「code mode」の検索結果

Manual QA harness for the senpi coding agent itself. MUST USE after changing packages/ai, packages/agent, packages/coding-agent, or packages/tui — a green typecheck and `npm test` are NOT QA. Drives the real CLI from source in an isolated sandbox (never touches ~/.senpi or real credentials) across four channels: remote RPC (--mode rpc JSONL stdio), TUI smoke (node-pty on Windows, tmux on POSIX), mock loop (a local fake model server for deterministic, zero-token agent-loop runs), and CLI smoke (--help/--print/--list-models). Every helper ships a --self-test. Use whenever someone says qa senpi, test the agent, verify my change, rpc qa, tui qa, mock-loop qa, smoke the cli, or needs evidence that an agent-loop, tool, keybinding, or provider change works end to end. Capture evidence to local-ignore/qa-evidence/.

日本語の概要は準備中です。原文の説明を表示しています。

Answer a hard question by fanning it out to a PANEL of models running in parallel — each answering independently with web search and bash, none seeing the others' work — then having Opus 4.8 judge every response into a structured analysis (consensus, contradictions, partial coverage, unique insights, blind spots) and write a final answer grounded in it. The panel is two independent Opus 4.8 runs (slug opus4.8-4.8), Opus 4.8 + GPT-5.5 via codex (opus4.8-gpt5.5), Opus 4.8 + Gemini 3.1 Pro via agy (opus4.8-gemini3.1pro), or all three (opus4.8-gpt5.5-gemini3.1pro). Opus always judges and writes the final answer — the pipeline can't be reversed. Runs on local CLI subscriptions (no metered API), and saves a timestamped provenance .md per run. Use this whenever the user asks to "run it through Fusion", says /fusion, wants a multi-model / panel / ensemble answer, wants a question cross-checked across models, or wants a higher-confidence answer with consensus and blind spots surfaced — even if they don't say "fusion". General-purpose: any topic (research, law, strategy, technical, personal). Best for high-stakes research, design calls, and debugging where being confidently wrong is expensive.

日本語の概要は準備中です。原文の説明を表示しています。

Use when you need to apply data-oriented programming best practices in Java — including separating code (behavior) from data structures using records, designing immutable data with pure transformation functions, keeping data flat and denormalized with ID-based references, starting with generic data structures converting to specific types when needed, ensuring data integrity through pure validation functions, and creating flexible generic data access layers. This should trigger for requests such as Improve the code with Data-Oriented Programming; Apply Data-Oriented Programming; Refactor the code with Data-Oriented Programming; Model Java data with records and pure functions; Separate Java behavior from immutable data structures; Validate data integrity with pure Java functions. Part of Plinth Toolkit

日本語の概要は準備中です。原文の説明を表示しています。

Decide where to enforce structured LM output (constrain at decode time with Outlines vs validate-and-retry with Instructor vs grammar with Guidance) and which failure stance to take (Assert/hard-fail vs Suggest/soft-retry). Use when an LM's output is parsed or typed by downstream code and you must pick one enforcement library plus its failure handling, when malformed output is burning tokens on retries, or when choosing between decode-time vs validation-time constraints for local vs API models.

日本語の概要は準備中です。原文の説明を表示しています。

Decision protocol for managing the context/session state of an AI coding tool: when to /clear, when to keep context, and how to detect "context bleed" — the failure mode where stale conversation history biases the model against the current task. Surfaces a discipline that Aider (/clear), Claude Code (/clear), CrewAI (memory=False, re-instantiate), and LangGraph (new thread_id, subgraph isolation) all encode separately but none name as a skill.

日本語の概要は準備中です。原文の説明を表示しています。

Sets up how you and your team build and work with AI agents, and produces an Agent Workflow Charter (agent lanes, plan-mode loop, autonomy ladder with promotion criteria, rules file, review policy, security rules, rollout plan). Use when you ask 'how should we work with Claude Code / Codex / Cursor', 'how many agents should I run', 'should the agent be autonomous', 'plan mode', 'CLAUDE.md', 'AI-native team', 'roll out AI to my team', or 'my agent keeps screwing up'. Draws on 110 Lenny's Podcast guests incl. Claire Vo, Boris Cherny and Aishwarya Naresh Reganti.

日本語の概要は準備中です。原文の説明を表示しています。

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D models, automation, pandas, matplotlib

日本語の概要は準備中です。原文の説明を表示しています。

Run a non-interactive Claude Code print-mode call from Codex. Use when the user asks to "claude print", "ask claude", "run claude", "consult claude", or when a Codex Turbo skill needs Claude as an independent peer reviewer.

日本語の概要は準備中です。原文の説明を表示しています。

Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScript code. Use when refactoring legacy code, implementing modern patterns, or optimizing JavaScript applications.

日本語の概要は準備中です。原文の説明を表示しています。

Diagrams and checkable docs from a codebase. Draws ERDs, C4 context/container/component views, API endpoint catalogues, lifecycle/state machines, and service-to-service call maps as a validated JSON spec plus a standalone HTML viewer, with Mermaid export. Imports OpenAPI, GraphQL SDL and Prisma; otherwise reads the code (NestJS, TypeORM, Express) and writes the spec. Use for: database diagram, ERD, data model, table relationships, C4 or architecture diagram, system context, API map, endpoint list, "show me the endpoints", status flow, state machine, allowed transitions, "what happens after X is approved", how services call each other, microservice map, Mermaid diagram. Also writes documentation as a fact graph: each statement carries its source and a computed confidence, and a drift check fails CI when the code moves. Use to document a system, write architecture or onboarding docs, or explain how a system works.

日本語の概要は準備中です。原文の説明を表示しています。

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.

日本語の概要は準備中です。原文の説明を表示しています。

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

日本語の概要は準備中です。原文の説明を表示しています。

Provides GitHub Copilot CLI task delegation in non-interactive mode with multi-model support (Claude, GPT, Gemini), permission controls, output sharing, and session resume. Use when users ask to hand work to Copilot, compare models, or run Copilot programmatically from Claude Code.

日本語の概要は準備中です。原文の説明を表示しています。

現セッションのリアルトークン使用量と推定削減量を表示。Claude Code セッションログから直接読込 — AI 推定なし。 `/genshijin-stats` で起動。出力は mode-tracker フックが注入し、モデル自身は数値計算しない。

Use claudraband CLI to control Claude Code sessions programmatically. Use when running, scripting, or automating Claude Code via the claudraband CLI — sending prompts, listing/resuming sessions, or working in interactive REPL mode. Triggers on any mention of claudraband, claudraband-cli, npx claudraband, bunx claudraband, or automating Claude Code sessions. Used when you need to ask yourself (Claude) a question

日本語の概要は準備中です。原文の説明を表示しています。

AutoMCM-Pro industrial-grade math modeling agent (opencode binding). Supports AP (AI-led) and Manual (human-spec-led) dual modes with mandatory GitOps checkpoints, forced self-verification of all solver code before LaTeX inclusion, and structured human cross-validation at each pipeline stage. Use for both CUMCM (Chinese) and MCM/ICM (English) competitions.

日本語の概要は準備中です。原文の説明を表示しています。

AutoMCM-Pro industrial-grade math modeling agent (Codex CLI binding). Supports AP (AI-led) and Manual (human-spec-led) dual modes with mandatory GitOps checkpoints, forced self-verification of all solver code before LaTeX inclusion, and structured human cross-validation at each pipeline stage. Use for both CUMCM (Chinese) and MCM/ICM (English) competitions.

日本語の概要は準備中です。原文の説明を表示しています。

Automatically generate TLA+ specifications from source code (C/C++, Python) for formal verification of distributed systems. Use when users need to: (1) Generate TLA+ specs from program implementations, (2) Model distributed systems, consensus protocols, or concurrent algorithms, (3) Extract state variables, actions, and invariants from code, (4) Create formal specifications for model checking with TLC, (5) Verify safety and liveness properties of distributed systems. Particularly effective for message-passing systems, replication protocols, consensus algorithms, and distributed transactions.

日本語の概要は準備中です。原文の説明を表示しています。

Automatically generate TLA+ specifications from program code, repositories, or system implementations. Use when asked to generate TLA+ spec, create TLA+ specification from code, convert program to TLA+, formalize system in TLA+, extract TLA+ model from code, or when working with formal specification of concurrent systems, distributed systems, protocols, algorithms, or state machines that need to be verified.

日本語の概要は準備中です。原文の説明を表示しています。

Convert code between programming languages while preserving functionality and semantics. Use when: (1) Translating functions, classes, or modules between languages (Python, JavaScript/TypeScript, Java, Go, Rust, C/C++), (2) Migrating entire projects to a different language, (3) Need idiomatic translation that follows target language conventions, (4) Converting between different paradigms (OOP to functional, etc.), (5) Porting legacy code to modern languages. Provides language-specific patterns, idiomatic translation guides, and project migration strategies.

日本語の概要は準備中です。原文の説明を表示しています。

Forensic case investigation with evidence-graded findings, calibrated to the input. Use when the user asks to investigate a bug, trace what caused an incident, walk through unfamiliar code, or build a mental model of a code area before working on it.

日本語の概要は準備中です。原文の説明を表示しています。

Apply DDD tactical patterns when working with domain code, and validate proposed domain models before approval (design mode). Enforces aggregate design, value objects over primitives, entity identity rules, and bounded context boundaries. Use when creating or modifying domain models, designing aggregates, working in the domain layer, or when the user mentions 'domain', 'aggregate', 'value object', 'entity', 'bounded context', or 'DDD'.

日本語の概要は準備中です。原文の説明を表示しています。

Enforce architectural rules when generating or modifying code, and validate proposed designs before approval (design mode). Defaults to clean architecture; supports any architecture style via the architecture-refiner. Validates layer responsibilities, dependency direction, and structural constraints using the loaded architecture rules. Use when generating code, reviewing architecture, creating new files, or when the user mentions 'architecture', 'layers', 'structure', 'dependency rules', 'hexagonal architecture', 'ports and adapters', 'modular monolith', or 'onion architecture'. Also use when reviewing generated code for structural compliance.

日本語の概要は準備中です。原文の説明を表示しています。

Connects Claude Code, Codex, Cursor, and other MCP hosts to Writingmate for model discovery, text comparison, image generation, and video generation with Seedance, Sora, Veo, Kling, PixVerse, and other available models.

日本語の概要は準備中です。原文の説明を表示しています。