.Codex

Execute an approved split plan, shipping each change group separately as its own branch and PR or as sequential commits on the current branch. Use when the user asks to "split and ship", "ship the split plan", "create separate PRs", or "split changes into branches".

Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only repairs, and App Center visibility issues.

Multi-language code quality validation (Python, JS/TS, Shell, SQL) — formatting, linting, type-checking, complexity analysis with auto language detection. Use when checking code quality or running linters. Trigger on "lint", "type-check", "quality check", "run the linters", "check code quality".

Generate unit test files with structure, fixtures, and mocking patterns for Python (pytest) or JS/TS (Jest), auto-detecting the framework. Use when starting tests for a source file. Trigger on "scaffold tests", "generate test file", "write test boilerplate", "set up tests for".

Shared changelog conventions and formatting rules referenced by $create-changelog and $update-changelog. Not typically invoked directly.

Survey the codebase for analogous features, reusable utilities, and existing patterns relevant to a proposed change, reading any source the task names outside this repo. Returns structured findings without writing code. Use when the user asks to "survey patterns", "find existing patterns", "look for analogous features", "check how similar things are done", "find prior art for this change", or needs pattern context before planning a change.

Apply a UX lens to a user-facing change: whether it serves the user's real goal and whether the path through it holds together, using the Understanding, Bridging, and Flowing contexts. Use when scoping, planning, or assessing any change that affects what a user sees or does. Loaded as a lens during planning and assessment.

Fast spec-driven implementation from a committed spec. Use after /spec to implement an issue with a phase roadmap, TDD waves, map patching, review, and pre-commit validation.

Initialize a new project with full setup — repo structure, docs, quality tools, and CI/CD. Use when starting a brand-new project from scratch. Trigger on "create a new project", "initialize a project", "set up a new repo", "bootstrap a project".

Audit a live website across 7 dimensions — SEO, performance, links, privacy, accessibility, security, content — with PASS/WARN/FAIL gates. Use when checking a deployed site's health or quality. Trigger on "audit my website", "site health", "check SEO", "is my site accessible", "website-health <url>".

Propose a turbo skill improvement upstream by filing a GitHub issue against the turbo repo. Use when the user asks to "contribute to turbo", "submit turbo changes", "contribute back", "suggest a turbo improvement", or "upstream my changes".

Create a CHANGELOG.md following keepachangelog.com conventions with version history backfilled from GitHub releases or git tags. Use when the user asks to "create a changelog", "add a changelog", "initialize changelog", "start a changelog", "set up changelog", "generate changelog", or "backfill changelog".

Analyze what changed and generate a structured test plan at .turbo/test-plans/<slug>.md covering four escalating levels: basic functionality, complex operations, adversarial testing, and cross-cutting scenarios. Use when the user asks to "create a test plan", "plan tests", "what should I test", "generate test scenarios", "test plan for this PR", or "what are the test cases".

Execute multi-level exploratory testing of the app covering basic functionality, complex operations, adversarial testing, and cross-cutting scenarios, plus usability observations through a UX lens reported separately from defects. Deeper than $smoke-test. Use when the user asks to "exploratory test", "test thoroughly", "test all scenarios", "deep test", "test edge cases", "test everything", "break it", "find bugs by testing", "test usability", or "check the UX while testing".

Capture an out-of-scope improvement opportunity so it doesn't get lost. Use when the user asks to "note improvement", "save improvement", "track this for later", "remember this improvement", "note this idea", "log improvement", "backlog this", or "park this idea". Also invoke proactively when noticing something improvable during work that falls outside the current task's scope, or after deliberately shipping a simpler approach that accepts a known ceiling — briefly mention it to the user and offer to note it.

Recall the reasoning behind a past change from Codex session history when available, falling back to commit diff and surrounding code. Use when the user asks to "recall reasoning", "find reasoning", "look up reasoning", "recall implementation reasoning", "find the rationale", "why did I do X", "recall from transcripts", or "find the transcript for this commit".

Choose an implementation path (direct or plan) for evaluated findings and dispatch it. Direct path applies fixes directly; plan path runs $turboplan. Use after $evaluate-findings has tagged findings and they need to be implemented, or when the user asks to "resolve findings", "apply evaluated findings", or "dispatch findings to implementation".

Run security verification — SAST pattern scanning, DAST against a running app, OWASP Top 10 compliance, CVSS assessment, and adversarial code audit. Use before commit/push or when checking code for vulnerabilities. Trigger on "security scan", "is this vulnerable", "OWASP check", "security verify", "scan for vulnerabilities".

Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to "evaluate findings", "assess review comments", "triage review feedback", "evaluate review output", or "filter false positives".

Fetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR conversation comments) without making changes. Use when the user asks to "fetch PR comments", "show PR comments", "check PR for unresolved comments", "list review comments", "what comments are on the PR", "show unresolved threads", or "summarize PR feedback".

Teach the user to deeply understand a change through interactive tutoring: restating understanding, drilling into why/what/how, and quizzing until mastery. The active counterpart to a one-shot explanation. Use when the user asks to "understand this change", "teach me this change", "help me understand what changed", "walk me through this change", "make sure I understand this", "quiz me on this", or "teach me what we did".

Choose Lime validation commands for GUI, command/bridge, config, version, and PR-readiness changes.

准备并执行 Lime 发版；覆盖版本号、发布说明、产物清理、验证门禁、commit、tag 和推送。

Interpret third-party feedback by running parallel internal and peer interpretations to surface intent, correctness concerns, and ambiguities. Use when the user asks to "interpret feedback", "interpret comments", "what does this feedback mean", "clarify reviewer intent", "understand this review", or "interpret these suggestions".

Fetch Claude Code documentation and help update configuration. Use /claude-code-guide <topic> where topic is: memory, skills, hooks, agents, settings, mcp, plugins, cli, overview, all

Analyze a codebase and produce a structured threat model at .turbo/threat-model.md covering assets, trust boundaries, attack surfaces with existing mitigations, attacker stories, and calibrated severity. Use when the user asks to "create a threat model", "threat model", "threat model this codebase", "security analysis", "analyze the attack surface", "what are the threats", or "identify security risks".

Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".

Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using reasoning recalled from past Codex session history). Use when the user asks to "resolve PR comments", "fix review comments", "address PR feedback", "handle review comments", "address review feedback", "respond to PR comments", "answer review questions", or "address code review".

Detect package managers and discover outdated or vulnerable dependencies. Returns structured findings without upgrading. Use when the user asks to "review dependencies", "check for outdated packages", "check dependencies", "scan dependencies", or "dependency review".

Upgrade project dependencies with breaking change research for major version updates. Use when the user asks to "update dependencies", "upgrade packages", "upgrade dependencies", "update deps", "upgrade deps", "update npm deps", "update Swift packages", "cargo update", "go get updates", "bundle update", or "pip upgrade".

Download retained Codex GitHub Action thread artifacts and load their rollout history into the local Codex app. Use when asked to open, load, import, resume, or inspect a Codex automation thread from a GitHub Actions run or a related GitHub issue or pull request.

Forensic scan for npm/PyPI supply-chain compromise (Shai-Hulud/TeamPCP campaigns) — checks persistence, hook injection, compromised packages, IOC strings, C2, dead-man switches. Use when auditing a machine or repo for malicious dependencies. Trigger on "supply chain audit", "check for compromised packages", "Shai-Hulud", "scan for malicious deps".

Detect agentic coding infrastructure in a project: CLAUDE.md, AGENTS.md, installed skills, MCP servers, hooks, and cross-tool compatibility (Claude Code and Codex CLI). Returns structured findings about agentic readiness without applying changes. Use when the user asks to "review agentic setup", "check agentic setup", "agentic readiness", "is this project set up for AI coding", or "review AI coding setup".

End-to-end PR shipping workflow for tinyhumansai/openhuman: commit local changes, push to the user's fork, open or reuse a PR against main, then babysit CI and CodeRabbit feedback until the PR is green and clean. Use when the user asks to ship, open a PR, monitor CI, address review comments, or 'babysit' a branch.

Assess project-wide structural technical debt: complexity hotspots, deprecated API usage, duplication clusters, and architecture rot. Ranks findings by impact and refactor effort into a report at .turbo/technical-debt.md. Use when the user asks to "assess technical debt", "find technical debt", "review technical debt", "what should we refactor", "find refactoring candidates", "where is the code rot", or "what's our worst code". Analysis-only — does not modify code.

Scans an existing codebase and generates project-specific skills that capture inferred conventions such as naming, file organization, framework usage, data access, error handling, and testing style. Writes into the project's chosen skill directory (e.g., `.claude/skills/`, `.agents/skills/`, or a custom path). Use when the user asks to "extract skills from the codebase", "create project skills", "infer project conventions as skills", "codify patterns as skills", or "mine the repo for best practices".

Validate improvements from .turbo/improvements.md, recommend a working set tailored to what's in the backlog, and run one lane: direct fixes, investigation, or planned work. One lane per session. Use when the user asks to "implement improvements", "work on improvements", "address improvements", "process improvement backlog", "tackle improvements", or "implement noted improvements".

