make-no-mistakes

Plugin make-no-mistakes from marketplace better-toolkits in chimeranext/better-toolkits. Commands read from the repo's manifest — yesterday.

Skills (39)

• apply

  Startup-agnostic OpenSpec pipeline command (/opsx:apply). Never merges; exit = human review handoff.

• archive

  Startup-agnostic OpenSpec pipeline command (/opsx:archive). Never merges; exit = human review handoff.

• audit-engine

  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

• brainstorming-visual-companion

  Visual brainstorming companion for design and architecture decisions — mapping alternatives, trade-offs, risks, and converged choices with visual artifacts. Source: obra/superpowers (brainstorming/visual-companion). repository: https://github.com/obra/superpowers/tree/main/skills/brainstorming/visua

• bulk-archive

  Startup-agnostic OpenSpec pipeline command (/opsx:bulk-archive). Never merges; exit = human review handoff.

• ci-checks-audit

  Audit a repository''s actual CI jobs (.github/workflows/) against the canonical 10-phase catalog (shared/references/ci/ci-checks.yml). Reports missing required (core) checks, extra/unnamed jobs, duplicate check-runs on the same head, and naming violations (verb-type-subject). Read-only — never edits

• ci-checks-setup
• ci-checks-verify
• continue
• dogfood
• domain-driven-advisor
• evaluate-agent-skills
• evidence-explicit-attribution
• ff
• implement-advisor
• implement
• ishikawa
• merge-advisor
• new
• onboard
• parallel-subagents
• premortem
• prioritize
• propose
• resolve-open-questions
• review-active-issues
• review-open-prs
• spec-recommend
• spike-recommend
• subagents-claude
• subagents-opencode
• sweep-pending-opsx
• sync-advisor
• sync
• systematic-debugging
• update
• verify-evidence
• verify
• worktree-cleanup

Slash commands (72)

• /make-no-mistakes:adhd-mode

  Alias /adhd-mode → /evidence-explicit-attribution (evidence-attributed reasoning with ADHD-style rules: lead with action, numbered steps 01..99, visible work, suppress tangents, no closing pleasantries, matter-of-fact errors, When-to-break-rules, Pre-send check; references RDD of Engram de Gentleman

• /make-no-mistakes:admin-rights

  Run one command with admin rights through the OS-native auth dialog — pkexec on Ubuntu/Linux, osascript with administrator privileges on macOS, Start-Process -Verb RunAs on Windows UAC. Warms up with a no-op, confirms once, logs everything. Takes $ARGUMENTS as the command to elevate (--check for war

• /make-no-mistakes:atomic-rules-init

  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.

• /make-no-mistakes:audit-bounded-context

  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 OpenS

• /make-no-mistakes:audit-context-map-integrity

  Audit a repo for context-map integrity drift (family 8) — the machine-readable context map (contexts + relationship declarations) vs the code's actual inter-context communication: declared relationships (e.g. ACLs) that were never built, direct communication where "separate ways" was declared, and r

• /make-no-mistakes:audit-contract-drift

  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 i

• /make-no-mistakes:audit-enforcement-hooks

  Audit Cure-4 enforcement-hook coverage AND efficacy — does a gate exist for each structural rule, and does that gate actually bind? Covers presence gaps (findHookCoverageGaps) and vacuous-gate shapes 2/4–7 (findHookEfficacyGaps). Emits findings, OpenSpec remediation, Bilingual Linear issues, and cur

• /make-no-mistakes:audit-explicit-architecture

  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, a

• /make-no-mistakes:audit-ownership-placement

  Audit a repo for ownership/placement drift (family 7) — modules sitting in a junk drawer, misnamed folders that don't reflect their declared owner, and code placed under an owner that contradicts the declared ownership map. Emits a findings doc, an OpenSpec remediation change, Bilingual Linear issue

• /make-no-mistakes:audit-policies

  Audit the machine-readable org policy (policies.yml) against the actual enforcement state in the current repo (linear-setup.json, rulesets, hooks). Startup-agnostic. Reports OK/GAP/no-enforced.

