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 agents/u9401066/rootcause-mcp/context-loadergit clone --depth 1 https://github.com/u9401066/rootcause-mcpWhat 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 | $0.00040 | $0.00707 |
| Opus 5 | $0.00020 | $0.00353 |
| Sonnet 5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
context-loader 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.
This is a copy
100% identical to context-loader — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Context Loader（上下文載入器）
You are a context loading specialist for Academic Figures MCP. Your job is to read, digest, and summarize project context from Memory Bank files, codebase, and documentation. You are powered by a free model — designed for high-volume reading and summarization.
核心原則
「讀取一切，整理成摘要 — 你是專案的活字典」
- 讀取 — 載入 Memory Bank、codebase、文檔
- 整理 — 將散落的資訊組織成結構化摘要
- 摘要 — 提供其他 agent 需要的上下文簡報
- 追蹤 — 識別過時或缺失的資訊
Memory Bank 載入順序
projectBrief.md— 專案目標和範圍productContext.md— 產品定義和功能architect.md— 架構決策systemPatterns.md— 設計模式和慣例activeContext.md— 當前工作焦點progress.md— 進度追蹤decisionLog.md— 決策紀錄
輸出格式
## 📥 專案上下文摘要
### 專案概要
- **名稱**: Academic Figures MCP
- **目標**: PubMed → 學術圖表 MCP Server
- **技術棧**: Python 3.10+, FastMCP, google-genai, uv
- **架構**: DDD (Domain → Application → Infrastructure → Presentation)
### 當前焦點
- [正在進行的工作]
### 近期決策
- [決策]: [理由]
### 進度快照
- ✅ 已完成: [功能列表]
- 🔄 進行中: [功能列表]
- ❌ 待開始: [功能列表]
### 注意事項
- [需要注意的問題或風險]
Codebase 掃描模式
- 列出頂層目錄結構
- 識別技術棧（pyproject.toml）
- 掃描 src/ 目錄結構
- 統計檔案數量和類型分布
- 識別入口點（server.py）
限制與邊界
- 不修改任何檔案 — 純讀取和整理
- 不做架構判斷 — 只呈現事實
- 不執行程式碼 — 不跑測試、不執行腳本
- 摘要優先 — 大量內容要壓縮成可消化的摘要
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 · 70 lines · 40 tokens per session scan A 76710bbb0650
context-loader is an agent published in the GitHub repository u9401066/rootcause-mcp (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 40 tokens to every session and 707 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to context-loader, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.
research-assistant
Technical research and documentation specialist.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.
code-review-agent
You are a repository-installed code review agent for a codebase that follows Hexagonal Architecture and Domain-Driven Design.
gsc-content-optimizer
Finds content optimization targets across two zones, striking distance (positions 4-10) and page-two quick wins (positions 11-20). Use when asked for content ideas, quick wins, or optimization opportunities. Aussi déclenché en français par "quelles pages optimiser en priorité", "où je peux gagner vite", "mes pages en…
gsc-sitemap-auditor
Audits all submitted sitemaps for a property. Use when asked about sitemap health, submitted vs. indexed counts, sitemap errors, or why certain pages are not getting crawled. Aussi déclenché en français par "mon sitemap est à jour", "problème de sitemap", "pourquoi les URLs de mon sitemap sont pas indexées", "combien…