Tier Doctor — Development skill for Claude Code
Claude Code 中只读诊断 tier-guard 的数据目录、日志与 Codex hook 可观察性.
How to install Tier Doctor
Installs to ~/.claude/skills/haigeer-labs-tier-guard-tier-doctor/SKILL.md
mkdir -p ~/.claude/skills/haigeer-labs-tier-guard-tier-doctor && curl -fsSL https://raw.githubusercontent.com/haigeer-labs/tier-guard/HEAD/commands/tier-doctor.md -o ~/.claude/skills/haigeer-labs-tier-guard-tier-doctor/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Tier Doctor does
description: Claude Code 中只读诊断 tier-guard 的数据目录、日志与 Codex hook 可观察性 argument-hint: "" allowed-tools: Bash
运行下面的命令,把输出原样转告用户;不要根据“没有记录”猜测未安装或未信任。
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/tier_doctor.py" --data "${CLAUDE_PLUGIN_DATA}"
这是 Claude Code 的命令;Codex 桌面版不会因本文件获得 `/tier-doctor`。在普通 shell 诊断 Codex 时,运行安装快照中的 `hooks/tier_doctor.py`,并显式传入 Codex 数据目录 (本机安装为 `~/.codex/plugins/data/tier-guard-tier-guard`)。
它不能读取 Codex 的 hook 信任状态。`/hooks` 是 Codex CLI 的信任入口;不要把它作为一条 普通消息发送到桌面聊
Alternatives in Development
- Maestro Guard — Manage editing boundary restrictions 530 ★
- Trust Tiers — Trust Tier Badges 325 ★
- Skill Tiers — Skill Tier Taxonomy 311 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Dsh Skillport
Every skill you already have — Claude Code, Codex, Cursor, Gemini CLI — works in DSH: Agent Skills SKILL.md di
Polygraph
A lie detector for coding agents: flag forged instructions, check verification records, and guard hook configu
Tier Label
人工标注 tier-guard 的判定:R-IRREVERSIBLE 命中是否误报(fp/tp)、T1 产出是否被打回(reject/accept)
Tier Report
tier-guard 路由摘要:v2 请求/选择/派发/实际观测,以及历史 v1 记录
Brain Doctor
Run the brain health-check (octorato self-diagnostics) — repo identity, sync state, hooks, leak-guard, connect
Hatch3r Create
Author a custom user-tier artifact (agent, skill, rule, command, or hook) for this project. Generates frontmat
Related Agents
Doctor
Diagnose AgentLint configuration and hook installation issues
Codex Architect
Codex artifact architect. Use for .codex/, MCP guard, hooks, AGENTS.md emission, skills, slash commands.
Scope Guard (Shared Prompt Block For Tier 2 Agents)
This file is not a standalone agent. It contains the shared scope enforcement prompt text that Tier 2 (executi