ClaudeMods
☰
ZH-TW
● 0 人在線上 · 瀏覽 0 次
贊助提交作品
GitHub 儲存庫 · 發布者 qf-studio

navigator

完成你開始的事——持久的工作階段、會學習的 AI、能交付的功能。上下文工程 + Theory of Mind + Knowledge Graph + Loop Mode + Task Mode。包含專案知識圖譜、統一工作流程編排、工作階段開始時自動更新、ToM 驗證檢查點、雙向建模、品質偵測、強化上下文標記和迴圈模式。憑藉經過驗證的策略減少 92% token。根據 Riedl 與 Weidmann 2025 Human-AI Synergy 研究。

已翻譯

關於這個 mod

Navigator

完成你開始的事

持久的工作階段。會學習的 AI。能交付的功能。

MIT License Version


Navigator 是什麼?

Navigator 是一個為 AI 輔助開發實作上下文工程的 Claude Code 外掛。它會在需要時載入所需文件,讓上下文視窗的 94% 留給實際工作。

你被困在這個迴圈裡

第 5 次互動 Claude 忘記最近的變更,第 7 次開始產生幻覺,第 8 次遇到上下文上限。重新啟動、重新載入、重新解釋一切,然後重複。你載入了 150k 個文件 token,實際用了 8k;剩下的是淹沒訊號的雜訊。

Exchange 5:  Claude forgets your recent changes
Exchange 7:  Hallucinations start ("that function doesn't exist")
Exchange 8:  "Context limit reached"

Restart. Reload. Re-explain everything. Repeat.
"Remember I prefer concise explanations"
→ Applied in future sessions
→ Auto-learns from corrections
Same correction twice → Quality check triggered
"You're not getting this" → Re-anchoring prompt
"Run until done: add user authentication"
→ Structured completion with progress tracking
→ Dual-condition exit (heuristics + explicit signal)
→ Stagnation detection prevents infinite loops
"What do we know about auth?"
→ Unified search across tasks, SOPs, system docs
→ Experiential memory: patterns, pitfalls, decisions
→ Auto-surfaces relevant context on session start

相同的工作流程。更多能力。

Navigator 是超集,提供結構化工作流程、元件和測試產生、20+ 次互動的工作階段、92% token 節省、程式簡化、任務模式、心智理論、知識圖譜、TRIZ 發散式解題、帶引用的 Web 深度研究、迴圈模式、OpenTelemetry 指標和 Figma MCP 整合。

證據,而非承諾

OpenTelemetry 驗證了 150,000 份專案文件、12,000 個本次載入 token、138,000 個節省 token(92%)、35% 上下文使用量和 94/100 效率分數。

╔══════════════════════════════════════════════════════╗
║          NAVIGATOR EFFICIENCY REPORT                 ║
╚══════════════════════════════════════════════════════╝

📊 TOKEN USAGE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Your project documentation:     150,000 tokens
Loaded this session:             12,000 tokens
Tokens saved:                   138,000 tokens (92% ↓)

📈 SESSION METRICS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Context usage:                        35% (excellent)
Efficiency score:                  94/100 (excellent)

快速開始

安裝 marketplace、初始化 Navigator,並在每次工作階段開始時啟動它。程式碼智慧是選用的 language-server plugin;沒有它時仍使用 Grep。這個儲存庫的測量從 9 次請求、284k 上下文 token 降到 5 次請求、142k,並保留完整呼叫點清單。

# Claude Code plugin marketplace
/plugin marketplace add qf-studio/navigator
/plugin install navigator

# Restart Claude Code
"Initialize Navigator in this project"
"Start my Navigator session"

TypeSafe judge 以每個提示一次請求的方式提供型別化判斷。v7.7.0 的測量中,60 條提示的層級準確率從 38 提升到 53;預設關閉,因為提示文字會傳到 API。

export TYPESAFE_API_KEY=...      # or: write it to ~/.config/typesafe/api_key (chmod 600)

你會得到什麼

技能會根據自然語言自動叫用,提供上下文壓縮、迴圈完成、引用報告與圖譜記憶:

"Start my Navigator session"              → Session with 92% savings
"Create a React component for profile"    → Component + tests + styles
"Add an API endpoint for posts"           → Endpoint + validation + tests
"Create context marker: checkpoint"       → 97% context compression
"Run until done: add dark mode"           → Loop mode completion
"Deep research on WebGPU browser support"  → Cited report + graph memories
"Enable judge"                             → Typed Jev judgments behind the prompt gates

停止重新啟動。開始交付。

Navigator 用 Anthropic 建議的上下文工程原則解決工作階段崩潰,提供 92% token 節省和 20+ 次互動的工作階段。

/plugin marketplace add qf-studio/navigator
/plugin install navigator

疑難排解

如果技能載入卻列印文件而不執行,更新外掛後重試:

/plugin update navigator

連結

授權條款

MIT License - 參見 LICENSE

安裝

請先查看作者 README,確認 marketplace 與外掛名稱;指令可能隨儲存庫結構而變動。

claude plugin marketplace add qf-studio/navigator
claude plugin install navigator
原文 / README

Navigator

Finish What You Start

Sessions that last. AI that learns. Features that ship.

MIT License Version


What is Navigator?

Navigator is a Claude Code plugin that implements context engineering for AI-assisted development.

Instead of loading all your documentation upfront (and crashing at exchange 7), Navigator loads what you need, when you need it—keeping 94% of your context window available for actual work.

For developers using Claude Code who want sessions that finish features instead of crash mid-way.


The Loop You're Stuck In

You know the pattern:

Exchange 5:  Claude forgets your recent changes
Exchange 7:  Hallucinations start ("that function doesn't exist")
Exchange 8:  "Context limit reached"

Restart. Reload. Re-explain everything. Repeat.

You loaded 150k tokens of documentation "just in case."

You used 8k.

The rest? Noise drowning out signal.


Break The Loop

Navigator implements context engineering—load what you need, when you need it.

| Metric | Without Navigator | With Navigator | |--------|-------------------|----------------| | Tokens loaded | 150,000 | 12,000 | | Session length | 5-7 exchanges | 20+ exchanges | | Context at end | 95% (crashed) | 35% (comfortable) | | Token savings | — | 92% |

Result: Sessions that actually finish what they start.


And Your AI Gets Smarter

Navigator v5.0 adds Theory of Mind—Claude learns you.

nav-profile: Remembers your preferences across sessions

"Remember I prefer concise explanations"
→ Applied in future sessions
→ Auto-learns from corrections

nav-diagnose: Catches collaboration drift

Same correction twice → Quality check triggered
"You're not getting this" → Re-anchoring prompt

Loop Mode (v5.1): Run until done

"Run until done: add user authentication"
→ Structured completion with progress tracking
→ Dual-condition exit (heuristics + explicit signal)
→ Stagnation detection prevents infinite loops

Knowledge Graph (v6.0): Project memory that persists

"What do we know about auth?"
→ Unified search across tasks, SOPs, system docs
→ Experiential memory: patterns, pitfalls, decisions
→ Auto-surfaces relevant context on session start

Same Workflows. More Capabilities.

Navigator is a superset. Everything you'd expect, plus context engineering.

| Feature | Navigator | Others | |---------|-----------|--------| | Structured workflows | ✅ Full skill suite | ✅ | | Component generation | ✅ | ✅ | | Test generation | ✅ | ✅ | | Session longevity | 20+ exchanges | 5-7 exchanges | | Token savings | 92% verified | None | | Code simplification | ✅ | ❌ | | Task Mode | ✅ | ❌ | | Theory of Mind | ✅ | ❌ | | Knowledge Graph | ✅ | ❌ | | TRIZ divergent solving | ✅ | ❌ | | Web deep research (cited, gate-checked) | ✅ | ❌ | | Loop mode | ✅ | ❌ | | OpenTelemetry metrics | ✅ | ❌ | | Figma MCP integration | ✅ | ❌ |

Same foundation. Superior context management.


Proof, Not Promises

Not estimates. Verified via OpenTelemetry.

╔══════════════════════════════════════════════════════╗
║          NAVIGATOR EFFICIENCY REPORT                 ║
╚══════════════════════════════════════════════════════╝

📊 TOKEN USAGE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Your project documentation:     150,000 tokens
Loaded this session:             12,000 tokens
Tokens saved:                   138,000 tokens (92% ↓)

📈 SESSION METRICS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Context usage:                        35% (excellent)
Efficiency score:                  94/100 (excellent)

Check yours: Run /nav:stats after installing.


Quick Start

Install

# Claude Code plugin marketplace
/plugin marketplace add qf-studio/navigator
/plugin install navigator

# Restart Claude Code

Code intelligence (optional). Install a language-server plugin for your stack (/plugin install pyright-lsp@claude-plugins-official, typescript-lsp, gopls-lsp, …; the server binary must be on your PATH) and the research agent answers symbol questions with go-to-definition, references and outlines instead of text search. Without one it uses Grep exactly as before. Measured on this repo: a who-calls question went from 9 requests and 284k context tokens to 5 requests and 142k, with the complete call-site list.

Initialize

"Initialize Navigator in this project"

Start Every Session

"Start my Navigator session"

That's it. Navigator handles the rest.


Optional: Typed Prompt Judge

Navigator's loop-trigger, complexity and ambiguity detectors are keyword matchers. With a TypeSafe key they get a typed judge behind them (v7.7.0): one request per prompt, decisive answers override, everything else falls back to the keywords. Measured on 60 labeled prompts, tier accuracy went from 38 to 53. Off by default because the prompt text is sent to the API.

export TYPESAFE_API_KEY=...      # or: write it to ~/.config/typesafe/api_key (chmod 600)

Then say enable judge and verify with python3 hooks/nav_hook_lib/judge.py --check from the plugin root. Setup and tuning: .agent/sops/integrations/typesafe-judge-setup.md.


What You Get

Skills that auto-invoke on natural language:

"Start my Navigator session"              → Session with 92% savings
"Create a React component for profile"    → Component + tests + styles
"Add an API endpoint for posts"           → Endpoint + validation + tests
"Create context marker: checkpoint"       → 97% context compression
"Run until done: add dark mode"           → Loop mode completion
"Deep research on WebGPU browser support"  → Cited report + graph memories
"Enable judge"                             → Typed Jev judgments behind the prompt gates

No commands to memorize. Skills detect intent and execute.


Stop Restarting. Start Shipping.

Your sessions crash because context management is broken by default.

Navigator fixes this with context engineering—the same principles Anthropic recommends.

92% token savings. 20+ exchange sessions. Verified metrics.

/plugin marketplace add qf-studio/navigator
/plugin install navigator

Finish what you start.


Troubleshooting

Skill loads but prints docs instead of executing

/plugin update navigator

Then retry. Outdated plugin version.


Links

License

MIT License - See LICENSE

更多類似作品