Instructions file CodexOpenCode
AGENTS.md instructions for voidful/hung-yi-lee-skill, covering hung-yi lee llm wiki schema, layers, 1. raw sources, 2. wiki and 3. schema.
1.3k
+10 22d ago A 843 tokens
hung-yi-lee
02Skill Claude CodeCodex
A teaching skill for machine learning, deep learning, generative AI, large language models, AI agents, and speech modeling, using a structured, intuition-first approach.
1.3k
+10 22d ago A 84 tokens
Skill Claude CodeCodex
Scaffold a new Harbor benchmark adapter by running harbor adapter init and then guide implementation using the Adapters Agent Guide as the authoritative spec.
695
+5 5d ago A 34 tokens
copy · 92% Apache-2.0
publish
04Skill Claude CodeCodex
Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.
695
+5 5d ago A 35 tokens
copy · 95% Apache-2.0
rewardkit
05Skill Claude CodeCodex
Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.
695
+5 5d ago A 46 tokens
copy · 91% Apache-2.0
Instructions file CodexOpenCode
Instructions for rhein1/fable5-codex, covering fable-5 repo instructions, working method and package rules.
2 12d ago A 372 tokens
original MIT
fable-audit
07Skill Claude CodeCodex
Evidence-first codebase audit for correctness, security, privacy, data, integration, operational, test, and docs-vs-reality risks. Use when the user asks for a Fable-5 audit, exhaustive audit, bug hunt, risk review, codebase audit, security/integration audit, or asks Codex to find issues before changing code.
2 12d ago A 75 tokens
original MIT
Skill Claude CodeCodex
Fable-5 deep code review for pull requests, branches, diffs, or proposed patches. Use when the user asks for deep review, PR review, branch review, review comments, regression review, or independent verification of a change.
2 12d ago A 54 tokens
original MIT
Skill Claude CodeCodex
Claim-by-claim verification of docs, status reports, launch claims, changelogs, READMEs, runbooks, and "done/tested/working/live" assertions against source, tests, artifacts, and runtime evidence. Use when the user asks Codex to fact-check, verify claims, audit truthfulness, or compare docs to reality.
2 12d ago A 76 tokens
original MIT
podlayer/message-drop-sentinel
Plugin Claude Code
Detects Claude Code's silent mid-turn message drops and provides a delivery channel the bug can't touch.
1 27d ago A
tokens not measured
original MIT
SessionStart
11podlayer/message-drop-sentinel
Hook
Runs when a session starts, executing hook.mjs via node. From podlayer/message-drop-sentinel.
1 27d ago A
tokens not measured
copy · 55% MIT
Stop
12podlayer/message-drop-sentinel
Hook
Runs when the agent finishes a response, executing hook.mjs via node. From podlayer/message-drop-sentinel.
1 27d ago A
tokens not measured
copy · 48% MIT
PostToolUse
13podlayer/message-drop-sentinel
Hook
Runs after a tool call finishes for Bash tool calls, executing relay.mjs via node. From podlayer/message-drop-sentinel.
1 27d ago A
tokens not measured
original MIT
At most 3 mods per repository are shown here — the rest are on their repository pages: