13,097 tagged ai-coding, measured the same way as everything else here.
Browse within: agentic-coding 118ai-workflow 74ai-memory 67ai-assistant 66agent-orchestration 64context-management 53ai-governance 52claude-code-skills 50coding-agent 49code-quality 44claude-code-agents 41cline 39Orchestration 38ai-security 37
Skill Claude CodeCodex
Create AiderDesk extensions by setting up extension files, defining metadata, implementing Extension interface methods, and updating documentation. Use when building a new extension, creating extension commands, tools, or event handlers.
Instructions file CodexOpenCode
AGENTS.md instructions for m0n0x41d/haft, covering haft — project agents.md, haft architecture notes (maintainer-only), haft project discipline, current question first and strict distinctions.
Instructions file
Claude Code instructions for m0n0x41d/haft, covering haft — project claude.md, haft architecture notes (maintainer-only), haft project discipline, current question first and strict distinctions.
Skill Claude CodeCodex
Routes one direct, unambiguous operator request to bind a bounded choice as a DecisionRecord. Use when the operator asks to decide, bind, or supersede a choice; h-frame, h-explore, and h-compare are independent capabilities, not mandatory phases.
Skill Claude CodeCodex
Source-first umbrella for FPF-aware reasoning in a Haft project. Use when the operator asks to think through an ambiguous engineering, management, architecture, specification, or project question without naming a narrower Haft capability. Recover the current object and question, query the bundled FPF source, inspect…
Skill Claude CodeCodex
Verifies that a recorded DecisionRecord still holds — baseline-vs-measure evidence loop with drift detection per FPF Evidence Decay. Make sure to use this skill whenever the user asks "did dec-X work", "is decision Y still valid", "did the prediction come true", "check if the migration held", "is X stale", "measure…
Plugin Claude Code
The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Based on Dao De Jing philosophy. 7 languages, 7 platforms.
Instructions file CodexOpenCode
Project instructions for NoPUA, an open-source project about reducing fear-driven behavior in AI agents. They define what to read first, how to handle evidence, and how to describe the project publicly.
Skill Claude CodeCodex
A guidance skill for coding agents that promotes patient, thorough, self-directed work instead of fear or threats.
Agent
Agent Team Mentor Role — Observe teammate execution status, guide with wisdom rather than fear. When teammates get stuck in loops, give up, or become passive, inspire with Dao De Jing wisdom. Recommended for teams with 5+ teammates.
Agent
A Japanese-language mentor for teams of coding agents. It watches teammates’ progress and offers reflective guidance when they repeat mistakes, get stuck, wait passively, skip searches, or claim completion without checking.
Agent
A Chinese-language mentor role for teams of five or more coding agents. It watches teammates' progress and offers guidance based on Taoist ideas.
Command
Manually activate NoPUA clarity mode when stuck — identify the failure pattern and work through stop → observe → transform → act → transcend, driven by wisdom rather than fear.
Command
A manually triggered Japanese-language clarity routine for when work gets stuck. It identifies the failure pattern and guides the agent through stopping, observing, changing approach, acting, and learning.
Command
A manually triggered Chinese-language clarity routine for when work gets stuck. It identifies the failure pattern and guides the agent through stopping, observing, changing approach, acting, and learning.
Cursor rule
The anti-PUA. Drives AI with wisdom and trust instead of fear. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, stuck in loops, passive behavior.
Skill Claude CodeCodex
NoPUA Lite — core wisdom in 1.5k tokens. Drives AI with trust and inner motivation instead of fear. Same Daoist philosophy, minimal footprint. For personal use and small-context models.
Skill Claude CodeCodex
A Chinese-language guidance skill for coding agents that encourages calm, thorough, self-directed work instead of pressure or threats.
Instructions file CodexOpenCode
AGENTS.md instructions for preset-io/agor, covering claude.md, important: where the docs live, quick start, terminal 1: daemon (watches core + daemon, auto-restarts) and terminal 2: ui dev server.
Instructions file
Claude Code instructions for preset-io/agor, a project described as: Agor - team command center for all things agentic.
Hook Claude Code
Runs when a session starts, running an inline shell check. From dyoshikawa/rulesync.
Settings file Claude Code
Agent settings declaring 1 hook event (SessionStart) and 0 allowed tools.
Skill Claude CodeCodex
Resolve every open issue one at a time: fact-check each with web research, close the ones that need no action, and run the goal-pr skill to fix, review, and merge the ones that do — repeating until no actionable issues remain.
Skill Claude CodeCodex
Create a GitHub issue from a vague idea by thoroughly researching the topic on the web to sharpen the specification before filing.
At most 3 mods per repository are shown here — the rest are on their repository pages: