harness

Plugin harness from marketplace aw-harness in AnastasiyaW/codex-claude-code-config. Commands read from the repo's manifest — yesterday.

Skills (59)

• agent-harness-design

  Designing agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool results, agent budgets (10 types), context trust labels against prompt injection, plan-artifact, approval records, observability and traces, evals (13 categories), event

• agents-best-practices

  Use when designing, auditing, refactoring, or explaining an agentic harness for any domain, especially when work must continue from a measured gap to verified completion. Covers provider-neutral loops, tools, permissions, environment adaptation, planning, durable workflow state, context, skills, obs

• diffusion-engineering

  Практическая инженерия диффузионных моделей: архитектуры, обучение, инференс, оптимизация памяти. Использовать при любых задачах с диффузионными моделями: проектирование или модификация архитектуры (UNet/DiT/Flow/Flux), выбор и настройка schedulers/samplers, дообучение (LoRA/DreamBooth/full fine-tun

• flux2-klein-prompting

  Expert prompt engineering for FLUX.2 [klein] image generation and editing model. Use this skill whenever the user wants to create prompts for FLUX.2 [klein], generate images, edit photos with the klein model, work with multi-reference image editing, or needs templates for T2I/I2I tasks. Trigger for

• flux2-lora-training

  Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. Do not use for generic Stable Diffusion/DiT training, prompt authoring, or model serving; route those tasks to their specia

• forensic-prompt-compiler

  Forensic image-to-prompt compiler for image generation models. Use this skill whenever the user wants to: convert/describe an existing image into a generation prompt, reconstruct a scene as a prompt, generate prompts from reference images for AI image tools (Midjourney, FLUX, Stable Diffusion, DALL-

• ml-research-lab

  Machine-learning research loop for dataset curation, fine-tuning, evaluation, inference deployment, experiment tracking, and model explainability. Use when working on ML experiments, training data, model benchmarks, RunPod/GPU runs, classifier quality, vLLM/GGUF serving, SHAP-style model explanation

• notebooklm-grounded-research

  Use when: NotebookLM, notebooklm MCP, large documentation sets, courses, books, papers, or citation-backed research are mentioned. Retrieves a small grounded answer from a stable corpus, preserves citations, and verifies claims against primary documentation, repository code, and tests. Do not use wh

• vlm-segmentation

  Choose and evaluate VLM or segmentation pipelines, including text-conditioned detection, masks, part labels, model-license constraints, and measured GPU deployment choices. Use when a task has a VLM or segmentation component; route pure diffusion prompting, training, or serving to its specialized sk

• feature-new

  Scaffold a feature narrative in an existing project layer with Design, Plan, Verify, and Conclusion sections. Use when: "create a new feature", "start work on feature", "scaffold feature doc", "/feature-new", or "begin feature narrative". Inspects and preserves the target project's feature ID, regis

• harness-design

  Design a scoped multi-agent harness for a requested long-running AI workflow. Preserve the user-approved product boundary while using Generator-Evaluator separation, testable sprint contracts, context management, and task-appropriate validation. Based on Anthropic Engineering patterns. Use when: "bu

• layer-new

  Scaffold a new layer in a project's docs/layers/ tree following the feature-layer architecture (principle 28). A layer is a bounded concern (security, data, ui, infrastructure, domain) with its own invariants, decisions, gotchas, patterns, and feature narratives. Use when: "create a new layer", "add

• plan-swarm-review

  Iterative plan review using multisampling + focused decomposition. Launches parallel independent agents to find issues that single-pass review misses. Up to four bounded rounds: broad, multisample, focused, focused-plus-multisample. Use when: "swarm review", "review plan thoroughly", "multisample re

• pixel-art-storyboard

  Convert short scene descriptions, book/album cover briefs, or 2-paragraph synopses into seamless-loop animated pixel-art covers rendered as self-contained HTML+canvas. Companion skill to pixel-art-studio. Use when the user asks to "make a cover for", "animated book cover", "looped pixel scene", "con

• pixel-art-studio

  Create production-quality pixel art and animations programmatically. Use when the user asks to "create pixel art", "draw a sprite", "make pixel animation", "generate sprite sheet", "convert image to pixel art", "pixelate this image", "make a pixel character", "пиксель арт", "пиксельная графика", "сп

• architecture-first

  Decide module boundaries before the first file: what modules exist, which way dependencies point, who owns state, and what each module may know. Use when starting a project, service, site, API, or subsystem; adding a feature with no obvious home; resolving a circular import or inverted framework dep

