sd0x-dev-flow

**Must read and follow the skill below before executing this command:**

Bug/Issue fix workflow. Investigate -> locate -> fix -> test -> review.

Bump package and plugin version in sync

Comprehensive assessment of Unit / Integration / E2E three-layer test coverage, identify gaps and provide actionable recommendations.

- Project root: !`git rev-parse --show-toplevel`

Pure Claude code investigation. Quickly deep-dive into codebase — trace execution paths, understand architecture, diagnose issues.

Dual-perspective code investigation. Claude and Codex explore independently, then integrate conclusions.

⚠️ **Must read and follow the skill below before executing this command:**

⚠️ **Must read and follow the skill below before executing this command:**

⚠️ **Must read and follow the skill below before executing this command:**

Explain complex code logic using Codex MCP

⚠️ **Must read and follow the skill below before executing this command:**

⚠️ **Must read and follow the skill below before executing this command:**

⚠️ **Must read and follow the skill below before executing this command:**

⚠️ **Must read and follow the skill below before executing this command:**

⚠️ **Must read and follow the skill below before executing this command:**

⚠️ **Must read and follow the skill below before executing this command:**

Initialize Codex CLI infrastructure (AGENTS.md + hooks). Setup sd0x-dev-flow for non-Claude agents.

Generate unit tests for specified functions using Codex MCP

⚠️ **Must read and follow the skill below before executing this command:**

EVM contract error and calldata decoder — decode selectors, revert data, calldata via Sourcify/Etherscan/4byte

- Branch: !`git rev-parse --abbrev-ref HEAD`

⚠️ **Must read and follow the skill below before executing this command:**

Remove AI-generated artifacts from documents, including tool names, boilerplate patterns, over-structuring.

Deep-dive analysis of an initial proposal — research code implementation, produce an actionable roadmap and alternatives

Multi-wave parallel code exploration. Orchestrates 2-3 Explore agents across multiple waves for large-scale codebase research with completeness scoring.

Multi-agent deep research orchestration. Parallel researcher agents explore web + code + community sources, synthesize via claim registry, validate with conditional adversarial debate.

⚠️ **Must read and follow the skill below before executing this command:**

Refactor documents — simplify without losing information, visualize flows with sequenceDiagram.

Start from first principles, explore possible solutions and quantitatively assess feasibility. Use before /tech-spec.

⚠️ **Must read and follow the skill below before executing this command:**

⚠️ **Must read and follow the skill below before executing this command:**

Investigate code history, track change origins and root causes

Git identity and GPG signing profile manager

- Worktrees: !`git worktree list 2>/dev/null || echo 'not in a git repo'`

- Repo root: !`git rev-parse --show-toplevel`

- Repo root: !`git rev-parse --show-toplevel`

- Repo root: !`git rev-parse --show-toplevel`

GitHub Issue and PR review thread deep analysis with Codex blind verdict. Read input -> classify -> verdict assessment -> investigate -> report.

Jira integration — view issues, generate branches, create tickets, transition status via event vocabulary

Load GitHub PR review comments into AI session — analyze, triage, plan. Default: analysis-only (no auto-fix).

Pre-merge analysis and preparation — conflict detection, impact analysis, suggested commands (analysis-only, no auto-merge)

Change-aware next step advisor. Runs deterministic analysis on git state, then suggests actionable next steps or session summary.

- Obsidian CLI: !`bash -c 'command -v obsidian >/dev/null 2>&1 && obsidian version 2>/dev/null || test -x "/Applications/Obsidian.app/Contents/MacOS/obsidian" && /Applications/Obsidian.app/Contents/MacOS/obsidian version 2>/dev/null || echo "not found"' 2>/dev/null || echo "unknown (sandbox)"`

- Session file: !`bash -c 'test -f "$HOME/.op-claude-session" && echo "exists" || echo "No session file"' 2>/dev/null || echo "unknown (sandbox)"`

⚠️ **Must read and follow the skill below before executing this command:**

Post friendly review comments to a GitHub PR — prepare, preview, submit.