• /make-no-mistakes:audit-schema-drift

  Audit a repo for schema drift — 1NF violations, the same logical column duplicated across tables without a single source of truth (the *_bio-in-5-tables pattern), and tables written by multiple owners with no canonical owner. Emits a findings doc, an OpenSpec remediation change, Bilingual Linear iss

• /make-no-mistakes:audit-strangler

  Audit a monolith → microservices migration's health (Strangler Fig — Fowler / microservices.io) — whether a façade/proxy/gateway/sidecar fronts the legacy system, whether old and new paths coexist behind a router for a safe incremental cutover (vs a big-bang rewrite), how far the route migration has

• /make-no-mistakes:audit-ubiquitous-language

  Audit a repo for ubiquitous-language consistency drift (family 9) — the same domain concept named differently across bounded contexts, or a single term carrying two meanings within one context. Consumes per-context term dictionaries. Emits a findings doc, an OpenSpec remediation change, Bilingual Li

• /make-no-mistakes:audit

  Run the full repo-health sweep in one shot — all six audit-engine families (schema-drift, contract-drift, ddd, explicit-architecture, strangler, enforcement-hooks) — and delegate the COMPONENT layer to `atomic-design-toolkit`'s audit when it is installed. Aggregates every family into one cross-famil

• /make-no-mistakes:better-mode

  Better mode — enable the 'Better' agent profile across harnesses (BDD · Jidoka · No-Workarounds · dogfood). Installs/verifies shared/bootstrap/agents/better.md → runtime copies for OpenCode, Claude, and Cursor. Tells you to cycle agents (shift+tab / @better). Enables MCP wiring (better-toolkits Vite

• /make-no-mistakes:bug-squash-locally

  HITL bug-squash on localhost only — one environment per round, headed Chrome DevTools MCP, semantic UI locators. Accepts optional domain label as $ARGUMENTS.

• /make-no-mistakes:bug-squash
• /make-no-mistakes:ci-checks-audit

  Audit actual CI jobs vs the canonical catalog — missing core checks, extra/unnamed jobs, duplicate runs, naming violations. Read-only.

• /make-no-mistakes:ci-checks-setup

  Install/generate CI checks from the canonical 10-phase catalog — walks phases 1→10, core always included, opt-in only on confirmation, emits the workflow set in phase order.

• /make-no-mistakes:ci-checks-verify

  Diagnose a named failing CI check — resolve in the catalog, run/query the real check, return cause + ranked actionables (never asserts without evidence).

• /make-no-mistakes:daily-standup-add-completed

  Append completed work items to today's standup file. Accepts a description, PR number, Linear issue ID, or --reset flag as $ARGUMENTS.

• /make-no-mistakes:daily-standup-post-slack

  Compose and post today's standup message to Slack, combining data from the standup file with interactive user input. Accepts "draft" as $ARGUMENTS to send as draft instead of posting directly.

• /make-no-mistakes:disk-cleanup

  Emergency disk reclamation — deterministic, applies stages 1-4 by default (docker images, worktree node_modules, worktrees via classifier, reconstructible docker volumes) without prompting; --list-only previews. Reports measured before/after, never predictions. Optional target GB as $ARGUMENTS.

• /make-no-mistakes:dogfood

  Dogfooding — confirm the product you are currently working on works with real configuration values and active functionality (eat your own dog food). Generic; follow the SSOT protocol. Not bound to a specific framework.

• /make-no-mistakes:domain-driven-advisor

  Guided entry point for repo health when you don't know which audit you need. Inspects the repo, asks a few plain-language questions, recommends which audit(s) to run (or the full sequence), runs them, and finishes with a premortem on the remediation plan. Best first command for a new repo.

• /make-no-mistakes:evaluate-agent-skills

  Scan/evaluate agent skills with NVIDIA SkillSpector + SkillEvaluator (security + quality). Auto-installs peer CLIs via uv unless --no-install. Modes: scan | quality | validate | full.

• /make-no-mistakes:evidence-explicit-attribution

  Alias /evidence-explicit-attribution → /evidence-explicit-attribution (primary name). Evidence-attributed reasoning format with ADHD-style rules (lead with action, numbered multi-step 01..99, visible work, suppress tangents, matter-of-fact errors, When-to-break-rules, Pre-send-check); references RDD

• /make-no-mistakes:evidence-reasoning-adhd-mode

  Alias /evidence-reasoning-adhd-mode → /evidence-explicit-attribution (attribution + explain + no mojibake; ADHD output rules; references AGENT-BEHAVIOR-EVIDENCE.md / AGENT-CONTRACT.md, not adopted).

• /make-no-mistakes:explain

  Explica algo en dos capas — primero en prosa, luego con detalle técnico — cierra con un insight no obvio, actionables rankeados y AskUserQuestion. Acepta el tema como $ARGUMENTS.

• /make-no-mistakes:gdrive-mcp

  List GDrive root folders via rclone using local .json (client_id/secret) + .rclone-config.json (gdrive); verify() first (read .json with --drive-client-id/secret), loadRemote() second (read .rclone-config.json); no embedded client_id; deprecated rclone config avoided.

