at the context seam and ubiquitous-language drift. Emits a findings doc, an OpenSpec remediation change, Bilingual Linear issues, and 4-cure scaffold proposals. Accepts a target path as $ARGUMENTS.

Audit Cure-4 enforcement-hook coverage — are the PreToolUse/PostToolUse hooks that prevent the other audits' drift actually installed? Checks for repo-level hooks (`.claude/hooks/`), inherited toolkit hooks, a rules config for them to enforce, and whether every structural rule the other five audits recommend is backed by a real hook (detection-without-enforcement is the anti-pattern). Emits a findings doc, an OpenSpec remediation change, Bilingual Linear issues, and cure scaffold proposals. Accepts a target path as $ARGUMENTS.

Audit a repo for Explicit Architecture violations (Herberto Graça) — the Hexagonal / Onion / Clean dependency rule (source dependencies must point inward, toward the domain), Hexagonal ports & adapters (missing port interfaces, primary vs secondary adapter misplacement), Onion/Clean layer leakage, and CQRS command/query mixing. Emits a findings doc, an OpenSpec remediation change, Bilingual Linear issues, and cure scaffold proposals. Accepts a target path as $ARGUMENTS.

Orchestrator agent for the /make-no-mistakes:implement protocol. Executes Linear issues with full discipline: worktree isolation, subagent dispatch for exploration and architecture, all-reviewer loops (Greptile + CodeRabbit + Graphite), CI verification, and clean merges. Dispatched by the implement command to run in its own context window.

Background agent for cross-referencing open PRs with Linear issues, checking Greptile review scores, forcing GitHub mergeable calculation, and generating actionable PR status reports. Dispatched by the review-open-prs skill.

Audit a repo for structural anti-patterns and repo health: schema drift, duplicated logical columns, multiple writers with no owner, and the broader six-family sweep. Use when the user asks to "audit" a repo, hunt for "drift" or an "anti-pattern", check "repo health", or run a named detector profile (e.g. schema-drift / SCH). Owns the full flow: preflight, scope, detect, verify, cure-map, emit (findings doc + OpenSpec change + Bilingual Linear issues + 4-cure scaffold proposals). Do NOT trigger for premortems, code review of a single PR, or generic status reports.

Guided entry point for repo health when you don't know which audit you need. Use when the user asks "which audit", "where do I start", wants to check "repo health", or mentions "domain driven" design. Inspects the repo, asks a few plain-language questions, recommends which audit(s) to run (or the full ordered sweep), runs them via the audit-engine, and finishes with a premortem on the remediation plan. Best first command for a new repo.

Detects when the user wants to work on a Linear issue, implement a feature, fix a bug, or start development work. Suggests the /make-no-mistakes:implement command. Triggers on: "implement", "work on issue", "start on", "pick up issue", "Linear issue", "build feature", "fix bug", "start coding", "work on <PREFIX>-NNN" or "implement <PREFIX>-NNN" for any Linear issue prefix (APP, BACK, SEC, MYTEAM, etc. — based on your workspace), "implement this", "let's build", "start implementing", "pick up this ticket", "work on this task", "execute this issue", "develop this feature", "ship this", pastes a Linear issue URL, or provides an issue ID. Does NOT trigger on: rebase, sync branches, standup, test execution, code review, general coding questions, or session management tasks.

Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: "premortem this", "premortem my", "run a premortem", "what could kill this", "future-proof this", "stress test this plan", "what am i missing here", "find the blind spots". STRONG TRIGGERS: "what could go wrong", "am i missing anything", "poke holes in this", "where will this break", "devil's advocate this". Do NOT trigger on simple feedback requests, factual questions, or LLM Council requests. DO trigger when someone has a plan or commitment where the cost of being wrong is high.

Applies MoSCoW (bucket) + RICE-adapted (intra-bucket ranking) to Linear issues of a product pillar, traceable to its PIBER+IDCF sub-spike and the latest vision audit. Use when the user asks to "prioritize issues", "priorizar el pillar", "aplicar MoSCoW", "rank the backlog", "RICE scoring", "/prioritize", or wants a data-backed decision on what to work on next within a pillar. Do NOT trigger for: generic backlog ranking without pillar context (use spike-recommend or implement-advisor instead), issue creation, or PR review.

8 hooks across 2 events