PR self-review — review changes, produce checklist, update rules

- Repo: !`gh repo view --json nameWithOwner --jq '.nameWithOwner' 2>/dev/null || echo 'unknown'`

Pre-PR confidence audit with 5-dimension scoring. Aggregates test quality, coverage, risk, and AC traceability into a single readiness index (0-100).

Quick pre-commit checks — lint:fix -> test

Run pre-commit checks: **lint:fix -> build -> test**

Project health audit with deterministic multi-dimension scoring. Evaluates OSS readiness, robustness, scope, runnability, and stability.

Convert a technical spec into a PM/CTO-readable executive summary. Simplify technical details, focus on business value.

⚠️ **Must read and follow the skill below before executing this command:**

**Must read and follow the skill below before executing this command:**

**Must read and follow the skill below before executing this command:**

Project initialization inventory (one-time). Use when first onboarding or after major structural changes.

Review technical spec documents from completeness, feasibility, risk, and code consistency perspectives.

Uncommitted code risk assessment — breaking changes, blast radius, scope analysis.

Safely remove plugin assets (skill/command/agent/rule/script/hook) with dependency detection and reference cleanup

P2 dismiss blind verification via Codex independent assessment

Wrap-up refactoring — simplify code, eliminate duplication, preserve behavior

**Must read and follow the skill below before executing this command:**

**Must read and follow the skill below before executing this command:**

- Branch: !`git rev-parse --abbrev-ref HEAD`

**Must read and follow the skill below before executing this command:**

⚠️ **Must read and follow the skill below before executing this command:**

**Must read and follow the skill below before executing this command:**

Research current code state then update corresponding docs, ensuring docs stay in sync with code.

Verification loop — lint -> typecheck -> unit -> integration -> e2e

**Must read and follow the skill below before executing this command:**

Rewrite the previous reply in Traditional Chinese

PM/CTO executive summary expert. Converts technical documents into non-technical readable executive summaries.

Cleanup refactoring expert. Simplifies code, eliminates duplication, preserves behavior.

Codex architecture consulting expert (third brain). Uses Codex CLI to obtain architecture advice and integrates dual perspectives.

Codex implementation expert. Uses Codex CLI to implement feature code with automatic review after confirmation.

Test coverage analysis expert. Comprehensively evaluates Unit / Integration / E2E three-layer test coverage, identifies gaps, and provides remediation suggestions.

Document refactoring expert. Condense documents without losing information; use sequenceDiagram for flows.

Feasibility analysis expert. Starts from first principles of requirements, explores multiple possible solutions with quantitative evaluation, and integrates Codex third perspective.

Code archaeology expert. Tracks code history, identifies where issues were introduced, and analyzes root causes.

Performance optimization expert. Identifies N+1 queries, memory leaks, and slow queries.

Refactoring review expert. Evaluates refactoring risk and verifies behavior preservation.

Solution deepening expert. Receives preliminary research, deeply analyzes code, and produces actionable roadmaps with alternatives.

Strict code reviewer. Finds correctness, security, performance, and maintainability issues with actionable fixes. Use proactively after code changes.

Technical spec review expert. Reviews technical documents for completeness, feasibility, and risk assessment, and provides improvement suggestions.

Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.

Industry best practices audit. Researches best practices (via WebSearch or agent-browser), analyzes current implementation, then uses /codex-brainstorm adversarial debate to confirm alignment. Outputs gap analysis report. Use when: auditing against industry standards, checking compliance with best practices, benchmarking implementation quality. Not for: code review (use /codex-review), architecture design (use /codex-architect).

Bug fix workflow. Use when: fixing bugs, resolving issues, regression fixes. Not for: new features (use feature-dev), understanding code (use code-explore). Output: fix + regression test + review gate.

Bump package and plugin version in sync. Updates package.json, .claude-plugin/plugin.json, and install-state manifest to the same version. Use when: user says 'bump version', 'update version', '更新版本', '版本 +1', or /bump-version

Claude Code config health check + plugin sync. Use when: auditing .claude/ structure, checking naming, verifying hook setup, detecting plugin version drift, syncing installed assets. Not for: skill quality (use skill-health-check), code review (use codex-code-review). Output: health report + fix recommendations.