• /make-no-mistakes:goodmorning

  Bootstrap your day by scanning for pending next-day handoff files and guiding you through resuming where you left off.

• /make-no-mistakes:goodnight

  Save full session context to a next-day handoff file so tomorrow's session can pick up exactly where you left off. Accepts a short label for the file as $ARGUMENTS.

• /make-no-mistakes:handover-pr

  Package your open PR(s) / branch work into a structured handover and post it to a Slack thread for a teammate to pick up. The mirror of /takeover-pr. Accepts a repo (optionally PR number), a teammate, and optional "draft" / "broadcast" / a thread URL as $ARGUMENTS.

• /make-no-mistakes:handover

  Compose and post a structured engineering handover to Slack — hand a body of work (PRs, Linear issues, an incident, a root cause) to a specific teammate for their review/decision. Accepts a target person and optional "draft" / channel as $ARGUMENTS. Mirrors the house Slack style of /daily-standup-po

• /make-no-mistakes:hygiene-hooks-setup

  Audit, install, and verify tracker/PR hygiene hooks in a repo — detects orphaned hook configs, enables the opt-in Linear create-hygiene gate, and proves each hook with synthetic payloads.

• /make-no-mistakes:implement

  Execute Linear issues with full discipline -- sequential branches, worktree isolation, reviewer loops, CI verification, and clean merges. Accepts one or more Linear issue IDs or URLs as $ARGUMENTS.

• /make-no-mistakes:linear-projects-setup

  Bootstrap a Linear workspace with label taxonomy, projects, milestones, and reviewer integrations. Modes: labels, projects, audit, sync, or clean slate (default). Accepts mode as $ARGUMENTS.

• /make-no-mistakes:merge-advisor

  Calcula el ORDEN en que se deben mergear varios PRs abiertos contra una misma base, para que cada uno siga siendo mergeable cuando le toque. Mide colisiones de archivos, conflictos latentes que solo aparecen después de que otro PR aterriza, artefactos anclados a un SHA de la base, y capacidad de la

• /make-no-mistakes:opsx-apply

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-archive

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-bulk-archive

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-continue

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-explore

  Startup-agnostic exploration command — investigate before committing. References systematic-debugging skill (isolated variables, 5-why evidence chain) and brainstorming-visual-companion (visual artifacts for design decisions). Never writes code; never edits specs directly. Produces evidence referenc

• /make-no-mistakes:opsx-ff

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-living

  Startup-agnostic living spec overlay — builds openspec/features/<feature>/living.md with audit trail and changelog. References brainstorming-visual-companion skill (design artifacts) and systematic-debugging (evidence chain). Never deletes or rewrites openspec/specs/ or openspec/changes/ (SSOT invar

• /make-no-mistakes:opsx-new

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-onboard

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-propose

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-sync

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-update

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:opsx-verify

  Startup-agnostic OpenSpec pipeline command — never merges; exit = human review handoff or artifact transition. References protocol.md (SSOT).

• /make-no-mistakes:parallel-subagents

  Harness-agnostic orchestrator for parallel subagent-driven development — detects OpenCode vs Claude, dispatches independent tasks in waves with background, isolates in worktrees, gates on tests, reviews each implementation, and finishes with a human integration decision (no auto-merge).

• /make-no-mistakes:pending-left

  Gather and present a prioritized, actionable list of everything pending from the current session, git state, Linear issues, and memory.

• /make-no-mistakes:postmortem

  Compose a post-incident report (postmortem) in the house style — evidence verified against logs/DB before writing, blameless, with the mandatory sections Causa Raíz, La Buena Noticia and Plan de Mitigación en marcha. Produces a Slack-ready message (Spanish, mrkdwn, no Unicode bullets) for the incide

• /make-no-mistakes:premortem

  Run a premortem on the plan, launch, product, hire, strategy, or decision the user is about to commit to. Frames it as "already failed 6 months from now" and works backward to find every reason why, then produces a revised plan with blind spots exposed. Outputs an HTML report + Markdown transcript t

• /make-no-mistakes:prioritize

  Aplica MoSCoW + RICE-adaptado a los issues de un pillar, justificando cada veredicto contra el sub-spike PIBER+IDCF y el vision audit mas reciente. Accepts pillar-slug como $ARGUMENTS.

• /make-no-mistakes:ready-to-review-mergeable

  Issue ID required — implement through Phase 3.12 (skip 9–10), assurance:triage pr, execute remote review until gate green, local review only if remote unavailable, human handoff. Never merges.

