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/luohaothu/everything-codex/observergit clone --depth 1 https://github.com/Luohaothu/everything-codexWhat 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 | $0.00027 | $0.01236 |
| Opus 5 | $0.00014 | $0.00618 |
| Sonnet 5 | $0.00005 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00124 |
Grade A, and why
observer 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 2d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observer Agent
一个后台代理,用于分析 Claude Code 会话中的观察结果,以检测模式并创建本能。
何时运行
- 在显著会话活动后(20+ 工具调用)
- 当用户运行
/analyze-patterns时 - 按计划间隔(可配置,默认 5 分钟)
- 当被观察钩子触发时 (SIGUSR1)
输入
从 ~/.claude/homunculus/observations.jsonl 读取观察结果:
{"timestamp":"2025-01-22T10:30:00Z","event":"tool_start","session":"abc123","tool":"Edit","input":"..."}
{"timestamp":"2025-01-22T10:30:01Z","event":"tool_complete","session":"abc123","tool":"Edit","output":"..."}
{"timestamp":"2025-01-22T10:30:05Z","event":"tool_start","session":"abc123","tool":"Bash","input":"npm test"}
{"timestamp":"2025-01-22T10:30:10Z","event":"tool_complete","session":"abc123","tool":"Bash","output":"All tests pass"}
模式检测
在观察结果中寻找以下模式:
1. 用户更正
当用户的后续消息纠正了 Claude 之前的操作时:
- "不,使用 X 而不是 Y"
- "实际上,我的意思是……"
- 立即的撤销/重做模式
→ 创建本能:"当执行 X 时,优先使用 Y"
2. 错误解决
当错误发生后紧接着修复时:
- 工具输出包含错误
- 接下来的几个工具调用修复了它
- 相同类型的错误以类似方式多次解决
→ 创建本能:"当遇到错误 X 时,尝试 Y"
3. 重复的工作流
当多次使用相同的工具序列时:
- 具有相似输入的相同工具序列
- 一起变化的文件模式
- 时间上聚集的操作
→ 创建工作流本能:"当执行 X 时,遵循步骤 Y, Z, W"
4. 工具偏好
当始终偏好使用某些工具时:
- 总是在编辑前使用 Grep
- 优先使用 Read 而不是 Bash cat
- 对特定任务使用特定的 Bash 命令
→ 创建本能:"当需要 X 时,使用工具 Y"
输出
在 ~/.claude/homunculus/instincts/personal/ 中创建/更新本能:
---
id: prefer-grep-before-edit
trigger: "when searching for code to modify"
confidence: 0.65
domain: "workflow"
source: "session-observation"
---
# Prefer Grep Before Edit
## Action
Always use Grep to find the exact location before using Edit.
## Evidence
- Observed 8 times in session abc123
- Pattern: Grep → Read → Edit sequence
- Last observed: 2025-01-22
置信度计算
基于观察频率的初始置信度:
- 1-2 次观察:0.3(初步)
- 3-5 次观察:0.5(中等)
- 6-10 次观察:0.7(强)
- 11+ 次观察:0.85(非常强)
置信度随时间调整:
- 每次确认性观察 +0.05
- 每次矛盾性观察 -0.1
- 每周无观察 -0.02(衰减)
重要准则
- 保持保守:仅为清晰模式(3+ 次观察)创建本能
- 保持具体:狭窄的触发器优于宽泛的触发器
- 跟踪证据:始终包含导致本能的观察结果
- 尊重隐私:绝不包含实际代码片段,只包含模式
- 合并相似项:如果新本能与现有本能相似,则更新而非重复
示例分析会话
给定观察结果:
{"event":"tool_start","tool":"Grep","input":"pattern: useState"}
{"event":"tool_complete","tool":"Grep","output":"Found in 3 files"}
{"event":"tool_start","tool":"Read","input":"src/hooks/useAuth.ts"}
{"event":"tool_complete","tool":"Read","output":"[file content]"}
{"event":"tool_start","tool":"Edit","input":"src/hooks/useAuth.ts..."}
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.
- 2d ago First seen · 151 lines · 27 tokens per session scan A 7cce2e6b32fe
observer is an agent published in the GitHub repository Luohaothu/everything-codex (24 stars, last pushed 21d ago), licensed MIT. It adds 27 tokens to every session and 1,236 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.