367 tagged codex-cli, measured the same way as everything else here.
Browse within: codex-plugin 182ai-governance 177architecture-governance 177arckit 177codex-extension 177cli 118gemini-cli 80agent-orchestration 62coding-agents 47skills 46agents-md 45cursor 45ai-skills 37bun 36
Untrivial-ai/agent-orchestrator
Command Claude Code
Inspect and control the current AO session's target-isolated browser. The desktop app must be open. The agent and user share the same live page, cookies, navigation state, and WebContentsView; the runtime remains usable while the Browser panel is hidden, except for commands that need the page to be painted (see…
ZIB-IOL/The-Agentic-Researcher
Command Claude Code
Reflect on the current research session and collect improvement suggestions.
Command Claude Code
Regenerate the demo animation for the README.
Command Claude Code
A command that explicitly sends a coding task to a DeepSeek sub-agent, an additional AI worker, instead of letting the main agent decide whether to delegate it.
Command Claude Code
Scan a project and suggest domain-expert skills it would benefit from, then draft the ones the user picks.
Command Claude Code
Generate MOD JSP 936 AI assurance documentation for defence AI/ML systems.
Command Claude Code
Search prior work to add context to a request, or browse previous sessions on a topic. Use before/after a request to ground it in past work, or standalone to recall and familiarize before asking.
Command Claude Code
Here’s a prompt to humanise AI essays and text. You can also append your writing sample to further teach ChatGPT to sound more like you.
Command Claude CodeOpenCode
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
Command Claude Code
Resume DMB context for this session.
Command Claude Code needs its repo
Check, configure, start, or install the local Codex quota guard.
Command Claude Code
Run a bounded, Claude-Code-style coding loop with onboarding helpers like --doctor, --demo, and shorthand budgets like 10m.
Command Claude Code
A guided interview for filling a MYLIFE vault with information about your personality, surroundings, money, work, and relationships. Astrology and birth-chart details are optional.
Command Claude Code
You are the Gate System controller. Execute quality gate reviews based on the user's request.
Command Claude Code
Plans, implements, reviews, and finalizes a thread in a single run without requiring prior setup.
Command Claude Code
Instructions for generating AI videos in Genspark from a written scene description, with optional settings such as format, quality, length, sound, and source images.
Command Codex
This prompt is specific to the codexshell project.
RaNDoM6913/claude-code-superkit
Command Claude Code
Full-stack development orchestrator — always-on, 16 phases (0–15): read-docs → understand → architect → pseudocode → plan → contract → validate → implement → evaluate → verify → test → goals → review → critic → document → report.
Command Claude Code
A four-step interview that helps a new user initialise a LifeOS vault, a collection of personal notes and files. It creates Identity.md and Soul.md and replaces placeholders throughout the vault.
Command Claude Code
Iteration delivery — delivery check + archive + commit & tag + bump version.
Command Claude Code
Smart conventional commit with security validation, branch flow enforcement, and auto-detection. Use for git commit, commit changes, save work, stage and commit.
Command Claude Code
Execute one dependency-safe routed wave through Claude Code and BoundedRelay.
Command Claude Code
Analyse une demande ou tache decrite dans un fichier ask sans modifier le code source. Produit une analyse detaillee avec table QA dans .notes/claude/outs/.
Command Claude Code
Get a second opinion from OpenAI Codex and have the codex-advisor subagent check it critically against the code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: