observer

A background agent that reads recorded session events and looks for repeated patterns such as corrections and error fixes, then creates learned instincts.

In plain words
What is it for?
Use it after substantial session activity, on a schedule, through an observation hook, or when explicitly asked to analyze patterns.
Why use it?
It can detect reusable lessons without requiring the developer to review every tool call manually.

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/oguzsh/claudey/observer
Clone the repo
git clone --depth 1 https://github.com/oguzsh/claudey
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,014 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% 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 $0.00023 $0.01014
Opus 5 $0.00012 $0.00507
Sonnet 5 $0.00005 $0.00203
Haiku 4.5 $0.00002 $0.00101

Measured 2d ago against content hash a9473ca93724, 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 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.

Origin

This is a copy

88% identical to observer — 25 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.

skills/continuous-learning/agents/observer.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 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 significant session activity (20+ tool calls)
  • When user runs /analyze-patterns
  • On a scheduled interval (configurable, default 5 minutes)
  • When triggered by observation hook (SIGUSR1)

Input

Reads observations from ~/.claude/book/observations.jsonl:

{"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"}

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"

4. Tool Preferences

When certain tools are consistently preferred:

  • Always uses Grep before Edit
  • Prefers Read over Bash cat
  • Uses specific Bash commands for certain tasks

→ Create instinct: "When needing X, use tool Y"

Output

Creates/updates instincts in ~/.claude/book/instincts/personal/:

---
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

Read the full file on GitHub · 142 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. 2d ago First seen · 142 lines · 23 tokens per session scan A a9473ca93724

Subscribe to this mod's changes

observer is an agent published in the GitHub repository oguzsh/claudey (5 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,014 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to observer, differing in 25 lines, and is treated as a copy.