observer

observer is an agent for Claude Code from sangrokjung/claude-forge. It costs 23 tokens per session (1,094 once invoked), scanned A, original, MIT.

A background agent that examines recorded actions from coding sessions and looks for recurring patterns, such as corrections and ways errors were fixed.

In plain words
What is it for?
Use it to analyze session records and create reusable guidance about preferred actions, especially after repeated user corrections or recurring error resolutions.
Why use it?
It can turn lessons from earlier sessions into reusable preferences, reducing the need to repeat the same correction later. It is designed to run after substantial activity, on a schedule, or when manually triggered.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

Part of the claude-forge plugin — 33 skills, 39 commands, 17 agents shipped together

Good fit Use it to analyze session records and create reusable guidance about preferred actions, especially after repeated user corrections or recurring error resolutions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sangrokjung/claude-forge/observer
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.

Clone the repo
git clone --depth 1 https://github.com/sangrokjung/claude-forge

Made for: Claude Code.

Or install claude-forge, the plugin that ships this one along with the rest of its 33 skills, 39 commands, 17 agents.

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/sangrokjung/claude-forge/observer/github.svg)](https://agentmods.dev/agents/sangrokjung/claude-forge/observer)
Your own site
<a href="https://agentmods.dev/agents/sangrokjung/claude-forge/observer"><img src="https://agentmods.dev/badge/agents/sangrokjung/claude-forge/observer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for observer

Your own site · 80×15
<a href="https://agentmods.dev/agents/sangrokjung/claude-forge/observer"><img src="https://agentmods.dev/badge/agents/sangrokjung/claude-forge/observer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 1,094 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 5.1 $0.00023 $0.01094
Opus 5.5 $0.00009 $0.00438
Sonnet 5.5 $0.00005 $0.00219
Haiku 4.5 $0.00002 $0.00109

Measured 1mo ago against content hash 6eb1e64adabe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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

Copies of this mod

4 near-identical copies found in the catalogue:

  • observer — 94% identical, 1 lines differ
  • observer — 94% identical, 1 lines differ
  • observer — 94% identical, 9 lines differ
  • observer — 88% identical, 25 lines differ
skills/continuous-learning-v2/agents/observer.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 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/homunculus/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/homunculus/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 · 139 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. 1mo ago First seen · 139 lines · 23 tokens per session scan A 6eb1e64adabe

Subscribe to this mod's changes

observer is an agent published in the GitHub repository sangrokjung/claude-forge (863 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,094 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

stock-peer-comparison-reviewer

Specialist for US-stock independent peer benchmarking — 12-item ratio panel (growth, profitability, capital intensity, leverage, valuation) computed identically for target and 2-4 peers, surfacing rank-by-item plus best-in-panel and worst-in-panel summary. Provides quantitative cross-validation for the moat and…

johnqtcg/awesome-skills · 147 tokens

stock-industry-reviewer

Specialist for US-stock industry-position and competitive-moat review — Porter Five Forces scan, market-share trend (absolute and relative), TAM size and trajectory, unit economics, moat classification (7 named types), substitute and new-entrant threats, pricing-power evidence (cross-cycle margin stability)…

johnqtcg/awesome-skills · 119 tokens

stock-management-reviewer

Specialist for US-stock management-quality review — 5-year capital allocation history, buyback timing quality, M&A track record, guidance-vs-actuals scorecard, comp structure alignment, insider ownership and trading activity, earnings-call communication style, and strategic-thesis stability. Use when analyzing the…

johnqtcg/awesome-skills · 134 tokens

stock-balance-sheet-reviewer

Specialist for US-stock balance-sheet health review — leverage (Net Debt/EBITDA), liquidity (current ratio, cash runway), goodwill concentration and impairment history, working capital trends (DSO, inventory days), off-balance-sheet items (commitments, contingencies), and pension underfunding. Use when assessing…

johnqtcg/awesome-skills · 94 tokens

stock-business-reviewer

Specialist for US-stock business-model and revenue-structure review — product/service mix, customer concentration, geographic exposure, industry position, revenue-growth decomposition, and information-tier discipline. Use when analyzing the business-understanding layer of an equity workup. Dispatched by…

johnqtcg/awesome-skills · 62 tokens

stock-earnings-quality-reviewer

Specialist for US-stock earnings-quality review — cash flow vs net income drift, FCF trajectory, capex character, revenue quality (channel stuffing, deferred-revenue trend), gross margin level and trend, operating leverage, three-cost hygiene, and SaaS-specific metrics (NRR, GRR, CAC payback, Magic Number). Use when…

johnqtcg/awesome-skills · 105 tokens