• architecture-quality

  Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape. Use when starting or extending a web app, backend, frontend, API or multi-page product; when a change makes

• bug-reproducer

  Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix. Also turn bug reports, stack traces, screenshots, failing behavior, support tickets, and regressions into minimal reproducible cases with red-to-green

• code-complexity

  Keep each unit comprehensible while the code grows: deep modules over shallow ones, information hiding, honest names, small functions with one job, error handling that does not lose the error, DRY and orthogonality, design by contract, and not leaving broken windows. Merges module-complexity managem

• control-cli

  Drive and inspect an interactive CLI or TUI with a repeatable local harness, deterministic input, transcripts, and optional profiling. Use for CLI UX checks, prompt flows, startup regressions, hangs, interrupts, resize behavior, or memory growth. Do not use for a non-interactive command that a norma

• control-ui

  Drive and inspect a local web, IDE, or Electron UI with browser or CDP automation and evidence. Use for UI regressions, screenshots, accessibility snapshots, visual diffs, focus, keyboard, scrolling, resize, console, network, performance, or heap checks. Do not use for backend-only changes or for a

• deep-review

  Parallel competency-based code review. Launches independent Agent reviewers per competency (security, performance, architecture, database, concurrency, error-handling, frontend, testing), each with a focused checklist and isolated context. Synthesizes findings into unified report with FIX/DEFER/ACCE

• deslop

  Remove AI-generated code noise from the current diff while preserving behavior. Use for deslop, AI slop cleanup, unnecessary comments, defensive checks, any casts, or needless nesting after an agent-generated change. Do not use as permission for a broad rewrite or when a real bug has not been isolat

• distill-feedback

  Turn captured user-correction signals into durable rules (learn-from-corrections loop). Use when - /distill-feedback, "process feedback queue", "what corrections did I give you", "encode lessons from my corrections", session-feedback-capture queued sessions, "обнови правила по моим поправкам", "разб

• harness-feedback

  Use when an agent says a test, VM, proof, evaluator, or release gate is overloaded, too strict, blocking staging, or causing false positives; split checks by profile, measure the burden, preserve high-risk evidence, and verify the smallest corrected workflow. Do not use for ordinary test selection,

• proof-verify

  Plan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify their own work). For multi-stage work, seal accepted inputs with commit/tree, contract, input/output digests, and a fresh verdict so downstream

• refactoring-safely

  Change the structure of code that already exists without changing what it does: smells as triggers, the named transformations (extract/inline, move feature, organise data, simplify conditionals), and above all the workflow that makes it safe — characterization tests first, one transformation at a ti

• repo-map

  Ranked symbol map of a codebase within a token budget — a compact "what matters in this repo" before reading files. Use when starting work in an unfamiliar/large codebase, before a refactor or deep-review fan-out, when you need JIT context instead of dumping whole files, or asked "give me a map of t

• root-cause-delivery

  Use for a reported bug, regression, crash, failed workflow, or substantive code change that must reach a verified candidate rather than a local patch. Map the affected layer, freeze a bounded plan, require incident reproduction red-to-green or planned-change contract proof, force re-triage after two

• system-and-data-design

  Decide whether the system will hold, and where the data lives: requirements and load first, then back-of-the-envelope numbers, building blocks (cache, queue, load balancer, CDN), and the data layer in depth — storage engines, indexes, replication, partitioning, transactions and consistency, batch vs

• testing-strategy

  Use when planning or reviewing tests for a code change, choosing between unit, focused regression, integration, contract, end-to-end, performance, security, property-based, or agent-evaluation checks; classify change risk first and select the smallest evidence set that proves the behavior. Do not us

• thermo-nuclear-code-quality-review

  Run an opt-in strict maintainability review for giant files, spaghetti growth, misplaced logic, weak boundaries, unnecessary abstractions, and missed structural simplifications. Use for a thermonuclear review, harsh code-quality audit, code-judo review, or a file approaching 1000 lines. Do not use a

• verify-this

  Prove a concrete behavior, performance, UI, CLI, API, or memory claim with fresh baseline-versus-treatment evidence and one explicit verdict. Use when asked to verify, prove, compare before and after, show evidence, or confirm that a fix works. Do not use for vague claims such as cleaner code, a ful

• workflow-orchestration

  Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов). Use when user просит workflow своими словами или включает ultracode, нужен fan-out на десятки-сотни агентов, codebase-wide аудит/миграция, cross-checked research, competency-review, batch-обработка списка элементов через с

