Skill Claude CodeCodex
A short premortem planning session that asks what could make a plan fail before work begins. It examines a plan from several viewpoints, suggests responses, and records the discussion in the project documentation.
Skill Claude CodeCodex
Use Google Gemini for image generation, text chat, file analysis, URL/YouTube analysis, and multi-turn conversations via MCP. Triggers on requests to generate images with Gemini, chat with Gemini, analyze files/URLs/videos with Gemini, use Gemini models, or when user asks to create/edit images and needs prompting…
Skill Claude CodeCodex
Complete VPN server setup from scratch — takes a fresh VPS (IP + root password from the hosting provider) through full server hardening and a 3x-ui (Xray) install with two VLESS+Reality inbounds (XHTTP for best DPI resistance, TCP+Vision for iOS), delivered as one subscription link and connected via the Happ client.…
Plugin Claude Code
Tech-lead orchestration for Claude Code. The expensive model decides, the cheap models type.
Plugin Claude Code
Tech-lead orchestration mode: the top-tier model keeps architecture and decisions, a role roster of cheaper subagents does the implementation, the routine, the digging and the review. Save tokens without losing quality.
Agent
Long, context-heavy investigations that would pollute the main context - exploring a large slice of a codebase, grinding through logs, multi-file debugging, background research. Returns a distilled conclusion, not raw material. Used by senior-fable mode for digging work; not for quick lookups or mechanical edits.
Agent
Mechanical, well-specified execution - writing tests to a spec, boilerplate, formatting, renames, simple edits with a clear definition of done. Not for design decisions, ambiguous requirements or investigations. Used by senior-fable mode for routine work.
Agent
Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable mode for the code the lead specifies but does not type. Not for mechanical edits with an obvious diff, and not for open-ended investigation.
Agent
Independent review of work someone else finished - a diff, a feature, a migration. Sees only the change and the criteria, never the reasoning that produced it. Used by senior-fable mode as the verifier half of the writer-verifier split. Not for reviewing your own work, and not for open-ended code exploration.
Skill Claude CodeCodex
Tech-lead orchestration for a session on your top-tier model: the lead keeps decomposition, architecture and final synthesis, and routes implementation, mechanical work and long investigations to cheaper subagents. Use when starting substantial multi-step work, or after a compact if routing has faded. Do NOT use for…
Skill Claude CodeCodex
Generate images with Google Imagen 4 and Nano Banana for free via Flow API. No API key, no paid subscription — just a Google account and Chrome extension. Use when the user asks to generate, create, or make an image, picture, illustration, logo, banner, or avatar. Triggers: generate image, create picture, make…
AndyShaman/telegram-business-bridge
Instructions file CodexOpenCode
Instructions for AndyShaman/telegram-business-bridge, covering telegram-business-bridge — instructions for the ai agent, two-layer memory, contact dossiers, tools and reply rules.
AndyShaman/telegram-business-bridge
Instructions file
Instructions for AndyShaman/telegram-business-bridge, covering telegram-business-bridge, active feature branch, session-start rule and ветки.
Instructions file CodexOpenCode
Instructions for AndyShaman/Soroka, covering agents.md — deployment protocol for ai agents, required values from the user, deployment, hand-off and diagnostics.
Instructions file
Instructions for AndyShaman/Soroka, covering soroka and session-start rule.
MCP server Claude CodeCodexCursor +2
MCP server "soroka" as configured in AndyShaman/Soroka. Runs locally from the soroka Python package.