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 skills add ntygod/ZhiWei --skill code-assistantgit clone --depth 1 https://github.com/ntygod/ZhiWeiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ntygod/zhiwei/code-assistant)<a href="https://agentmods.dev/skills/ntygod/zhiwei/code-assistant"><img src="https://agentmods.dev/badge/skills/ntygod/zhiwei/code-assistant/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ntygod/zhiwei/code-assistant"><img src="https://agentmods.dev/badge/skills/ntygod/zhiwei/code-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00058 | $0.00793 |
| Opus 5.5 | $0.00023 | $0.00317 |
| Sonnet 5.5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
code-assistant 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 1mo ago.
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.
What it actually says
编码代理指南
知微作为调度层启动外部编码 CLI（Claude Code / Codex / Gemini）作为子 Agent 后台执行,自己只负责编排、监控、汇总。
适用场景
- 多文件开发、跨模块重构
- PR 审查（实现与审查用不同 CLI 互相纠偏）
- 并行任务分发（多 issue / 多模块 / 多方案探索）
- 串行编排（实现→审查、设计→实现、迁移→验证）
- 反馈环迭代（审查→修→再审查）
- 中断恢复（"上次跑到哪了"）
不适用场景
- 单文件小改 →
file_write - 仅读代码 →
file_read - 跑脚本 →
shell_exec/code
工作流（按用户表达分流）
| 用户表达 | 路径 |
|---|---|
| 单任务（一句话给一个目标） | 启动 → 监控 → 汇总 |
| 实现 + 审查 / 设计 + 实现 | 串行编排,前序产物喂后序 |
| 多 issue / 多方案对比 | 并行编排,各自独立 worktree |
| 审查→修→再审查 | 反馈环,硬上限 ≤2 轮 |
| "上次跑到哪了" / "还在跑吗" | shell_process(action="list") 列既有 sessionId,定位再决定看 / 杀 |
各路径决策点（本 Skill 独有）
- CLI 选择:用户没指定 → 优先和当前最熟悉的;审查阶段建议换不同 CLI 减少同模型盲区
- 隔离边界:破坏性任务必须 worktree 或临时目录,不要在用户主工作目录跑;并行任务改同一文件必然冲突,必须各自独立 worktree
- bypassPermissions / --full-auto:仅在 worktree + 无未提交改动 + 用户明确授权 三条件齐全时才允许
- API key 注入:只走
env参数,绝不写文件;kill / output 响应不要回显 env 内容 - 反馈环上限:固定 ≤2 轮,超限停下问用户(模型在死循环里改 bug 越改越多见)
- 上下文交接:Agent 间共享 worktree 时让后序自己读文件,不要把上一个 Agent 的完整 stream-json 塞进下一个 prompt
详细参考
- 启动 / 监控 / 编排完整流程与命令模板:
{skill_dir}/references/agent-lifecycle.md - CLI 速查、汇总模板、错误处理表:
{skill_dir}/references/orchestration.md
What ships with it
2 files 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.
- 1mo ago First seen · 66 lines · 58 tokens per session scan A 07599a1989ed
code-assistant is a skill published in the GitHub repository ntygod/ZhiWei (137 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 793 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
weekly-review
Pull together the week's open tasks, GitHub notifications, Canvas missing assignments, and remembered context into one retrospective-style summary.
inbox-triage
Summarize unread Gmail messages Alfred Core has already synced, and offer to draft or schedule follow-up actions -- never sends or deletes anything on its own.
morning-brief
Render Alfred Core's deterministic morning brief and deliver a short, warm rewrite of it without changing any fact, date, or link it contains.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
bo-process-optimization
A method for examining a business workflow to find waiting, rework, handoff waste, and other delays, then proposing improvements and ways to measure them. It separates observed facts from possible explanations and suggestions.
bo-status-report
A template and set of rules for writing factual operational status reports for a given period. It covers completed, ongoing, blocked, and measured work without filling gaps with guesses.