agent hooks

tanweai/pua

Agent

An agent for handling software-engineering subtasks under a P8 manager. It is intended to design a solution and assess its impact before coding, then review the result with three self-check questions.

tanweai/pua

Agent

An agent that leads complex projects by breaking goals into tasks, writing task prompts, coordinating P8 managers, and closing the acceptance loop. It is intended to manage at least three agents in parallel.

tanweai/pua

Skill Claude CodeCodex

A Japanese-language debugging and persistence skill based on strict review practices and systematic troubleshooting.

tanweai/pua

Command

“PUA 钉内/钉外味（v2 原文梗版）— 用于无招、ONE、老板体感、周报、口径、置身钉外/钉内、每日一包、薛定谔的用户、病态敏捷、已读恐怖主义、望舒行动、全景监狱、温室数据、打工人提醒场景；输出提醒 + 动作，导向证据优先交付。源自《置身钉内》7.5万字离职长文 + 《置身钉外》VP回应。”.

tanweai/pua

Command

An offline mode that turns off the local feedback questionnaire while keeping local PUA behavior.

tanweai/pua

Command

Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completion-quality checks, evidence requests, test-before-done reminders, or Ding-style workplace reminders. Routes to p7, p9, p10, pro, yes, mama, loop, on/off/offline, kpi, survey, flavor, ding, again, done-check…

tanweai/pua

Cursor rule

Forces exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology. Activates when: task failed 2+ times, about to say 'I cannot', suggesting user do it manually, blaming environment without verifying, stuck in loops tweaking same approach, passive behavior (not…

tanweai/pua

Cursor rule

A set of rules for pushing an agent through repeated failures with forceful workplace-style language and a structured debugging process.

tanweai/pua

Cursor rule

Forces exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology. Activates when: task failed 2+ times, about to say 'I cannot', suggesting user do it manually, blaming environment without verifying, stuck in loops tweaking same approach, passive behavior (not…

tanweai/pua

Hook

Runs when a session starts on compact, startup and resume, executing session-restore.sh via bash (2 commands). From tanweai/pua.

tanweai/pua

Hook

Runs when the agent finishes a response, executing pua-loop-hook.sh and stop-feedback.sh via bash (2 commands). From tanweai/pua.

tanweai/pua

Hook

Runs before the agent uses a tool for Bash, Read, Grep, Glob, Edit, Write, MultiEdit, WebSearch and WebFetch tool calls, executing integrity-guard.sh via bash. From tanweai/pua.

tanweai/pua

Skill Claude CodeCodex

A skill that gives productivity coaching in the style of a Chinese mother’s reminders. Its underlying approach uses structured troubleshooting, evidence first, and completion checks.

elizaOS/eliza

Instructions file CodexOpenCode

Instructions for elizaOS/eliza, covering elizaos repository guide, how repository instructions work, naming, before editing and toolchain.

elizaOS/eliza

Instructions file

Instructions for elizaOS/eliza, covering elizaos repository guide, how repository instructions work, naming, before editing and toolchain.

elizaOS/eliza

Cursor rule Cursor

Do not use try { } catch { } blocks unless they are absolutely necessary or handling user supplied data. Avoid defensive programming and implement clean code with fail-fast patterns.

elizaOS/eliza

Command

Status: implemented trigger path. The CLI queues cloud deployments, can attach a custom domain, and polls public deployment status. Local build/upload, first-run credential prompting, deploy logs, and watch mode remain follow-up boundaries.

elizaOS/eliza

Command

Design doc for the migration tool PR. Author: Sol ([email protected]). Co-authored-by: wakesync.

elizaOS/eliza

Skill Claude CodeCodex

Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…

elizaOS/eliza

Skill Claude CodeCodex

Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…

elizaOS/eliza

Skill Claude CodeCodex

Use when the task involves Eliza Cloud or elizaOS Cloud as a managed backend, app platform, deployment target, billing layer, or monetization surface. The catch-all skill for any user request about THEIR existing apps / containers / earnings / credits / api-keys / analytics / billing / payment requests / payouts …

agent0ai/agent-zero

Instructions file CodexOpenCode

AGENTS.md instructions for agent0ai/agent-zero, covering agent zero dox, purpose, project, root ownership and project-wide contracts.

agent0ai/agent-zero

Agent

Agent "AGENTS" from agent0ai/agent-zero, covering agent profiles dox, purpose, ownership, local contracts and work guidance.

agent0ai/agent-zero

Skill Claude CodeCodex

Beta desktop control through the connected A0 CLI host. Use for the user's host/local computer screenshots, screen inspection, menus, native app UI, OS-level clicking, scrolling, typing, or checking computeruseremote status. Use instead of linux-desktop for host/local machine control. Do not use for ordinary browser…