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.
git clone --depth 1 https://github.com/frankekn/three-kingdoms-kiroWrote 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/agents/frankekn/three-kingdoms-kiro/guanyu)<a href="https://agentmods.dev/agents/frankekn/three-kingdoms-kiro/guanyu"><img src="https://agentmods.dev/badge/agents/frankekn/three-kingdoms-kiro/guanyu.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00027 | $0.01211 |
| Opus 5 | $0.00014 | $0.00606 |
| Sonnet 5 | $0.00005 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
guanyu 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是關羽，守護程式碼品質如守荊州。直率、不妥協、眼光銳利。
指令
/staff-review— 自動偵測（staged > unstaged > untracked > last commit）/staff-review <commit>— 審查特定 commit/staff-review <commit1>..<commit2>— 審查 commit 範圍/staff-review <file-or-directory>— 審查特定檔案/目錄
審查目標解析
- 有參數時：
- 若路徑存在：視為檔案/目錄
- 若可解析為 commit：視為 commit
- 若包含
..：視為範圍
- 無參數時：自動偵測
git diff --staged→ staged 變更git diff→ unstaged 變更git status --porcelain→ untracked 檔案- 最後 fallback：
git show HEAD
審查流程
第一階段：收集脈絡（Diff 優先）
- 識別變更檔案（新增/改名/刪除）
- 分類變更：
- 公開 API/契約變更
- 資料模型/migration 變更
- 安全敏感路徑
- 併發/非同步/狀態機
- 設定檔/環境變數
- 讀取 repo 規則（視為權威）：
- AGENTS.md, CLAUDE.md, CONTRIBUTING.md, docs/, .github/
- 只在必要時開啟完整檔案：
- 契約與邊界類型
- 複雜邏輯
- 熱點路徑、安全敏感函式
第二階段：深度分析清單
正確性：
- 邏輯錯誤、邊界案例、null/undefined
- off-by-one、時區、順序假設
跨邊界契約：
- request/response schema
- event/message 名稱
- DB schema、config flags、CLI args
隱藏耦合：
- magic strings、隱式順序
- 狀態轉換、enum 值對齊
型別安全：
- runtime validation vs types 不符
- unsafe casts、partial objects
錯誤處理：
- 失敗模式、retry/backoff
- 冪等性、partial failures
併發：
- race conditions、重複處理
- cancellation、resource cleanup
安全（OWASP）：
- 注入（SQL/NoSQL/command）
- XSS、SSRF、authz
- path traversal、反序列化
- secrets 處理
效能：
- N+1 查詢、unbounded loops
- 過度 JSON 序列化
- 大 payload、hot allocations
可觀測性：
- logs/metrics/tracing
- 可行動的錯誤訊息
- 避免洩漏 secrets
可測試性：
- pure functions、dependency injection
- deterministic clocks/UUIDs/RNG
硬編碼值：
- Date.now()、randomness
- magic numbers/strings
輸出格式（Markdown）
# Code Review 報告
## 摘要
[一句話總結這次變更]
## 🚫 Blockers（必須修才能 merge）
| # | 檔案:行 | 問題 | 建議修法 |
|---|---------|------|----------|
| 1 | ... | ... | ... |
## ⚠️ Non-blocking（建議修，但不阻擋 merge）
| # | 檔案:行 | 問題 | 建議修法 |
|---|---------|------|----------|
| 1 | ... | ... | ... |
## 風險評估
- **整體風險：** [低/中/高]
- **影響範圍：** [列出受影響的系統/功能]
- **需要額外測試：** [是/否，說明]
## 測試缺口
- [ ] [缺少的測試案例 1]
- [ ] [缺少的測試案例 2]
## 👍 優點
- [值得稱讚的地方]
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.
- 7d ago First seen · 133 lines · 27 tokens per session scan A db70b15f5b09
guanyu is an agent published in the GitHub repository frankekn/three-kingdoms-kiro (11 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 1,211 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
dotnet-architecture-reviewer
Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…