Review tutti git diffs for project structure, layering, module ownership, and duplicate event-center infrastructure by planning focused architecture review tasks, then having the main agent orchestrate sub-agents for only the changed areas.

Update all project documentation including implementation docs, user guides, API docs, and architecture diagrams. Use when finalizing features to ensure comprehensive documentation.

OpenLoomi Pet sprite and state helper for Codex. Use for pet state, themes, custom characters, and sprite overrides.

Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and render fanout, implement semantically safe fixes, and verify behavior plus repository budgets. Use for trace files, reported profiling durations or call chains, dropped frames, long tasks, resize or scroll jank, render storms, layout thrashing, selector hot paths, interaction latency, or requests to locate exact source-level bottlenecks.

Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.

Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Recall available if needed` capability hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.

Walk a brand-new OpenLoomi user through the entire pipeline in one guided session: setup health → pet reaction → connector onboarding → run a Loop tick → inspect & approve a decision card → seed Memory → optionally register a custom Loop channel / classifier rule / decision type. Triggers: openloomi tour, guided tour, walk me through openloomi, show me everything, end-to-end demo, 带我看一下, 体验一下, 一条龙, 一键体验, first time using openloomi, what's next after setup.

Draft, confirm, and post a single conversational reply to GitHub PR conversation comments (issue comments). The reply addresses all tracked items in one natural-prose message. Use when the user asks to "reply to PR conversation", "post PR conversation replies", or "draft PR conversation messages".

For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under .memsearch/skill-candidates/, not the host agent's own skills system.

Add, repair, or validate an OpenBiliClaw platform source across fetching, account signals, discovery, and user surfaces. Use for source-specific integration work and its acceptance; exclude unrelated UI, recommendation-algorithm, or release-only work.

OpenLoomi install & first-use setup helper for Codex. Use when the user wants to install OpenLoomi, configure it, or troubleshoot `INSTALL_REQUIRED` / `SOURCE_FOUND_APP_NOT_BUILT` / `SESSION_INITIALIZATION_REQUIRED` after running setup-status. Triggers: install openloomi, configure openloomi, setup openloomi, openloomi not installed, openloomi not finalized, install_required, install missing, guest session.

Internal helper contract for calling the codex-companion runtime from Claude Code

Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin

From a Tutti checkout, run, audit, freshly replay, publish, or diagnose Session Replay cassettes that are driven by case-repository scenario scripts (CDP), not by interactive UI recording. Use for real-Provider capture while a scenario.mjs executes, cassette transport or semantic-state mismatches, fresh replay qualification, AgentGUI replay evidence, and product-side support for a new Agent Target beyond local:codex / local:claude-code. Do not use to author Case metadata or scenario scripts (case repository write-replay-case), or for executionKind "ui" Cases.

Mandatory iPolloWork code-change gate for modern, minimal, performant, reuse-first implementation and clean repository ownership. Use whenever AI creates, edits, deletes, or refactors application code, server code, packages, scripts, tests, dependencies, schemas, routes, UI, or generated-file workflows. Reuse existing code before creating files, keep one source of truth, prevent parallel implementations and junk directories, justify every new file or dependency, and audit the current change before completion.

Create, modify, debug, or migrate Minecraft mods for current NeoForge or Fabric 26.x, legacy 1.21.x, and Forge 1.20.1. Use for loader-based gameplay code and assets; use minecraft-multiloader when one codebase must target both modern loaders.

Design and implement automated tests for current Minecraft 26.x or legacy 1.21.x mods and plugins using JUnit, MockBukkit, NeoForge Game Tests, or Fabric Game Tests. Use for test code and test execution, not release publishing or gameplay implementation.

Internal guidance for presenting Codex helper output back to the user

Create or update reusable iPolloWork templates through conversation for Design, Slides/native editable PPT, and HyperFrames Video. Use when planning, generating, repairing, validating, or saving a template package, manifest, reusable variables, cover, slide/PPT markers, video composition, or design-system token integration.

Create, edit, and debug vanilla Minecraft 26.x and 1.21.x datapacks, including functions, advancements, recipes, loot tables, predicates, tags, and pack metadata. Use when the deliverable is a datapack file tree without Java or loader APIs.

Generate or edit Minecraft raster assets such as pack icons, promo art, concept textures, thumbnails, banners, and UI mockups. Use when the deliverable is a bitmap image rather than JSON, SVG, or code-native assets.

Set up and review CI, artifact publishing, versioning, and release governance for Minecraft 26.x or legacy 1.21.x mods and Paper plugins. Use for pipelines and releases, not gameplay implementation or server operations.