Pure Claude code investigation. Use when: tracing execution paths, understanding architecture, diagnosing issues. Not for: dual-perspective review (use code-investigate), code review (use codex-code-review). Output: analysis report with findings.

Dual-perspective code investigation. Use when: deep code analysis needing both Claude and Codex perspectives. Not for: quick exploration (use code-explore), code review (use codex-code-review). Output: integrated findings from dual analysis.

Codex architecture consulting. Use when: designing features, evaluating architecture, getting second opinion on design. Not for: implementation (use codex-implement), code review (use codex-code-review). Output: architecture advice + design recommendations.

Adversarial brainstorming via Claude+Codex debate. Use when: exploring solutions, feasibility analysis, exhaustive enumeration. Not for: implementation (use feature-dev), architecture only (use codex-architect). Output: Nash equilibrium consensus + action items.

Code review via Codex CLI with full disk access. Use when: deep review needing full codebase read, uncommitted change review. Not for: quick diff review (use codex-code-review), doc review (use doc-review). Output: severity-grouped findings + merge gate.

Code review using Codex MCP. Use when: PR review, code audit, second opinion on changes. Not for: doc review (use doc-review), security audit (use security-review). Output: severity-grouped findings + merge gate.

Explain complex code via Codex MCP. Use when: understanding complex logic, tracing data flow, onboarding to unfamiliar code. Not for: code review (use codex-code-review), exploration (use code-explore). Output: structured explanation at chosen depth.

Implement features via Codex MCP. Use when: writing new code from specs, implementing features, Codex-driven development. Not for: code review (use codex-code-review), architecture advice (use codex-architect). Output: implemented code + review loop.

Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs git hooks, copies runner scripts. Use when setting up a new project or after updating skills.

EVM contract error and calldata decoder. Use when: user pastes hex revert data, calldata, function selector, or mentions custom error, execution reverted, 4byte, decode. Input contains 0x + 8+ hex chars.

Create or update GitHub PR with gh CLI. Auto-extracts ticket ID from branch name, generates title/summary from commits. Auto-detects existing PR and switches to update mode. Default: --dry-run (show command, don't execute). Use when: user asks to open/create/update a PR, says /create-pr, wants to refresh PR description after new commits, or says 'update pr', 'update PR title', 'refresh PR body'.

Create, update, or scan request documents. Use when: planning features, tracking requests, updating progress, scanning incomplete requests, checking request status dashboard. Not for: tech specs (use tech-spec), code implementation (use feature-dev). Output: request document with status tracking.

Remove AI artifacts from documents. Use when: cleaning AI-generated text, removing tool names, fixing boilerplate patterns. Not for: doc review (use doc-review), doc refactoring (use doc-refactor). Output: cleaned document preserving original intent.

Multi-wave parallel code exploration orchestrator. Use when: large-scale codebase research, understanding complex cross-domain systems, deep investigation needing multiple perspectives simultaneously. Not for: quick lookup (use code-explore), dual confirmation (use code-investigate), code review (use codex-code-review). Output: unified exploration report with completeness scoring.

Multi-agent deep research orchestration for any topic. Use when: user wants to deeply research a topic, explore a question from multiple angles, understand industry practices, compare approaches, or needs comprehensive analysis combining web sources + codebase + community knowledge. Triggers on: 'research this', 'deep research', 'explore this topic', 'what are the best approaches for', 'investigate options for', 'comprehensive analysis of', multi-perspective research, or any question that benefits from parallel exploration across web + code + community sources. Not for: quick code lookup (use code-explore), code review (use codex-review-fast), audit-only (use best-practices), feasibility comparison (use feasibility-study).

Document review via Codex MCP. Use when: reviewing .md docs, tech spec audit, document quality check. Not for: code review (use codex-code-review), test review (use test-review). Output: 5-dimension rating table + gate.

Feasibility analysis from first principles. Use when: evaluating solutions before tech-spec, comparing approaches, risk assessment. Not for: implementation (use feature-dev), architecture advice (use codex-architect). Output: quantitative comparison + recommendation.

Feature development workflow. Use when: implementing features, writing code, running dev loop. Not for: understanding code (use code-explore), reviewing code (use codex-code-review). Output: implemented feature + tests + review gate.

Feature verification (READ-ONLY, P0-P5). Use when: verifying feature behavior after deployment, validating API responses, diagnosing production issues, post-deploy smoke test. Not for: modifying data (use feature-dev), code review (use codex-review-fast), writing tests (use codex-test-gen), security audit (use codex-security).

Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.

Git identity and GPG signing profile manager. Discovers profiles from GPG + git config, switches local identity, checks signing health. Use when: user says 'switch identity', 'git profile', 'check signing', 'gpg key status', 'which identity', or /git-profile

Git worktree management. Work on multiple branches simultaneously without switching or re-cloning. Use when: user mentions worktree, parallel development, simultaneous branches, or /git-worktree

GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + verdict assessment + investigation strategy.

Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).

Load GitHub PR review comments into AI session — analyze, triage, plan. Default: analysis-only (no auto-fix). Use when: reviewing PR feedback, planning fixes, addressing review comments, replying to reviewers. Not for: creating reviews (use codex-review-fast), creating PRs (use create-pr), viewing PR status (use pr-summary).

Pre-merge analysis and preparation. Analyzes source branch vs target branch: commit stats, conflict detection, file impact. Analysis-only v1 — outputs report + suggested commands, does not auto-merge. Use when: user says 'merge prep', 'pre-merge', 'merge analysis', or /merge-prep

Change-aware next step advisor. Use when: user asks what to do next, workflow progression is unclear, session just started with dirty worktree. Not for: executing the suggested command (user decides), auto-loop decisions (hooks handle that). Output: findings-based suggestions or session summary with commit seed.

Obsidian vault integration via official CLI. Use when: capturing dev artifacts to Obsidian vault, searching vault for context, appending to daily note, managing tasks in vault. Not for: general note-taking without Obsidian (use regular files), browsing Obsidian docs (use agent-browser). Output: vault search results, captured notes, task updates.

Initialize 1Password CLI session for Claude Code. Use when: starting a session that needs 1Password secrets, op CLI keeps prompting biometric auth, setting up OP_SESSION token. Solves: Claude Code's no-TTY subprocess model triggers 1Password biometric auth on every op call. Supports both token-based and App Integration auth modes — auto-detects which mode to use.

Portfolio system knowledge base. Use when: position queries, routing strategy questions, provider integration. Not for: general code exploration (use code-explore), code review (use codex-code-review). Output: domain-specific analysis + recommendations.

Post-development test completion. Use when: checking test coverage after feature-dev, writing missing integration/e2e tests. Not for: unit test generation (use codex-test-gen), test review (use test-review). Output: test files + coverage report.

Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review. Use when: posting code review comments, giving PR feedback, sending inline suggestions. Not for: reading existing reviews (use load-pr-review), creating PRs (use create-pr), PR status (use pr-summary).

List open PRs, filter automation PRs, group by ticket ID, format as Markdown. Use when: user asks for PR summary, PR status, or /pr-summary

Pre-PR confidence audit with 5-dimension scoring. Use when: final check before commit/push/PR, evaluating PR readiness, assessing test quality + risk + coverage holistically. Triggers: pre-pr, readiness check, confidence audit, final verification, ready to PR, how confident. Not for: code review (use codex-review-fast), post-deploy verification (use feature-verify), periodic health (use project-audit).

Project health audit with deterministic scoring. Use when: evaluating project quality, onboarding to new codebase, periodic health checks. Not for: runtime performance analysis, security-specific audits (use /codex-security). Output: 5-dimension score + actionable findings.

Project configuration initialization. Use when: first-time setup, auto-detecting framework, replacing CLAUDE.md placeholders. Not for: ongoing config checks (use claude-health), skill creation (use skill-creator). Output: configured CLAUDE.md + project settings + rules + hooks.

Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).

Lightweight model correction with context-aware rule loading. Use when: model forgot a rule, skipped a required step, edited code/docs without running review, needs to re-read CLAUDE.md or rules. Triggers on: 'you forgot', 'remind', 'check rules', 'what did you miss', '你忘了', 'did you skip review', 'why didn't you run precommit', or /remind. Also use PROACTIVELY after editing files if unsure whether auto-loop was followed — running /remind costs nothing and catches drift early. Not for: full code review (use codex-review-fast), next step advice (use next-step), workflow progression (use feature-dev).

Project initialization inventory (one-time). Use when: first onboarding a project, rebuilding cache after structural changes. Not for: day-to-day development (read cache directly), finding specific files (use code-explore). Output: project map with entrypoints + test map + next steps.

Request tracking knowledge base. Use when: querying request status, managing document references, tracking progress. Not for: creating requests (use create-request), tech specs (use tech-spec). Output: status report + progress tracking.

Uncommitted code risk assessment with breaking change detection, blast radius analysis, and scope metrics. Use when: evaluating PR risk, pre-commit risk check, large refactoring review. Not for: security vulnerabilities (use /codex-security), code correctness (use /codex-review-fast). Output: 3-dimension weighted score + risk level + gate.

Safely remove plugin assets (skill/command/agent/rule/script/hook) with dependency detection and reference cleanup. Use when: user says 'remove skill', 'delete command', 'deprecate', 'clean up unused', or /safe-remove. Not for: code refactoring (use /simplify), feature removal requiring architecture changes (manual).

Security review via Codex MCP. Use when: OWASP Top 10 audit, dependency vulnerability check, security-sensitive changes. Not for: code review (use codex-code-review), test review (use test-review). Output: security findings + audit report.

Lightweight blind verification for P2 finding dismissal. Use when: Claude or user wants independent Codex verification before dismissing a P2 review finding. Triggers: dismiss verification, seek verdict, verify dismiss, P2 false positive check. Not for: P0/P1 (must fix), Nit (use [NIT_DEFERRED]), or general code review (use codex-code-review). Output: [DISMISS_VERDICT] audit trail with verdict, confidence, and evidence refs.

Validate skill quality against routing, progressive loading, and verification criteria. Use when: auditing skills, checking skill health, reviewing skill design. Not for: code review (use codex-code-review) or doc review (use doc-review). Output: health report with per-skill ratings + Gate.

Smart batch commit. Analyzes uncommitted changes, groups by cohesion, generates commit messages matching project style. Default: output git commands for manual execution. With --execute: directly run git add + git commit (requires user approval). Use when: user says 'commit', 'batch commit', 'prepare commit', 'write commit message', or /smart-commit

Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (use git directly), merge conflict resolution (use /merge-prep), branch switching (use git checkout). Output: rebase plan table + copy-pasteable git rebase --onto command.

Customize Claude Code statusline. Use when: user says 'statusline', 'status line', 'customize statusline', 'modify statusline', 'statusline settings', 'statusline theme', 'change theme', 'color scheme', wants to add/remove/change segments (cost, git, model, context), switch color themes (catppuccin, dracula, nord), or asks what can be shown in the statusline.

Tech spec generation and review. Use when: designing features, writing specs, requirement analysis. Not for: implementation (use feature-dev), architecture advice (use codex-architect). Output: numbered tech spec document.

Context-aware test orchestration. Use when: smart test selection, failure triage, progressive test ladder, test failure analysis. Not for: writing tests (use post-dev-test), reviewing tests (use codex-test-review), generating tests (use codex-test-gen), full manual run (use verify). Output: test results + triage report + fixer actions.

Test coverage review via Codex MCP. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.

Monitor GitHub Actions CI runs until completion. Use when: watching CI after push, checking build status, monitoring PR checks, waiting for CI completion, user says 'watch CI', 'check CI', 'CI status', 'monitor build', or /watch-ci. Not for: pushing code (use push-ci), creating PRs (use create-pr). Output: per-run verdict (pass/fail/timeout).

6 hooks across 4 events