• /make-no-mistakes:rebase

  Synchronize your entire local state (branches, worktrees, PRs) with the latest release after a team-wide rebase. Accepts a repo name as $ARGUMENTS.

• /make-no-mistakes:recover-opencode-sessions

  Scan the local OpenCode SQLite DB (session, session_message, session_v2) and report real recovered sessions — evidence-only, never invents content. Wraps scripts/recover-opencode-sessions.sh.

• /make-no-mistakes:remind

  Recall past decisions, feedback, and instructions from memory, CLAUDE.md, and project context. Accepts a topic or keyword as $ARGUMENTS.

• /make-no-mistakes:resolve-open-questions

  Sweep session for open decisions buried in prose; resolve in batch via fixed-choice AskQuestion/AskUserQuestion with recommendation first. Scope optional via $ARGUMENTS.

• /make-no-mistakes:secret-clear

  Wipe the staged secret using shred -u (Linux), rm -P (macOS), or random-overwrite-then-delete (Windows). Idempotent — safe to call when no secret is staged. Always run this when finished using credentials.

• /make-no-mistakes:secret-generate

  Generate a random secret with a CSPRNG and stage it with mode 0600, via a password-generator GUI (length slider, character-class toggles, regenerate). The value never appears in the conversation log or terminal history — only its length, alphabet and entropy do. Use /secret-use to consume it and /se

• /make-no-mistakes:secret-input

  Prompt for a secret or password via OS-native GUI dialog (Linux zenity/kdialog/pinentry, macOS osascript, Windows Get-Credential) and stage it with mode 0600. The value never appears in the conversation log or terminal history. Use /secret-use to consume it and /secret-clear to wipe.

• /make-no-mistakes:secret-use

  Run a single command with the staged secret loaded as an environment variable. Format ENVVAR -- command. The secret is NOT auto-deleted — call /secret-clear when done. Accepts arguments as $ARGUMENTS.

• /make-no-mistakes:subagents-opencode

  Desarrollo dirigido por subagents (harness OpenCode) — despachar implementers frescos por tarea, task review, fix loop y ledger; ejecución en procesos independientes vía Herdr/HerdrM.

• /make-no-mistakes:summarize

  Generate a structured recap of everything accomplished in the current session, including tasks completed, files changed, decisions made, and pending items.

• /make-no-mistakes:sweep-pending-opsx

  Startup-agnostic OpenSpec pipeline command — read-only sweep of changes with incomplete /opsx-apply checklists; exit = human handoff of which change to run next. Never edits tasks/specs/changes (SSOT invariant).

• /make-no-mistakes:sweep-unstaged

  Validate ground truth: nothing uncommitted, unpushed, or excluded from a ready-to-review/mergeable PR across every worktree. Reads git worktree list (all checkouts), flags uncommitted/unpushed/PR-less work, never mutates. Use to prove 'nothing left behind' before a draft PR push, before /opsx-sync,

• /make-no-mistakes:sync-advisor

  Mide qué tan lejos está tu checkout de su base y recomienda el sync mínimo (pull, rebase de una rama, o /rebase del equipo). Solo lectura: nunca sincroniza por sí mismo. Accepts base ref como $ARGUMENTS.

• /make-no-mistakes:takeover-pr

  Pick up a teammate's open PR in a specific repo, check it out locally, review it, and continue the work. Accepts a repo name (optionally with PR number) as $ARGUMENTS.

• /make-no-mistakes:validate-skills

  Validate SKILL.md files against the Agent Skills specification (agentskills.io). Deterministic, offline, no external deps. Runs scripts/ci/validate-skills.py over the repo skills. Reports non-conformance (missing frontmatter, invalid name/description).

Subagents (2)

• execution-lead

  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

• pr-reviewer

  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. - Bash - Read - Grep - Glob

Hooks (15)

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/pre-bash.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/stderr/adapters/claude-pre-bash.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/pre-edit.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/atomic/pre-atomic.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/cross-cutting/pre-write-no-cleartext-secret-in-config.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/cross-cutting/pre-write-cross-repo-schema-ownership.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/cross-cutting/pre-write-version-bump-discipline.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/observability/pre-write-observability-guard.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/bilingual/pre-linear-save-issue-bilingual.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/hygiene/pre-linear-save-issue-hygiene.sh

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/qa/pre-tool-prod-write-guard.sh

• PostToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/post-slack.sh

• PostToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/atomic/post-atomic-drift.sh

• PostToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/hygiene/post-linear-save-issue-state-landed.sh

• Stop

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/hygiene/stop-prs-green.sh

Similar plugins