AnastasiyaW

60 mods across 1 repository, 147 stars between them.

AnastasiyaW/codex-claude-code-config

Plugin Claude Code

Battle-tested configuration system for Claude Code agents: architectural principles, safety hooks, composable skills, review agents, alternative comparisons, and project templates. Includes proof, handoff, feedback, UI/CLI harness, architecture, and multi-session coordination patterns.

147 7d ago A tokens not measured original MIT

ci-watcher

04

AnastasiyaW/codex-claude-code-config

Agent

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.

147 7d ago A 59 tokens original MIT

AnastasiyaW/codex-claude-code-config

Agent

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", "verify loop…

147 7d ago A 140 tokens original MIT

AnastasiyaW/codex-claude-code-config

Agent

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 composition", "is this…

147 7d ago A 137 tokens original MIT

AnastasiyaW/codex-claude-code-config

Agent

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 correctly", "is…

147 7d ago A 156 tokens original MIT

AnastasiyaW/codex-claude-code-config

Agent

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

147 7d ago A 163 tokens original MIT

pixel-art-reviewer

09

AnastasiyaW/codex-claude-code-config

Agent

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 qualitycheck.py, reads the rendered PNG with fresh context (does not see how the art was made)…

147 7d ago A 138 tokens original MIT

AnastasiyaW/codex-claude-code-config

Agent

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", "verify palette…

147 7d ago A 129 tokens original MIT

AnastasiyaW/codex-claude-code-config

Agent

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.

147 7d ago A 46 tokens original MIT

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

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 model, streaming…

147 7d ago A 195 tokens original MIT

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

A practical engineering guide to diffusion models, which generate or edit images by gradually removing noise. It covers model architectures, sampling controls, training methods, text encoders, memory use, evaluation, and debugging.

147 7d ago A 287 tokens original MIT

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

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 any mention of…

147 7d ago B 218 tokens original MIT

flux2-lora-training

15

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

Comprehensive reference for training LoRAs on FLUX.2 Klein 9B and Qwen Image Edit 2511 models. Use this skill whenever the user asks about: training LoRAs for flux2/flux 2 klein/qwen-image-edit, before/after edit LoRAs (head swap, face swap, image editing), inpainting LoRAs, training at larger resolutions, latent…

147 7d ago A 242 tokens original MIT

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

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-E, or any diffusion…

147 7d ago A 218 tokens original MIT

ml-research-lab

17

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

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 explanations, or…

147 7d ago A 96 tokens original MIT

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

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 when: the answer is…

147 7d ago A 91 tokens original MIT

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

An engineering guide for using vision-language models, object-segmentation models, and image-generation models on GPUs. Segmentation means identifying the exact pixels belonging to objects, while vision-language models connect images with text.

147 7d ago B 371 tokens original MIT

feature-new

20

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

Scaffold a new feature narrative document in an existing layer following the ULTRAPACK-style template extended for feature-layer architecture (principle 28). Creates docs/layers/ /features/feat-NNN- .md with Design / Plan / Verify / Conclusion sections, populates layer README features table, and adds entry to…

147 7d ago A 156 tokens original MIT

harness-design

21

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

Design and build multi-agent harness architectures for long-running AI application development. GAN-inspired Generator-Evaluator pattern, Sprint Contract negotiation, context management, quality criteria calibration. Based on Anthropic Engineering patterns. Use when: "build a harness", "multi-agent architecture"…

147 7d ago A 171 tokens original MIT

layer-new

22

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

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 security layer"…

147 7d ago A 150 tokens original MIT

plan-swarm-review

23

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

Iterative plan review using multisampling + focused decomposition. Launches parallel independent agents to find issues that single-pass review misses. 4 escalating rounds: broad -> multisample -> focused -> focused+multisample. Use when: "swarm review", "review plan thoroughly", "multisample review", "deep plan…

147 7d ago A 172 tokens original MIT

AnastasiyaW/codex-claude-code-config

Skill Claude CodeCodex

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", "convert this story…

147 7d ago A 303 tokens original MIT