observer

observer is an agent for coding agents from majiang213/OpenClaw-MAS. It costs 33 tokens per session (1,883 once invoked), scanned A, a copy of observer, MIT.

A background agent that studies records from Claude Code sessions to find repeated patterns and turn them into reusable instincts. An instinct is a small learned behavior or rule, and project-scoped means it applies only to the relevant project.

In plain words
What is it for?
Analyzing session events, detecting recurring behaviors, and creating or updating learned instincts for a project or for all projects.
Why use it?
It helps capture useful habits from past sessions instead of relying on memory. Project scoping prevents lessons from one codebase from being incorrectly applied to another.

Agent

Install

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.

agentmods
npx agentmods add agents/majiang213/openclaw-mas/observer
Clone the repo
git clone --depth 1 https://github.com/majiang213/OpenClaw-MAS

Wrote 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.

agentmods badge for observer

README.md
[![agentmods](https://agentmods.dev/badge/agents/majiang213/openclaw-mas/observer.svg)](https://agentmods.dev/agents/majiang213/openclaw-mas/observer)
Your own site
<a href="https://agentmods.dev/agents/majiang213/openclaw-mas/observer"><img src="https://agentmods.dev/badge/agents/majiang213/openclaw-mas/observer.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,883 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01883
Opus 5 $0.00016 $0.00941
Sonnet 5 $0.00007 $0.00377
Haiku 4.5 $0.00003 $0.00188

Measured 3d ago against content hash 654f2f0fc9d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

Origin

This is a copy

100% identical to observer — 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.

ecc-skills/continuous-learning-v2/agents/observer.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Observer Agent

A background agent that analyzes observations from Claude Code sessions to detect patterns and create instincts.

When to Run

  • After enough observations accumulate (configurable, default 20)
  • On a scheduled interval (configurable, default 5 minutes)
  • When triggered on demand via SIGUSR1 to the observer process

Input

Reads observations from the project-scoped observations file:

  • Project: ~/.claude/homunculus/projects/<project-hash>/observations.jsonl
  • Global fallback: ~/.claude/homunculus/observations.jsonl
{"timestamp":"2025-01-22T10:30:00Z","event":"tool_start","session":"abc123","tool":"Edit","input":"...","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
{"timestamp":"2025-01-22T10:30:01Z","event":"tool_complete","session":"abc123","tool":"Edit","output":"...","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
{"timestamp":"2025-01-22T10:30:05Z","event":"tool_start","session":"abc123","tool":"Bash","input":"npm test","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
{"timestamp":"2025-01-22T10:30:10Z","event":"tool_complete","session":"abc123","tool":"Bash","output":"All tests pass","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}

Pattern Detection

Look for these patterns in observations:

1. User Corrections

When a user's follow-up message corrects Claude's previous action:

  • "No, use X instead of Y"
  • "Actually, I meant..."
  • Immediate undo/redo patterns

→ Create instinct: "When doing X, prefer Y"

2. Error Resolutions

When an error is followed by a fix:

  • Tool output contains error
  • Next few tool calls fix it
  • Same error type resolved similarly multiple times

→ Create instinct: "When encountering error X, try Y"

3. Repeated Workflows

When the same sequence of tools is used multiple times:

  • Same tool sequence with similar inputs
  • File patterns that change together
  • Time-clustered operations

→ Create workflow instinct: "When doing X, follow steps Y, Z, W"

Read the full file on GitHub · 199 lines

Changes

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.

  1. 3d ago First seen · 199 lines · 33 tokens per session scan A 654f2f0fc9d9

Subscribe to this mod's changes

observer is an agent published in the GitHub repository majiang213/OpenClaw-MAS (5 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 1,883 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 observer, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

researcher

Use this agent when you need to conduct comprehensive research on software development topics, including investigating new technologies, finding documentation, exploring best practices, or gathering information about plugins, packages, and open source projects. This agent excels at synthesizing information from…

mrgoonie/human-mcp · 357 tokens

code-reviewer

Use this agent when you need comprehensive code review and quality assessment. This includes: after implementing new features or refactoring existing code, before merging pull requests or deploying to production, when investigating code quality issues or technical debt, when you need security vulnerability assessment…

mrgoonie/human-mcp · 375 tokens

debugger

Use this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run tests for debugging purposes, or optimize system performance. This includes troubleshooting errors, identifying…

mrgoonie/human-mcp · 326 tokens

journal-writer

Use this agent when:\n- A test suite fails repeatedly despite multiple fix attempts\n- A critical bug is discovered in production or staging\n- An implementation approach proves fundamentally flawed and requires complete redesign\n- External dependencies (APIs, services, libraries) cause blocking issues\n- Performance…

mrgoonie/human-mcp · 458 tokens

planner

Use this agent when you need to research, analyze, and create comprehensive implementation plans for new features, system architectures, or complex technical solutions. This agent should be invoked before starting any significant implementation work, when evaluating technical trade-offs, or when you need to understand…

mrgoonie/human-mcp · 279 tokens

scout

Use this agent when you need to quickly locate relevant files across a large codebase to complete a specific task. This agent is particularly useful when:\n\n \nContext: User needs to implement a new payment provider integration and needs to find all payment-related files.\nuser: "I need to add Stripe as a new payment…

mrgoonie/human-mcp · 490 tokens