• frontend-design

  Создание высококачественных, визуально выдающихся фронтенд-интерфейсов. Используй ВСЕГДА когда пользователь просит создать веб-страницу, компонент, лендинг, дашборд, UI-кит, форму, карточки, навигацию, анимации, или любой другой веб-интерфейс. Скилл покрывает: HTML/CSS/JS компоненты, React/Vue/Svelt

• motion-framer

  Use when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation. Do not use for static styling, backend/API work, or animation in another runtime unless Motion/Framer Motion is an expli

• ui-design

  Unify product UI design, frontend implementation, and verification. Use when asked to design, redesign, build, or fix a web, desktop, or mobile interface; a page, dashboard, form, component, design system, responsive layout, accessibility, interface animation, or editable hero/banner/infographic wit

• ui-ux-pro-max

  Use when designing, building, reviewing, or fixing a web, mobile, or desktop interface: pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, or stack-specific UI implementation. Do not use for pure backend/API/database/DevOps work or non-visual

• ios-development

  Comprehensive iOS app development skill. Use this skill for ANY iOS-related task: writing Swift/SwiftUI/UIKit code, architecting apps, debugging crashes, setting up navigation, networking, data persistence, animations, performance optimization, App Store submission, Xcode configuration. Trigger when

• lean-code

  On-demand minimalism intensifier — find the smallest sufficient, verified implementation for the requested outcome. Use when the user says "be lazy / yagni / simplest / minimal / shortest / don't over-engineer", complains about bloat / boilerplate / unnecessary dependencies / abstraction, or before

• cross-harness-continuation

  Use when work moves between Claude Code and Codex, a session resumes from a handoff, or an agent may rewrite an existing implementation. Loads the shared CONTINUITY.json contract, preserves accepted decisions, checks Git baseline and scope, and requires explicit replan mode for intentional redesign.

• deepseek-provider-contract

  Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries. Use when integrating DeepSeek, adding DeepSeek tool calls or streaming, debugging DeepSeek 400 after

• desktop-sessions-discovery

  Discover, search, and selectively restore Claude desktop app sessions hidden across multiple accountIds. Use when user mentions "missing sessions after account switch", "lost desktop sessions", "where do my old sessions live", or runs multiple Claude accounts on the same machine. Do NOT use for Clau

• epistemic-challenge

  Use this skill when the user asks the agent not to agree automatically, to challenge an assumption, evaluate a proposal critically, identify counterevidence, or make a high-consequence decision under uncertainty. Separates facts, inference, counterevidence, uncertainty, and a falsifier; do not use f

• gemini-delegate

  Делегирование задач в Gemini CLI с проверкой установленной версии, доступной модели и текущего доступа. Use when - спроси/делегируй gemini, second opinion от другого вендора, bulk-курация картинок/данных, нужен большой контекст на чтение, или диагностируй quota/model ошибку Gemini. НЕ используй для

• harness-audit

  Score a project's agent harness across 5 subsystems (Instructions / State / Verification / Scope / Lifecycle), identify the bottleneck, and produce a prioritized improvement plan. Use when assessing if a project is ready to graduate to [LONG-RUN] status, when an agent keeps failing despite good mode

• observability-monitoring

  Design, audit, and troubleshoot production monitoring and observability using user-impact checks, layered telemetry, USE/RED, SLI/SLO/SLA, error budgets, cardinality controls, actionable alerting, burn-rate response, and postmortems. Use when asked about monitoring, наблюдаемость, алерты, Prometheus

• remote-compute-ops

  Operate GPU and remote compute across RunPod (Pods and Serverless), Massed Compute VMs, and owned or virtual remote servers through existing bridges, SSH sessions, MCP/API adapters, bounded polling, cost controls, and resumable lifecycle checks. Use when the user mentions RunPod, Massed Compute, a r

• plan-to-tickets

  Use when a large plan, PRD, feature, refactor, research plan, or multi-step coding task must be split into small ready-for-agent tickets with acceptance criteria, verification commands, blockers, and vertical tracer-bullet slices. Do not use for small tasks that should be implemented directly, singl

• product-meaning-extractor

  Deep product analysis before creating videos, presentations, or ads. Use when: 'analyze product', 'extract value', 'product brief', 'what makes this product special', 'prepare brief', 'understand the product', 'video brief'. Takes a URL or product description and outputs a structured brief with core

