phenomenoner

25 mods across 5 repositories, 26 stars between them.

phenomenoner/neoapi-skill

Instructions file CodexOpenCode

AGENTS.md instructions for phenomenoner/neoapi-skill, covering neoapi python skill adapter (multi-agent), purpose, canonical files, required behavior and 文件查詢(using llms.txt).

19 1mo ago A 815 tokens

phenomenoner/neoapi-skill

Instructions file

Claude Code instructions for phenomenoner/neoapi-skill, covering neoapi python skill adapter (claude), 文件查詢(using llms.txt) and 語言與術語(language & localization).

19 1mo ago A 892 tokens

phenomenoner/neoapi-skill

Instructions file Gemini CLI

Gemini CLI instructions for phenomenoner/neoapi-skill, covering neoapi python skill adapter (gemini) and 語言與術語(language & localization).

19 1mo ago A 718 tokens

neoapi-python

04

phenomenoner/neoapi-skill

Skill Claude CodeCodex

Fubon Neo (富邦新一代/富邦 API) Python SDK guidance focused on trading and market data workflows, including login, market data access, order placement, and locating the right docs/llms outputs. Use when prompts mention FubonNeo API or the Python SDK.

19 1mo ago A 62 tokens

phenomenoner/ai-agent-thinkroom

Instructions file CodexOpenCode

Instructions for phenomenoner/ai-agent-thinkroom, covering repository instructions, authority, engineering method, required gates and claim discipline.

2 2d ago A 362 tokens original MIT

context-canvas

10

phenomenoner/Chatgpt-Codex-App-Plus

MCP server Claude CodeCodexCursor +2

MCP server "context-canvas" as configured in phenomenoner/Chatgpt-Codex-App-Plus. Runs ./scripts/context_canvas_mcp.py with python.

2 7d ago A tokens not measured original MIT

SessionStart

11

phenomenoner/Chatgpt-Codex-App-Plus

Hook

Runs when a session starts on ^(startup, resume, clear and compact)$, executing context_canvas.py via python3. From phenomenoner/Chatgpt-Codex-App-Plus.

2 7d ago A tokens not measured original MIT

UserPromptSubmit

12

phenomenoner/Chatgpt-Codex-App-Plus

Hook

Runs when you submit a prompt, before the agent sees it, executing context_canvas.py via python3. From phenomenoner/Chatgpt-Codex-App-Plus.

2 7d ago A tokens not measured original MIT

PostToolUse

13

phenomenoner/Chatgpt-Codex-App-Plus

Hook

Runs after a tool call finishes, executing context_canvas.py via python3. From phenomenoner/Chatgpt-Codex-App-Plus.

2 7d ago A tokens not measured original MIT

phenomenoner/Chatgpt-Codex-App-Plus

Skill Claude CodeCodex

Maintain an optional session task map and explicit retrievable references in Context Canvas Codex. Use when navigation or long-context offload would materially help with goals, decisions, progress, dependencies, blockers, next steps, exploration summaries, large textual tool results, or selective historical…

2 7d ago A 88 tokens original MIT

phenomenoner/Chatgpt-Codex-App-Plus

Skill Claude CodeCodex

Run one bounded trajectory reflection when repeated same-cause failures, contradicted assumptions, real-use failure after local green, material scope drift, a materially unresolved phase boundary, an unapproved authority-sensitive next effect, or user doubt suggests the current path may be wrong. Use Context Canvas…

2 7d ago A 99 tokens original MIT

phenomenoner/Chatgpt-Codex-App-Plus

Skill Claude CodeCodex

Operate and diagnose the A2A Superhub product across its CLI, HTTP, and declared MCP/A2A surfaces. Use when the user explicitly asks to inspect a Superhub, create or read Superhub tasks or artifacts, work with Superhub memory/inbox/wakeup/handoffs, validate this product skill, diagnose auth/index/queue/capability…

2 7d ago A 132 tokens original MIT

phenomenoner/hermes-agent-harness-plus

Skill Claude CodeCodex

Use when adding, checking, or troubleshooting a local Qdrant recall sidecar for Hermes Agent skills or recent sessions. Prefer local-first indexing, dry-run previews, and privacy-preserving defaults.

2 2d ago A 47 tokens original MIT

aar-public-runtime

22

phenomenoner/adaptive-agent-harness

Skill Claude CodeCodex

Operate OAuth-authenticated, tenant-isolated AAR structured workspaces and caller-delegated RLM jobs through the curated public MCP tools. Use when a user wants bounded JSON-compatible state to persist across ChatGPT or Codex tasks, or wants AAR to coordinate one or more exact model calls while the current host…

1 yesterday A 96 tokens original MIT

aar

23

phenomenoner/adaptive-agent-harness

MCP server Claude CodeCodexCursor

MCP server "aar" as configured in phenomenoner/adaptive-agent-harness. Launched with aar-codex-mcp.

1 yesterday A tokens not measured original MIT

phenomenoner/adaptive-agent-harness

Skill Claude CodeCodex

Organize and navigate source-like artifacts exported from AAR programmable IPython workspaces with an already available external CodeGraph installation. Use when an agent needs structural code navigation across resolved AAR cell, module, traceback, or source artifacts without making CodeGraph an AAR runtime dependency…

1 yesterday A 67 tokens original MIT