Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cacr92/wereply/python-agent-developmentnpx skills add cacr92/WeReply --skill python-agent-developmentgit clone --depth 1 https://github.com/cacr92/WeReplyWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00038 | $0.02373 |
| Opus 5 | $0.00019 | $0.01187 |
| Sonnet 5 | $0.00008 | $0.00475 |
| Haiku 4.5 | $0.00004 | $0.00237 |
Grade A, and why
python-agent-development scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Agent Development Skill (Windows)
Expert guidance for developing Windows Platform Agent using Python 3.12 + wxauto v4.
Project Structure
platform_agents/windows_agent/
├── agent.py # 主入口
├── wechat_monitor.py # 微信监听模块
├── input_writer.py # 输入框控制模块
├── ipc/ # IPC 通信模块
│ ├── message_sender.py
│ └── command_receiver.py
├── utils/ # 工具模块
│ ├── logger.py
│ └── config.py
├── requirements.txt # 依赖列表
├── tests/ # 测试目录
│ ├── test_monitor.py
│ └── test_writer.py
└── README.md
Dependencies (requirements.txt)
wxauto==4.0.0
pywin32>=305
Main Entry Point
# agent.py
import sys
import time
from wechat_monitor import WeChatMonitor
from input_writer import WeChatInputWriter
from ipc.message_sender import MessageSender
from ipc.command_receiver import CommandReceiver
class WindowsAgent:
def __init__(self):
self.monitor = WeChatMonitor(interval_ms=500)
self.input_writer = WeChatInputWriter()
self.command_receiver = CommandReceiver()
self.setup_command_handlers()
def setup_command_handlers(self):
"""注册命令处理器"""
self.command_receiver.register_handler("WriteInput", self.handle_write_input)
self.command_receiver.register_handler("ClearInput", self.handle_clear_input)
self.command_receiver.register_handler("HealthCheck", self.handle_health_check)
self.command_receiver.register_handler("Stop", self.handle_stop)
def handle_write_input(self, command):
content = command.get('content', '')
success = self.input_writer.write_to_input(content)
return success
def handle_clear_input(self, command):
success = self.input_writer.clear_input()
return success
def handle_health_check(self, command):
MessageSender.send_health_status("ok", "windows_wxauto")
return None # 不发送 CommandResponse
def handle_stop(self, command):
self.command_receiver.stop()
return True
def run(self):
"""启动 Agent"""
try:
# 启动命令监听(后台线程)
self.command_receiver.start_listening_async()
# 启动微信监听(主线程)
self.monitor.start_monitoring()
except KeyboardInterrupt:
MessageSender.send_error("Agent 被用户中断")
except Exception as e:
MessageSender.send_error(f"Agent 运行错误: {str(e)}")
finally:
sys.exit(0)
if __name__ == '__main__':
agent = WindowsAgent()
agent.run()
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 419 lines · 38 tokens per session scan A 13f113c3030e
python-agent-development is a skill published in the GitHub repository cacr92/WeReply (5 stars, last pushed 7mo ago), licensed MIT. It adds 38 tokens to every session and 2,373 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…