• remotion-production-guide

  Remotion (React video framework) production guide with Apple-style design rules. Use when: 'create video with remotion', 'remotion project', 'render video', 'product demo video', 'animated video', 'video from code'. Covers project setup, animation library, spring presets, typography rules, color pal

• script-evaluator

  Evaluate video scripts and presentations for flatness, tension, and emotional impact. Use when: 'is this script good', 'review script', 'evaluate video', 'why is this boring', 'flatness check', 'script review', 'improve script', 'rate this video'. Scores 6 dimensions (tension, specificity, emotional

• video-narrative-arc

  Proven narrative arc templates for product videos and ads. Use when: 'write script', 'video structure', 'narrative arc', 'scene plan', 'storyboard', '15 second video', '30 second video', '60 second video', 'how to structure the video', 'video script template'. Provides beat-by-beat templates with ti

• video-post-production

  Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master audio', 'export settings', 'platform requirements'. Covers FFmpeg patterns, audio chain, subtitle standa

• article-structure-review

  Проверить структуру технической статьи после черновика: задача читателя, жанр, опора значимых утверждений на доказательства и честные ограничения. Use after the first draft, before publication. Исправлять структуру, когда это входит в запрос; не создавать обязательный конвейер из других навыков. Для

• caveman

  Ultra-compressed reply mode. Cuts output tokens ~65-75% by answering in terse "caveman" style while keeping full technical accuracy, and shapes what survives: action first, state restated every turn, concrete time estimates, visible wins. Intensity levels: lite, full (default), ultra, wenyan-lite, w

• humanize-english

  Edit English drafts for clear, natural language while preserving facts, uncertainty, technical meaning, citations and genre. Use when: humanize this text, remove AI-style filler, improve English prose, or edit an English article before publication. Not an authorship detector or a promise to bypass o

• humanize-russian

  Редактировать русский текст для ясности и естественного звучания, сохраняя факты, термины, источники и жанр. Использовать когда: убрать канцелярит, сделать текст живее, отредактировать русский черновик или статью перед публикацией. Не определяет авторство и не обещает обход детекторов. Для английско

• owner-voice

  Пишет и редактирует текст голосом владелицы — сообщение, письмо, пост, объяснение, урок, рабочий разбор, на русском и английском. Use when: «напиши от моего лица», «в моём стиле», «моим голосом», «отредактируй, чтобы звучало как я», «перепиши по-человечески от меня», «напиши письмо/пост/сообщение за

Subagents (8)

• ci-watcher

  Watch PR checks for the current branch and report pass/fail with relevant links and concise next steps. Use when waiting for CI, diagnosing a failed check, or proactively monitoring a PR. Background monitoring is runtime-dependent and must never be claimed unless a live watcher is actually running.

• pixel-art-animation-reviewer

  Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing",

• pixel-art-composition-reviewer

  Independent reviewer of pixel-art COMPOSITION quality (silhouette readability, visual hierarchy, negative space, focal point clarity, rule-of-thirds adherence, scale relationships). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check com

• pixel-art-interaction-reviewer

  Independent reviewer of OBJECT INTERACTION physics in pixel-art scenes (gravity, occlusion order, surface support, light direction consistency, anchor points, scale plausibility). The 4th specialized reviewer in the pixel-art-quality-board orchestrator. Use when the user asks "do objects interact co

• pixel-art-quality-board

  Orchestrator agent that runs 4 specialized pixel-art reviewers in parallel (style + animation + composition + interaction), then synthesizes their verdicts into a single PASS/NEEDS_WORK/REJECT decision with prioritized fixes. Use when the user asks to "review my pixel art quality", "score this anima

• pixel-art-reviewer

  Use when the user generated pixel art and wants an independent quality review, or when the pixel-art-studio skill has produced output that needs to be evaluated before delivering. Performs Generator-Evaluator review: runs quality_check.py, reads the rendered PNG with fresh context (does not see how

• pixel-art-style-reviewer

  Independent reviewer of pixel-art STYLE quality (palette discipline, surface detail, layer depth, retouch-style adherence). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check style of pixel art", "is this pixel art retouch-quality", "ve

• thermo-nuclear-code-quality-review

  Independent strict maintainability reviewer for a collected diff and changed-file contents. Use the matching thermo-nuclear-code-quality-review skill as the complete rubric; do not modify code or spawn nested reviewers.

Hooks (22)

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PreToolUse

  python

• PostToolUse

  python

• PostToolUse

  python

• Stop

  python

• SessionStart

  python

• SessionStart

  python

• SessionStart

  python

• SessionStart

  python

Similar plugins